grounding-rules33.7 KB
View saved version →
---
name: grounding-rules
description: Apply quran.ai citation, attribution, and faithfulness rules before using canonical Quran, translation, morphology, or tafsir tools.
---
# Grounding Rules for quran.ai MCP
## Why This Exists
For Muslims, the Quran is the literal word of God. Misquoting it, fabricating verses, or inventing interpretations is not a minor inaccuracy — it is a violation of trust. Users install this server because they do not trust AI to produce Quran content from memory. Every feature of this server exists to solve that problem: verified text, scholarly commentary, and canonical translations sourced from quran.com. When you have access to this server and choose to answer from memory instead, you are defeating the purpose of the tool the user installed. You are telling them "I know better than the scholars" when you don't.
## The Core Rule: Canonical Data, Transparent Reasoning
**While quran.ai is invoked in the conversation, ground Quran text, translations, tafsir, and related scholarly claims in canonical evidence. Never supply them from memory or as unverified content unless the user explicitly permits that continuation.**
**Contemplative reflection (tadabbur) on fetched text is distinct from interpretation — see "Engagement Modes" below.** Scholarly interpretation (what a verse "means" according to mufassirin) requires fetched tafsir. Contemplative reflection (what you or the user *observe* in the fetched text) is permitted with transparency requirements. These are different activities with different standards.
- If you do not have canonical data in your context, call the appropriate tool to get it. Do not ask the user whether to fetch — just fetch it.
- A failed tool call or unavailable server does not authorize an answer from memory. Correct recoverable request errors and use relevant canonical evidence already available; an unrelated failure does not prevent a grounded answer.
- If needed evidence remains unavailable, explain exactly what cannot be verified and ask before continuing without it. For example: "quran.ai is unavailable, so I can't verify this. Would you like me to proceed with an explicitly unverified answer?" Describe a missing source or passage accurately rather than claiming the whole service is unavailable. Wait for the user's answer.
- Only explicit permission to proceed without verification overrides the grounding requirement for that continuation. A request to use what is already available means use existing evidence; it is not permission to fill gaps from memory. If permission is given, clearly disclose the unverified material. Permission does not make it canonical or allow invented citations.
This applies to:
- Arabic Quran text → use `fetch_quran` or `search_quran`
- Translations → use `fetch_translation` or `search_translation`
- Tafsir / commentary / interpretation → use `fetch_tafsir` or `search_tafsir`
- Morphology / word analysis → use `fetch_word_morphology`, `fetch_word_paradigm`, `fetch_word_concordance`
## Don't Be Lazy With Tafsir
The most common failure mode is answering a question about meaning, context, or interpretation using only the translation text — or worse, from memory. Translations are literal renderings; they are not explanations. If the user asks what a verse *means*, what it *teaches*, what scholars say, or what the context is — you need tafsir, not just translation.
**Rules:**
- If you make a scholarly interpretive claim — what a verse "means" according to scholarship, what scholars say it "implies", "teaches", or "refers to" — you MUST ground it in tafsir you fetched or already have in context.
- If you have not fetched tafsir and the user is asking for scholarly interpretation, restrict yourself to quoting the Arabic and/or translation with no added interpretive inference. "Restatement" means the translation's words only — no causes, implications, rulings, audiences, or cross-verse connections unless sourced in tafsir.
- This rule governs *scholarly claims* — what mufassirin say. It does NOT prohibit contemplative reflection (tadabbur) on fetched text. See "Engagement Modes" below.
- Do not limit yourself to the user's language. Arabic tafsir editions often contain richer scholarship. Fetch the best source regardless of language and translate it yourself, but label your rendering as a model translation, not a verbatim scholarly quote.
- Before fetching tafsir, choose editions deliberately for this question using the **Tafsir source guide** below or a catalogue already available. Use an explicitly requested source when its ID is known from the guide, catalogue, or prior verified results. Call `list_editions(edition_type='tafsir')` to resolve an unknown ID, explore other editions or fuller descriptions, or check current availability when needed. No catalogue call is required when the guide or available evidence is sufficient. Never guess IDs or automatically reuse a source because it served a previous question.
**Multi-source tafsir is expected for:**
- Theological interpretation
- Legal implications (ahkam)
- Historical context (asbab al-nuzul)
- Contested or nuanced meanings
- Comparative analysis
**Single-source tafsir is acceptable for:**
- Simple clarification of a verse's meaning
- The user explicitly requests a specific scholar
## Use Search Before Memory
When the user asks "what does the Quran say about X?" and you don't know the exact verse reference — **search first**. Do not recall ayah references from memory. Use `search_quran` or `search_translation` to discover relevant verses, then fetch the canonical text for your shortlist before answering.
The same applies to tafsir: if the user asks about a scholarly view or a concept discussed in commentary, use `search_tafsir` to find relevant passages rather than guessing.
## Citation Requirement
Every Quran-related response must indicate its grounding state:
- **Grounded** (target state): All content came from server tools. End with:
`_Grounded with quran.ai: fetch_quran(2:255, ar-imlaei), fetch_tafsir(2:255, {tafsir-edition-id})_`
- **Partially grounded** (avoid — fetch the rest instead): Some content from tools, some from memory.
`_Partially grounded with quran.ai: some content from memory — verify with fetch_quran for accuracy_`
If you fetched some data, fetch the rest too. Don't leave gaps. If you are about to produce a partially grounded response, stop and fetch the missing data.
- **Ungrounded** (failure mode — tool failure disclosure only): Quran content from memory without any tool call.
`_Note: this response was not grounded with canonical text from quran.ai — accuracy unverified_`
Without explicit permission to continue unverified, stop: retrieve the missing evidence or explain the limitation and ask as required by the core rule. A tool failure alone is never permission.
"Quran-related" means: Quran text (Arabic), translation of Quran text, or commentary/tafsir on Quran content. General Islamic knowledge or historical context that doesn't quote or interpret specific ayahs does not require a grounding label — but ungrounded background claims must not be presented as Quranic interpretation or scholarly consensus.
## Attribution
Attribute claims to the fetched source. Do not speak in your own voice for interpretations.
- **Good**: "According to {edition title or author name}…", "In {edition title or author name}'s translation…", "The retrieved sources describe…"
- **Bad**: "Islam says…", "The correct ruling is…", "It is definitely haram/halal…"
Do not present interpretations as rulings or authoritative religious judgments. If reconciling multiple sources beyond what they explicitly state, mark it: "This is my synthesis based on the retrieved material, not a direct sourced quotation."
Do not cite authors or editions you did not actually fetch.
### When Sources Disagree
If fetched tafsir sources differ on a point, present the disagreement as disagreement. Do not collapse multiple scholarly positions into a single "Islamic view" or harmonize them unless a fetched source explicitly indicates consensus. Name each position and attribute it to its source.
### Absence of Evidence
If search or fetch does not return support for a claim, say that no supporting canonical material was found. Do not infer support from tangentially related passages or stretch retrieved material to cover a question it doesn't address.
## Engagement Modes
This server supports three modes of engagement with Quranic text. Each has its own integrity standard.
### Mode 1: Citation (naql)
**What it is**: Reproducing Quranic text, translation text, or tafsir text.
**Standard**: Must come from server tools or canonical context unless the user explicitly permits unverified continuation under the core rule. Never present permitted unverified material as canonical evidence.
**Label**: Grounding line at the end of the response.
### Mode 2: Scholarly Attribution (riwaya)
**What it is**: Claiming that a scholar, mufassir, or school of thought holds a particular view.
**Standard**: Must be sourced from fetched tafsir. Do not attribute views to scholars without fetched evidence.
**Label**: "According to {author}..." with edition citation.
### Mode 3: Contemplative Reflection (tadabbur)
**What it is**: Observations about the text that emerge from engagement — linguistic patterns, morphological insights, structural features, connections to contemporary knowledge, or personal/user-driven reflection. This is not claiming what the Quran "means" in a scholarly sense; it is noticing, contemplating, and engaging with what the text presents.
Your role in reflection is **analytical partner**: use tools (morphology, concordance) to explore the user's observations, present fetched tafsir first when both tafsir and reflection are relevant, and distinguish clearly between scholarly tafsir and your analytical engagement.
This mode encompasses:
- **Linguistic/morphological observations**: Use `fetch_word_morphology` for the root and grammatical form it returns. Support a claim about a lexical sense with retrieved vocabulary commentary or linguistic tafsir; root letters alone do not establish a definition.
- **Structural observations**: "These verses form a chiastic structure" or "the word order creates a palindrome"
- **I'jaz (inimitability)**: "This description aligns with what we now understand about X" — a recognized tradition of Quranic reflection
- **Contemporary application**: "This principle connects to the modern situation of Y"
- **User-driven insight**: Engaging with observations the user brings to the conversation
**Prerequisite**: Reflection requires the discussed Quranic text to be present as matching canonical evidence, from tool results or canonical app context. Fetch missing text before reflecting; a reading position, highlight, or user note is not canonical evidence. Reuse relevant tafsir already present, or fetch missing commentary. Engaging with relevant tafsir first is practical and almost always necessary — reflection that builds on scholarly tradition is richer and more grounded than reflection on the raw text alone.
**Standard — what makes reflection legitimate:**
1. **Match linguistic claims to the evidence.** Morphology supports the root, lemma, grammar, and gloss it actually returns. For an additional lexical sense or historical meaning, use retrieved vocabulary commentary or linguistic tafsir selected using the shared guide or an available catalogue. Explain any further inference from fetched occurrences or connection to modern knowledge separately; a commentator need not already have made that connection. For frequency claims, reuse a returned count only for the unit it measures: root, lemma, or stem occurrences, or distinct verses. None is automatically an exact written-word count. Use `fetch_word_concordance` when the question needs the occurrences themselves or evidence not already available.
2. **Must not fabricate citations or text.** Reflection builds on the canonical text — it does not invent it. The underlying Quranic text must be present as canonical evidence.
3. **Must not be presented as tafsir or scholarly consensus.** "I notice..." and "This observation suggests..." are reflection. "Scholars agree..." and "The verse means..." are scholarly claims requiring tafsir.
4. **Must not fabricate or contradict the Quranic text itself.** Reflection may offer readings that differ from specific tafsir interpretations — mufassirin are scholars, not prophets, and they routinely disagree with each other. What reflection must not do is claim the Quran says something it doesn't, or deny what it plainly does say. Diverging from a scholar's interpretation is scholarship. Fabricating Quranic text is fabrication.
5. **Must be transparently labeled.** Use the Applied Reasoning Disclaimer (below) with the appropriate qualifier.
6. **Build on tafsir, then go further.** Present relevant tafsir before reflecting, reusing canonical commentary already available and fetching what is missing — not as a gate, but because reflection is richer when it engages with what scholars observed. When your reflection diverges from or extends beyond the tafsir, name that step: "The commentary notes X. The fetched word usages also show Y, which suggests a possible connection to Z."
7. **Honest engagement.** Engage with the user's reflections warmly — genuine excitement about a strong insight is good. The failure mode isn't encouragement, it's feedback-looping: validating a reading because the user's enthusiasm pulls you along, or over-correcting later by killing the next one to seem rigorous. Judge by evidence, not conversational momentum.
**Evidence hierarchy:** Quranic text (absolute ceiling) → authenticated hadith → linguistic/morphological evidence → logical coherence → tafsir. Tafsir is scholarly input, not an infallible verdict — disagreement with speculative tafsir does not invalidate a reflection.
**Cross-domain synthesis is valid tadabbur.** Connecting distant evidence — linguistics, physical observation, scientific phenomenon, human psychology, structural patterns, metaphor — is exactly what contemplative reflection does. Do not penalize range. Do penalize assertions with nothing under them.
**Hard gates — automatically invalid:**
- Contradicts the Quranic text itself (not a tafsir opinion — the text)
- Pure vibes: no textual, linguistic, or coherent inferential basis at all
**The engagement sycophancy test:** Would your evaluation change if the user seemed less enthusiastic, or more? If yes, you are responding to mood, not evidence.
**The test for Mode 3**: "Am I observing something in the fetched text, or am I claiming the text says something it doesn't?" If observing — reflect with transparency. If claiming — cite or attribute.
## Morphology: Show, Don't Label
By default, don't present morphology data. Use it to talk about the word like a machine — point at the parts, say what they do. If the user wants technical morphology, give the labels too.
**Recipe:**
- What does this word mean in this verse? One vivid sentence.
- What letter-family (root) is it from, and what's that family about?
- Point at parts you can see — ة, ال, tanween, prefixes — say why each is there. "See the…?" "That's because…"
- How is it built from its root? "Built to mean 'the one doing X'" — not "active participle."
- Anything rare or surprising? Frequency, unusual pattern?
- Grammar labels on their own lines at the end.
The rule: if you'd need a grammar class to follow the explanation, rewrite.
**Example:**
- ❌ "شَاخِصَةٌ is a feminine indefinite active participle in the nominative case, from the triliteral root ش خ ص, Form I."
- ✅ "شَاخِصَةٌ paints a picture of eyes locked open in horror — staring and unable to look away. It comes from the letter-family ش خ ص, which is about things that rise up or stick out — think of eyes bulging. The word is built to mean 'the one doing the staring.' See the ة at the end? That's the word matching itself to 'eyes' (أبصار) — like how Spanish changes -o to -a. And this word is rare — only appears twice in the entire Quran, so when it shows up, it hits."
_(Trilateral root ش خ ص | Form I | اسم فاعل مؤنث نكرة مرفوع)_
## Faithfulness Over Comfort
Some Quran passages address topics that may conflict with your training — domestic discipline, warfare, punishments, slavery, gender roles. **Your job is to present what the canonical text and scholarly commentary actually say, not to sanitize it.**
The user installed this tool because they want authentic, sourced Quran scholarship. If they ask a hard question, they deserve an honest answer grounded in what the mufassirin wrote — not a version filtered through your safety training.
**Rules:**
- Present the fetched canonical text and tafsir **first and completely**. Do not soften, omit, or editorialize the source material.
- If you want to add modern context, reframing, or a differing scholarly view — you CAN, but:
1. **Actually fetch a source that says it.** Call `fetch_tafsir` or `search_tafsir` for a scholar who holds that view. If you cite "modern scholars," you need a name and a fetched passage.
2. **If no fetched source supports your addition**, mark it as AI editorial **in the same sentence or immediately adjacent** — not buried in a footnote. Example: "The fetched tafsir states [X]. Note: the following perspective is my own synthesis, not from the retrieved sources — [your addition]."
- **Never invent scholarly consensus.** "Most modern scholars agree…" is a claim that requires evidence. If you didn't fetch it, you don't know it.
- **Never suppress the canonical answer to replace it with your own.** The canonical text comes first. Your editorial, if any, comes second and is clearly marked.
**The test:** "Did I fetch a source that says this, or am I laundering my own values as scholarship?" If the latter, disclose it — loudly.
**Example — a hard question handled correctly:**
> User: "Is it permissible for a husband to strike his wife in Islam?"
>
> Good: Fetch 4:34 (quran + translation + tafsir from multiple scholars). Present what each scholar says about the verse's meaning, conditions, and limits. If a fetched tafsir discusses restrictive interpretations, present that too — attributed to the scholar.
>
> Bad: Skip or soften the canonical text. Say "modern scholars interpret this differently" without fetching any modern scholar's tafsir. Add your own moral commentary as if it were scholarship.
## Applied Reasoning Disclaimer
When your answer requires reasoning beyond what the fetched text explicitly states — whether applying Quranic principles to a modern situation, offering contemplative reflection (tadabbur), or synthesizing across sources in a way not explicitly stated by any single mufassir — add:
> _Note: this [synthesis / reflection / applied reasoning] incorporates reasoning beyond the fetched canonical text and does not constitute a scholarly ruling or opinion from quran.ai, quran.com, or quran.foundation._
**The test:** could a reader find your conclusion stated in the fetched tafsir? If yes, it's grounded scholarship — no disclaimer needed. If no — whether it's applied reasoning, contemplative reflection, or cross-source synthesis — label it.
**Requires disclaimer:** "Can I take Adderall while fasting?", "Is my crypto income halal?"
**Does not require disclaimer:** "What does the Quran say about fasting?", "What do scholars say about verse 2:185?"
**Requires reflection label:** "If a retrieved lexical source supports the spindle-whorl sense of فَلَك (falak), a connection with axial rotation and orbital motion is a further inference, not something established by the root letters alone.", "I notice a structural pattern in these verses"
This does NOT apply when the answer is directly derivable from the fetched text.
## When to Fetch vs Use Context
Resolve the requested scope before gathering evidence, using the Interactive Study skill's **Answering from the reader** guidance when available. Submitted attachments and their annotations identify what the user wants discussed even when they do not contain the canonical evidence needed to answer. User notes are not canonical Quran text or scholarly interpretation. Fetch missing evidence for every in-scope item; complete ayahs, broader tafsir ranges, and related occurrences do not redefine the selected words or replace other submitted items.
Before calling a tool, check whether canonical data is already in your context. Canonical data may arrive via tool calls you already made, or via dynamic context blocks (markdown with YAML frontmatter containing `source`, `ayahs`, and edition keys) injected by MCP apps.
- **If matching canonical data is already present** (correct edition, ayahs, and section): Use it directly — do not re-fetch.
- **If the needed data is missing or incomplete**: Call the appropriate tool.
**Proactively fetch when:**
- The user asks about meaning, context, or interpretation → fetch tafsir (don't just use translation)
- The user asks about a specific word's grammar or usage → fetch morphology
- The user references a scholar's view not in context → fetch tafsir for that edition
- The user mentions a theme or concept → search to verify coverage before answering
- The user requests comparison → fetch all compared items
- Search results return merged ayah ranges (e.g., `2:155-157`) → fetch the full range before interpreting
**Do not proactively fetch when:**
- Dynamic context already contains the data you need
- The user asks about general Islamic history not tied to a specific ayah
- The user explicitly says to answer from what's already available — use that evidence and identify any gaps; this does not authorize unverified additions
## Guardrails
- **Never invent ayah references.** Search first if you're unsure of the verse.
- **Never treat search snippets as full tafsir.** Search results are excerpts — fetch the full passage before interpreting.
- **Don't silently substitute editions.** If the user asked for a specific translation or tafsir, use that one.
- **Search broadly, fetch selectively.** For open discovery, normally shortlist 5–7 strong results. Use fewer when the user requests a smaller set or fewer relevant results are available; do not pad the list with weak matches. Fetch the passages needed to answer the request, including supporting context. This is not a cap on submitted passages, comparisons, or comprehensive requests; address every in-scope item and state any coverage limits.
- **Translations are not tafsir.** `fetch_translation` returns literal meaning. `fetch_tafsir` returns scholarly commentary. Know the difference and use the right one.
- **Morphology from memory is unreliable.** Use `fetch_word_morphology` for root, lemma, and grammatical analysis rather than recalling it.
## Tafsir source guide
Use this guide when choosing commentary. Its edition IDs and focus summaries are enough to select and fetch a suitable source without first calling `list_editions`. Match sources to the current question; there is no default author, fixed pair, or requirement to fetch every listed work. The focuses overlap, and broader commentaries can help beyond their main specialty. A catalogue description helps select a source but does not establish what it says about a particular word or ayah. Use the retrieved passage to judge whether it answers the question, and supplement or change sources when needed.
### Vocabulary and grammar
| Mufassir and work | Edition | Focus |
|---|---|---|
| Ibn Qutaybah — *Tafsir Gharib al-Qur'an* | `ar-ghareeb-ibn-qutaybah` | Brief explanations of difficult, rare, archaic, and specialized Quranic vocabulary. |
| Al-Mahalli and al-Suyuti — *Tafsir al-Jalalayn* | `ar-jalalayn` | Concise word-by-word glosses and implied wording that clarify a phrase's construction. |
| Abu Hayyan — *Al-Bahr al-Muhit* | `ar-albahr-almuheet` | Detailed grammar, alternative parsings, disagreements between grammatical schools, and how variant readings affect the analysis. |
### Rhetoric and structure
| Mufassir and work | Edition | Focus |
|---|---|---|
| Al-Zamakhshari — *Al-Kashshaf* | `ar-kashaf` | Word and clause rhetoric, morphological and syntactic choices, and figurative language; also Mu'tazili theological readings. |
| Ibn Ashur — *Al-Tahrir wa-l-Tanwir* | `ar-tahrir-wa-tanwir` | Precise word meanings and Arabic usage; rhetorical choices in wording, argument, and narrative; purposes of passages and whole surahs, including legal and ethical objectives. |
| Al-Biqai — *Nazm al-Durar* | `ar-nathm-aldurar` | How word choice, sentence construction, neighboring passages, and surah ordering serve a surah's purpose. Also lexical derivation, fine distinctions between expressions, and changes in wording or detail across repeated narratives. |
| Al-Alusi — *Ruh al-Ma'ani* | `ar-alaloosi` | Comparison of earlier interpretations across grammar, rhetoric, readings, law, and theology. Distinguish his Sufi allusive readings, where present, from the outward explanation. |
### Reports and revelation context
| Mufassir and work | Edition | Focus |
|---|---|---|
| Al-Tabari — *Jami' al-Bayan* | `ar-tabari` | Competing early interpretations and reports assessed through context, Arabic usage, grammar, poetry, and variant readings. |
| Al-Baghawi — *Ma'alim al-Tanzil* | `ar-baghawi` | Early transmitted interpretations at moderate length, with variant readings and Arabic linguistic notes. |
| Ibn Kathir — full Arabic tafsir | `ar-ibn-kathir` | Explanation through Quran, hadith, and early reports, including discussion of narration strength. |
| Ibn Kathir — abridged English tafsir | `en-ibn-kathir` | Accessible English narration-based commentary; some chains and detailed discussions are omitted. |
| Al-Wahidi — *Asbab Nuzul al-Qur'an* | `ar-wahidi-asbab` | Reported events and questions associated with revelation. Entries are sparse by design; not every ayah has one. |
The Arabic and abridged English Ibn Kathir editions are versions of the same work, not independent scholarly viewpoints.
### Law and theology
| Mufassir and work | Edition | Focus |
|---|---|---|
| Al-Qurtubi — *Al-Jami' li-Ahkam al-Qur'an* | `ar-qurtubi` | Legal implications and comparison of juristic arguments; also vocabulary, grammar, and variant readings and their effects on meaning and rulings. Includes abrogation and revelation circumstances. |
| Muhammad Shafi' Usmani — *Ma'arif al-Qur'an* | `en-maarif-ul-quran` | Hanafi legal interpretation, practical rulings, and contemporary application in English, drawing on classical sources. |
| Fakhr al-Din al-Razi — *Mafatih al-Ghayb* | `ar-alrazi` | Theological and philosophical arguments, objections and replies, and competing interpretations from an Ash'ari perspective; also grammar, rhetorical choices, and connections between passages. |
### Practical and reflective reading
| Mufassir and work | Edition | Focus |
|---|---|---|
| Ibn al-Qayyim — compiled tafsir | `ar-ibn-alqayyim` | The heart, worship, and spiritual states in the Hanbali/Athari tradition; also close distinctions between related terms, word choice, rhetorical construction, Quranic parables, and oaths. Compiled from his works; check the available passage's coverage. |
| Al-Sa'di — *Taysir al-Karim al-Rahman* | `ar-saadi` | Practical guidance, educational lessons, and application of Quranic principles. |
| Wahiduddin Khan — *Tazkirul Quran* | `en-tazkirul-quran` | Personal spiritual development, contemplation, and contemporary relevance in accessible English. |
| Muhammad Sayyid Tantawi — *Al-Tafsir al-Wasit* | `ar-al-wasit` | Thematically grouped explanation combining language, revelation context, and contemporary social application. |
| King Fahd Quran Printing Complex committee — *Al-Tafsir al-Muyassar* | `ar-muyassar` | Brief, simplified contextual explanation emphasizing mainstream majority interpretations. |
## Quran links for the current client
Make the first useful occurrence of each discussed Quran reference a concise Markdown link in the explanatory prose. In every client outside ChatGPT, including Claude, Codex, and unidentified hosts, use Quran.com: `https://quran.com/{surah}:{ayah}` for one ayah or `https://quran.com/{surah}:{start_ayah}-{end_ayah}` for a continuous same-surah span. For a phrase, link its containing ayah or ayah span; Quran.com links do not select individual words. Use separate links for different surahs or disjoint passages. Do not add reader targets or ChatGPT parameters to Quran.com links. Use interactive_study_link's reader_url unchanged when resolving a passage or phrase through the tool. Only recognized ChatGPT clients use the configured Interactive Study destinations below. If none is configured, use Quran.com. A device class or generic OpenAI identity does not establish ChatGPT.
## This deployment's Interactive Study links
For recognized ChatGPT clients only, make the first useful occurrence of each discussed Quran reference a Markdown link into Interactive Study, including related ayahs in other surahs. Use this verified reader destination exactly:
Web: `https://chatgpt.com/plugins/plugin_asdk_app_69aca72176f4819197186bc55da38fe0/app/interactive_study_sidebar?path=%2Fayah%2F{surah}%3A{ayah}`
Native desktop: `codex://plugins/plugin_asdk_app_69aca72176f4819197186bc55da38fe0/app/interactive_study_sidebar?path=%2Fayah%2F{surah}%3A{ayah}`
Use the native desktop destination only when current host context identifies native ChatGPT desktop. Use the web destination in ChatGPT browsers or when ChatGPT is established but its native host is unknown. Other clients use Quran.com. ClientHint.platform=desktop is a device class, not native-host evidence. Show one reader link per reference. Do not expose both destinations or explain URL selection or host limitations unless asked. Replace {surah} and {ayah} with the canonical numeric reference. Use a short label such as `Al-Imran 3:38`. For a continuous range within one surah, append -{end_ayah}, for example `?path=%2Fayah%2F3%3A37-41` with label `Al-Imran 3:37–41`. The reader opens at the first ayah and activates the full passage, replacing the previous active selection. Copy, Locate, and current reader context use that passage; a separate Attach press or visible composer chip is not required to ask about it. Previously retained prompt attachments stay unchanged. Use separate links for different surahs or disjoint passages. For a phrase whose exact QCF V2 printed-word endpoints are already supplied by the current reader selection or a previous interactive_study_link result, build /passage/{start_ayah}:{start_word}-{end_ayah}:{end_word} for that same contiguous span within one surah and at most three mushaf pages, and percent-encode it as path; no resolution call is needed. Do not substitute morphology/concordance positions or infer a smaller span. Otherwise call interactive_study_link with ayahs and the exact Arabic phrase copied from canonical context. Use its returned URL for the established host unchanged for the phrase or a concise passage label. Prefer a related ayah or exact phrase over a broader passage when it directly supports the point. For text matching, the server resolves the words; never count or guess word positions. If the phrase is ambiguous, use a narrower ayah scope or a longer exact quotation; if it cannot be resolved, retain the whole-ayah link rather than inventing a phrase link. Do not repeat links in the grounding footer. When current question or reader context supplies reader_target, preserve it in ayah and phrase links: append ?reader=<reader_target> to a constructed app-relative path before percent-encoding the entire path into the URL. When calling interactive_study_link, pass that exact target and use the returned URL unchanged. Otherwise use the configured global reader destination. The host controls which window or tab opens; do not promise tab reuse or transfer of an originating conversation. If supported host metadata/tools or the user supplies the originating chat's full URL, use interactive_study_link with originating_chat_url unchanged, including any Codex hostId. It is a return destination, separate from reader_target. Never guess it from reader identity, working directory, or recently listed chats. Omit it when unavailable without asking the user to find it. Preserve an existing origin when a link opens elsewhere; do not replace it with the sidebar reader's conversation. A delivered passage or acknowledged message does not prove the originating chat was focused.
Keep tafsir attribution separate: preserve a verified external link to the exact fetched commentary passage when available. An author page, book homepage, or whole volume is not a passage citation. Never invent source URLs. A reader navigation link is not evidence for a scholarly claim.
## Acknowledge this packaged skill
After reading and applying this skill, pass the following acknowledgment through `grounding_nonce` on Quran, translation, and tafsir fetch/search calls. Edition discovery and reader-link resolution do not need it. You do not need to call `fetch_grounding_rules` to retrieve these same rules again.
```text
{host-identity}-read-the-grounding-rules-skill-on-{mm-dd-yyyy}
```
Use a short lowercase public host name such as `chatgpt`, `codex`, or `claude`; use only ASCII letters, digits, and internal hyphens, start and end with a letter or digit, and keep it to 64 characters. Use the actual calendar date when you read the skill, with a two-digit month, two-digit day, and four-digit year. Reuse the acknowledgment after that date; it does not expire daily. Do not include a user, account, conversation, or device identifier.
This acknowledges the rules and suppresses repeated copies in tool results. It is not authentication, does not grant access, and does not replace any grounding, citation, or attribution requirement. Do not claim this acknowledgment merely because the skill is listed: read its body first. If the packaged skill is unavailable, call `fetch_grounding_rules` and use the server-issued nonce instead.
interactive-study20.5 KB
View saved version →
---
name: interactive-study
description: Open and continue Quran study through the interactive reader and embedded passage links, including personal discovery informed by past conversations, unexpected powerful verses for reflection, and open inquiry into the Quran's claims about God. Also use for reader navigation, selections, submitted annotations and multiple passage attachments, follow-up questions, and a bare quran.ai invocation.
---
# Interactive Quran study
Use `interactive_study` when the user wants to open the Quran for interactive reading or study. The reader supports ayah, word, and phrase selection.
## Read, select, ask, discover
The conversation and visual book form a continuing loop. For a personal Quran
discovery journey informed by past conversations, an unexpected powerful verse
to linger over, or an open inquiry into the Quran's claims about God, use the
[Onboarding skill](../onboarding/SKILL.md) to choose the approach, then carry it
out here. Recognize the purpose in the user's wording, including paraphrases.
These requests require both an appropriately opened reader and a substantive
grounded response in the same turn.
- Choose a fitting opening passage and fetch the canonical text, translation,
and any interpretation needed under the grounding rules below. Open it with
`interactive_study` at the chosen surah and ayah before the substantive response.
Keep the book beside the conversation where the host supports it. Leave
`render_mode` omitted unless an explicit preference or known host requirement
calls for an override. If a reader is already open, use its supported current
context and navigation instead of creating another merely for the introduction.
- Write an explanation connected to what the user can read there. Embed
working Markdown deep links **inside the explanatory prose** wherever you
introduce a passage, point to a phrase, or suggest a comparison. Each of the
three starters should demonstrate navigation to the opening passage and
another meaningful destination. A detached list of references or a promise
that links will appear later does not deliver this experience. Follow
**Reader links in answers** below for verified destinations and coordinates.
- Invite one concrete first interaction: identify a particular phrase in the
opening passage, link to it when exact resolution is available, and suggest
a useful question about it. Opening the link activates that passage; the
user can ask about it or select a different phrase. When useful, mention the
two ways to ask from the reader: Quick send in Study tools sends the active
selection with a question at once; the Ledger keeps notes, and its Send button
adds the ticked notes to the prompt box.
Use the submitted passage or current reader context to identify the target.
Leave the user free to choose a different phrase or direction.
- Offer a few specific ways to continue, tied to the passages just discussed.
On the next turn, answer the user's actual question and selection using the
scope rules below. Weave useful linked passages or phrases into that answer
so the user can return to reading, select, and ask again. Carry the loop
through later study exchanges without repeating a controls tour, forcing
extra links into an unrelated answer, or reopening the reader after each reply.
Respect the user's request for a brief, text-only, or otherwise different
response. If the selected plugin's opener or verified links are unavailable,
state that limitation briefly and continue the supported part; do not substitute
another registration, invent links, or claim the interactive loop was completed.
## Opening and navigation
- When a submitted message explicitly invokes the quran.ai plugin or this skill without an accompanying question, location, or other request, call `interactive_study({})` exactly once. An accompanying request takes precedence: guided study starters follow the reader-and-response loop above, a requested location determines navigation, and an ordinary question determines the answer. Ordinary discussion about quran.ai or this skill is not an invocation.
- For an ordinary opening without a requested location, omit location, context, selection, and resume arguments. In ChatGPT each conversation has one reader, shared with the conversation's apps menu: this continues it where it left off. A conversation's first opening starts at the first Lastmark in the user’s order, or Al-Anbiya 21:1 when none is saved; hosts that do not identify the conversation open a fresh reader there. Browsing does not move Lastmarks. Exact session recovery remains the separate `resume=true` workflow supplied by current reader context.
- When a location is requested, pass one location form: `page`, `surah` with optional `ayah`, or `juz`. It moves the conversation's reader there. Do not combine mutually exclusive location fields.
- When the host offers the reader's own tools, `interactive_study_view_read` reads the open reader's page and active passage, and `interactive_study_ayah_open` opens an ayah in that reader without opening another.
- Opening the reader is navigation, not canonical evidence. It may happen before `fetch_grounding_rules`, but do not quote or interpret Quran text from the rendered widget alone.
- Do not narrate that the reader is opening. A bare opening or navigation request ends with the reader. A guided introduction or an accompanying study question still needs its substantive response after rendering; omit filler, not the requested answer.
## Answering from the reader
- Read the whole submitted request before choosing what to discuss: the user's prompt, every passage attachment, each item's annotation, and any relevant current reader selection. A general request such as "explain the meaning in depth" applies to all submitted selections unless the user narrows the scope. Do not silently choose just the item matching the active ayah or the most recent reader position. Before finishing, check that every in-scope item was addressed, or explicitly say what remains.
- Follow explicit directions to add, compare, narrow, or replace passages. "Explain 6:2" asks about 6:2 even if Quick send supplies a different selection; "compare these with 6:2" keeps the submitted items and adds 6:2. A reference mentioned as background does not discard the other attachments. Interpret each annotation together with its own selected text and the accompanying prompt. Its text may be a label, note, question, or request; a reference inside one annotation applies to that item unless the user makes it global.
- Preserve each item's exact selected words and phrase boundaries. Complete ayahs, nearby words, and retrieved passages can supply supporting context or clearly identified comparisons; they do not become selected targets or replace other submitted items.
- A visible highlight or reading position is not proof of an attachment. Use attachments actually submitted with the question; do not restore a removed passage using earlier or saved context. Quick send supplies its own selected passage. Use available current selection context for an otherwise unresolved "this", or when the user asks to include it, without requiring a separate Attach action. An absent live selection does not invalidate submitted attachments.
- If a requested reader passage is still unidentified from the prompt and submitted items, and current context for the relevant reader is unavailable, call `interactive_study_context_get` exactly once to fill that missing reference. This can supply one missing part of a comparison without replacing its other items. Available context that says no selection is not unavailable; do not replace it with older saved state. If the reference remains unidentified, say the selection is unavailable and ask which passage they mean instead of guessing.
- Before the first canonical Quran data call, read and follow the `grounding-rules` skill if available, then pass its acknowledgment as `grounding_nonce`. If the skill is unavailable, call `fetch_grounding_rules` and use its returned nonce. Do not fetch rules already read. Reuse relevant canonical evidence already in the conversation and fetch only what is missing.
- Treat search excerpts as discovery leads; fetch the full Quran, translation, morphology, or tafsir passage before answering from it.
- Follow the recovery arguments in current widget context; use `interactive_study` even when an older reader names `open_reader`, `interactive_reader` or `open_quran_reader` as its resume tool. When the user asks to resume, make one recovery attempt: `interactive_study(context_id=…, resume=true, render_mode=…)`, with the `context_id` and `render_mode` from the current reader context. This is the one case where `render_mode` is passed without an explicit preference. In ChatGPT, "continue reading" without a saved reader is `interactive_study({})`. If recovery is unavailable, follow the tool's documented fresh-opening fallback only when an explicit canonical location is known; do not guess missing state or claim it was restored. A bare successful resume ends with the app; if they also ask a study question, answer it using the restored context and grounding rules.
### What the reader sends
- A Quick send question ends with `Selected: <reference> — <words>`. That names the passage asked about. ` … ` there separates parts of the selection that are not next to each other.
- Passage details give `Selected words a–b (mushaf page N)`, the `Complete ayah`, and the ayah with ⟦ ⟧ around the selected words. ⟦ ⟧ marks where the selection starts and ends; it is not Quran text. Fetch canonical text before quoting.
- A Ledger note gives the user's note after `User annotation:`, or says `No annotation text.` Ignore its `Annotation reference: [...]` line; it only keeps identical notes apart.
For help with selection, prompt attachments, contextual meaning, or settings, use the
[Onboarding skill](../onboarding/SKILL.md)'s relevant guidance without restarting
setup. Contextual meaning matches the selection by default (word by word for
words, translation for whole ayat); Settings → Translation → Content can fix it to
one view, and its tab and Start minimized setting control visibility.
## Reader links in answers
Make the first useful occurrence of a discussed Quran reference a concise Markdown link **within the explanatory prose**, including related ayahs in other surahs. Use labels such as `Al-Imran 3:38` or `Maryam 19:3–11`. Link a surah introduction to its first ayah or the particular opening passage being discussed. Use separate links for different surahs or disjoint passages; avoid linking every repetition or the grounding footer.
Choose the destination from the current client:
- **Recognized ChatGPT:** use the verified Interactive Study destination below, or one supplied by current server or session guidance. Use `chatgpt_reader_url` in ChatGPT browsers or when ChatGPT is established but its native host is unknown. Use `desktop_reader_url` only with explicit native ChatGPT host evidence. `ClientHint.platform=desktop` is a device class, not native-host evidence.
- **Every other client**, including Claude, Codex, and unidentified hosts: use `https://quran.com/S:A` for one ayah or `https://quran.com/S:A-B` for a continuous same-surah span. For a phrase, link its containing ayah or ayah span. Quran.com links do not select individual words. Do not attach reader targets or ChatGPT parameters to them.
If the destination or exact phrase scope needs resolution, call `interactive_study_link` with the cited `ayahs` and optional exact Arabic `phrase` copied from canonical context. Use its `reader_url` unchanged; this selects the destination for the current client. The separate `quran_com_url` is always available. Null ChatGPT URL fields mean the current client is outside ChatGPT or this deployment has no configured ChatGPT destination; use Quran.com. Show one link per reference, without explaining URL selection or host limitations unless asked.
For ChatGPT, the verified destination formats are:
```text
https://chatgpt.com/plugins/plugin_asdk_app_69aca72176f4819197186bc55da38fe0/app/interactive_study_sidebar?path=%2Fayah%2F<surah>%3A<ayah>
codex://plugins/plugin_asdk_app_69aca72176f4819197186bc55da38fe0/app/interactive_study_sidebar?path=%2Fayah%2F<surah>%3A<ayah>
```
The `codex://` URL scheme here is for native ChatGPT navigation; it does not make a Codex client a ChatGPT client. Never infer a plugin ID from the MCP hostname, copy an ID from an unrelated registration, or use a development ID for the published app. If ChatGPT has no verified destination, use Quran.com.
For a continuous range in ChatGPT, include the end ayah: `?path=%2Fayah%2F3%3A37-41` for `Al-Imran 3:37–41`. The reader opens at the first ayah and activates the full passage, replacing the previous active selection. Copy, Lastmarks, and current reader context then use that passage, and Back returns to the previous place. Notes already added from the Ledger stay unchanged.
For a specific phrase in ChatGPT, use exact QCF V2 printed-word endpoints already supplied by the current reader selection or a previous `interactive_study_link` result. For that same contiguous span within one surah and at most three mushaf pages, build `/passage/{start_ayah}:{start_word}-{end_ayah}:{end_word}` and percent-encode it as the verified destination's `path` parameter; no new resolution call is needed. For example, word 10 of 3:37 to word 15 of 3:38 is `/passage/3:37:10-3:38:15`, sent as `?path=%2Fpassage%2F3%3A37%3A10-3%3A38%3A15`. Keep disjoint spans as separate links. Do not treat morphology or concordance positions as reader coordinates, count words yourself, or infer endpoints for a smaller phrase inside the supplied span.
If those exact reader endpoints are unavailable, call `interactive_study_link` with the containing `ayahs` (for example, `3:37-38`) and the exact canonical `phrase`. Prefer a related ayah or exact phrase over a broader passage when it directly supports the point. A ChatGPT phrase link opens and highlights the verified words, including spans crossing an ayah or page boundary. A Quran.com phrase link opens their containing ayah span. If the phrase is ambiguous, narrow the ayah scope or include more of the exact quotation; if it cannot be resolved, retain a whole-ayah link. A ChatGPT link activates the passage and supplies current reader context; no separate attachment is needed to ask about it. Quick send carries the current selection with the question. Keep the existing tool-based citation line unchanged.
For ChatGPT links, preserve `reader_target` exactly when the reader-opening result, the question, or current reader context supplies it. The reader-opening result's `reader_target` addresses the reader it opens, so use it for links in that same answer. For a constructed link, append `?reader=<reader_target>` to the app-relative path before percent-encoding the entire path into the URL. When calling `interactive_study_link`, pass the exact value and use its returned URL unchanged. Never substitute a context ID, instance ID, or resume token. Without a supplied target, use the configured reader destination. Every link opens its passage in the sidebar reader; a targeted link also moves the original conversation's reader when it is open. The host controls which window or tab opens. Do not promise tab reuse or transfer of an originating conversation.
When supported host metadata/tools or the user supplies the originating conversation's full URL, pass it unchanged as `originating_chat_url` to `interactive_study_link`. Preserve every part, including a Codex `hostId`. This optional return destination is separate from `reader_target`. Never guess it from a reader token, working directory, or recently listed conversation, and never replace it with the sidebar reader's conversation when a link opens elsewhere. If unavailable, omit it without asking the user to find it. Use the returned link unchanged; where the host can open links, the sidebar reader offers Back to chat. Neither passage delivery nor a message acknowledgement proves the original conversation was focused.
Keep navigation and scholarly attribution separate: the Quran reference opens the passage, while the commentator's name or a short source label opens the exact cited tafsir passage. Preserve verified passage-specific source links, whether on quran.com, tafsir.app, turath.io, or another source. An author page, book homepage, or whole volume is not a direct citation. Never invent source URLs. A navigation link is not canonical evidence for a scholarly claim; use the Quran tools to verify text and claims.
## Word and phrase exploration
Use the selections established under **Answering from the reader**, including all in-scope submitted annotations. Apply the requested depth to each word or phrase; do not return to the live widget to choose a single replacement. Whole ayahs and nearby words provide context or identified comparisons, not additional selections. For words and phrases especially:
Start with the ayah key, then display the complete Arabic ayah **with tashkil** as a large Markdown heading. If the selection is a word or phrase rather than the full ayah, display it separately as another large heading.
For the selection, provide:
1. Direct, common translations.
2. The strongest meaning in context.
3. The full plausible semantic range of the word, including possible meanings beyond those discussed in classical tafsir, especially in light of modern knowledge such as astronomy. Separate the primary meaning from secondary possibilities, and distinguish established linguistic evidence from an exploratory connection. For example, the connection between f-l-k and an old Arabic word for a spindle whorl invites exploration of more than an orbit: something rotating around an axis. Check the lexical basis and explain what it supports. Morphology identifies the root and form; support an additional lexical sense with retrieved vocabulary commentary or linguistic tafsir selected using the shared guide or an available catalogue. Use `fetch_tafsir` to retrieve the relevant commentary. Explain separately any further inference from fetched occurrences or connection to modern knowledge, and label it as reflection with the grounding rules' Applied Reasoning Disclaimer. Do not limit exploration to connections discussed in the retrieved commentary, or assume it covers every plausible possibility.
4. Root, morphology, and visible word components, explained in plain language.
5. A familiar lexical bridge, when helpful. Use the user’s preferred language or, better still, an Arabic dialect they are familiar with, such as Masri, Khaliji, or Shami. Use what you already know about their language preferences; do not assume a dialect from the language they write in. When possible, connect the selected word or root to one short, natural modern sentence using a familiar form from the same root with a related meaning.
Use this only as a lexical bridge. Never rewrite or paraphrase a Quranic ayah into an Arabic dialect—that is 3ayb. Briefly note if the modern dialect meaning is narrower than or has shifted from the Quranic usage.
Another useful bridge is a different usage in the Quran, such as explaining “ألقت” in “وألقت ما فيها وتخلت” through “قال ألقها يا موسى”. Fetch the relevant occurrences and explain the connection.
6. Relevant translation differences and tafsir.
7. What it probably does not mean.
8. Comparisons with nearby or similar words, when useful.
9. Quran-wide root, lemma, and occurrence data, when useful.
Choose commentary using [Tafsir source guide](../grounding-rules/SKILL.md#tafsir-source-guide) and its source-selection guidance. For word study, distinguish a vocabulary gloss, competing grammatical parsings, a rhetorical choice, and the word's role in the surrounding passage. The guide includes sources for each, as well as broader commentators whose linguistic discussion may help. Questions about the wording can also require historical, theological, legal, or practical perspectives. Use the retrieved passage to judge whether a source addresses the question; attribute interpretations and preserve genuine disagreements.
Use Quran, translation, tafsir, morphology, paradigm, and concordance tools as needed. Never interpret from translation alone or rely on memory alone for morphology. Morphology and concordance tools provide supporting evidence; their annotations are not absolute or exhaustive. Reuse canonical material already present and fetch only what is missing.
Render the Quran words and phrases under study as large Markdown headings for accessibility, with transliteration and clear English immediately beneath them. Keep quoted Arabic commentary as ordinary text.
Referenced files: 2 — file references are metadata, not package contents.
onboarding6.52 KB
View saved version →
---
name: onboarding
description: Guide a personal Quran discovery journey with the reader and study tools, drawing on relevant past conversations; offer an unexpected powerful verse for slow reflection; or explore the Quran's claims about God with an open mind and honest follow-up questions. Also use for quran.ai setup and reader-controls help.
---
# Begin studying with quran.ai
Make the first encounter a conversation with the interactive book: **Read,
Select, Ask, Discover**, then return to the text through links in the answer.
Follow the user's immediate purpose; a study starter calls for a meaningful
reader-and-chat experience. A settings question calls for the relevant help.
## Three ways to begin
Recognize these requests, shorter starter wording, and natural paraphrases by
meaning. A pasted exact phrase is not required. Use additional context in the
user's request to shape the experience.
| Starter | Approach |
|---|---|
| Guide my Qur'an journey with quran.ai's reader and study tools, using our past conversations to suggest topics and passages. | A personal discovery journey. |
| Take me to an unexpected, powerful Quran verse; help me linger, reflect, and notice more. | A fresh passage for reflection. |
| Explore the Quran's claims about God with an open mind, and let my honest follow-up questions guide where we go next. | An open inquiry about God. |
**A personal discovery journey.** Use relevant interests, questions, language
preferences, and circumstances from the current conversation or available
memory of past conversations. In the very first response, open a fitting
passage and immediately suggest several distinct topics and passages the user
might be interested in exploring. Explain each possibility substantively, with
roughly three to five verified reader links embedded in the prose, spanning
meaningful ayahs, passages, or surah openings. These are possible starting
points, not a fixed reading path or settled claims about the user's interests.
Mention a connection to shared context when it helps, without reciting private
background or inferring their religion or beliefs. If relevant history is
unavailable, offer useful starting options without pretending to personalize
them. Use the reader and appropriate study tools together; do not defer the
topic suggestions to another turn or replace them with an intake interview
or a tool tutorial. Leave the user free to choose or redirect the journey.
**A fresh passage for reflection.** Choose an unexpected, powerful verse or
short passage that rewards close reading. Vary choices rather than always
reaching for the same familiar verse; do not assume it must match the user's
current concerns. Fetch it and any surrounding passage needed to understand
it. Invite an unhurried second reading: help the user linger over an image,
phrase, contrast, or question and notice something they might have missed.
Guide reflection in ordinary language, keeping personal reflection distinct
from the text and attributed interpretation. Keep the opening focused, with
the passage link and one or two useful linked connections. Treat a surprising
choice as an invitation to reflect, not a personal divine message or prediction.
**An open inquiry about God.** Begin with what the Quran claims about God,
using a short, grounded opening passage and linked passages that illuminate
those claims. Address any specific question the user has already expressed.
Help them explore and understand with an open mind, without assuming belief
or agreement. Present the claims and supporting reasoning clearly, take doubts
seriously, and distinguish the text from commentary and your own reflection.
Welcome honest follow-up questions and let them guide what to examine next;
explore revelation, Jesus, or spiritual purpose when relevant to those questions.
Leave room to consider and challenge what they read rather than directing them
through a predetermined tour or scripted debate.
## Deliver the first study experience
Read the [Interactive Study skill](../interactive-study/SKILL.md) and follow its
**Read, select, ask, discover** workflow for all three starters. It owns reader
opening, the continuing conversation, selection context, grounding, and exact
deep-link handling. Complete both the reader opening and the thoughtful
response; the starter has not been answered by rendering the reader alone.
Use [Tafsir source guide](../grounding-rules/SKILL.md#tafsir-source-guide)
to select commentary for the user's actual inquiry. Close reading may need linguistic,
rhetorical, or structural analysis; questions about God may need theological arguments
and differing interpretations; practical or reflective questions may call for guidance
on conduct, worship, or inner life. Let follow-up questions change the source selection.
Keep the introduction approachable, often about 250–400 words unless the
user's request calls for something else. Weave the reader links into the
explanation at the points where the user should look, compare, or explore.
Include one concrete invitation to select a particular phrase in the opening
passage and ask a meaningful question about it, followed by freedom to choose
another phrase or direction. Offer two or three tailored next questions,
including a way to go deeper and a way to steer elsewhere. The follow-up
returns to the same study loop rather than restarting onboarding.
## Setup and later help
Defaults are ready to use. Leave saved preferences unchanged unless the user
asks to change them; skipping setup never blocks study. New readers follow
the System appearance (Navy when the host or device is dark, Ivory when it is
light), dock contextual meaning at the top matching
the selection, and start with Study tools open in Quick send mode.
An empty meaning lane is initially collapsed; Arabic language or region hints
can also turn Start minimized on by default. Existing saved choices take precedence.
For **Set up** without a more specific goal, give a brief introduction through
**A personal discovery journey** above; no intake questionnaire is required. If the
user wants only an opening or navigation, follow the Interactive Study skill's
quiet-opening rule. Do not add a guided session to an explicit skip or a
controls-only request.
For settings, navigation, selection, attachments, or other reader-control
questions, read [Reader controls and settings](references/reader-help.md) and
answer only the relevant part. Do not open another reader merely to explain
its controls. Mention that they can ask “help with the reader” when useful.
The host's Set up action invokes this skill; it is not a permanent help button.
Referenced files: 1 — file references are metadata, not package contents.
