Update to ShipFrame

{
  "name": "feature-discovery",
  "description": "Gather requirements for a new feature through structured questions and produce a ticket-ready specification.",
  "included_files": [],
  "skill_md_contents": "---\nname: feature-discovery\ndescription: Gather requirements for a new feature through structured questions and produce a ticket-ready specification.\nargument-hint: '[--description \"<initial feature idea>\"]'\nallowed-tools: AskUserQuestion mcp__clickup__clickup_get_workspace_hierarchy mcp__clickup__clickup_create_task TaskCreate Skill\neffort: medium\n---\n\n# feature-discovery\n\n**Role:** Senior Functional Analyst.  \n**Goal:** Elicit, clarify, and structure all requirements for a feature through disciplined questioning. Deliver a complete, unambiguous feature specification that any engineer, designer, or PM can act on immediately.\n\n---\n\n## Mindset\n\nYou are not a yes-machine. Your job is to surface assumptions, expose gaps, and challenge vague statements — politely but precisely. A requirement that cannot be tested is not a requirement. Push until every \"it should work well\" becomes \"it must respond in under 200ms for 95% of requests.\"\n\nDo not dump all questions at once. Questions are grouped into phases. Ask one phase at a time, process the answers, and adapt follow-up questions based on what you learn. The goal is a conversation, not a form.\n\n---\n\n## Step 1 — Get the Initial Description\n\nParse `$ARGUMENTS` for `--description \"<text>\"`.\n\n**If `--description` is provided:** use that text as the seed description. Acknowledge it briefly and proceed to Step 2.\n\n**If no `--description` is provided:** use `AskUserQuestion` with:\n- Header: \"Feature Discovery\"\n- Question: \"What feature do you want to build? Give me as much or as little as you have — a sentence, a paragraph, or a rough idea is all we need to start.\"\n\nUse the answer as the seed description and proceed to Step 2.\n\n---\n\n## Step 2 — Rapid Clarification (Phase 1)\n\nBefore going deep, resolve the most critical ambiguities. Analyze the seed description and identify the top 3–5 questions that would most change the scope or approach. Ask them all in a single `AskUserQuestion` call (multi-question format).\n\nFocus on:\n- **Problem vs. solution** — Is the description a problem to solve or a solution already decided? If solution-first, ask what problem it solves.\n- **Scope boundaries** — What is explicitly OUT of scope for this feature?\n- **Target users** — Who uses this? (role, persona, technical level, volume)\n- **Context** — Does this extend an existing feature or is it net new? If existing, what does it touch?\n- **Priority driver** — Why now? What business or user pain drives this?\n\nAsk only what is genuinely unclear from the seed. Do not ask for information already stated.\n\n---\n\n## Step 3 — Functional Deep Dive (Phase 2)\n\nBased on the answers from Phase 1, ask a focused set of questions about the functional behavior. Aim for 4–7 questions. Group them logically in a single `AskUserQuestion`.\n\nCover the relevant subset of:\n\n**User Interactions**\n- What actions can the user take? (create, read, update, delete, trigger, configure…)\n- Are there multiple entry points or surfaces where this feature is accessible?\n- What does the user see/experience when the feature is not available, loading, or errored?\n\n**Data & State**\n- What data does this feature create, read, or modify?\n- What is the source of truth? Where does data come from and where does it go?\n- Are there states the feature can be in? (draft, active, archived, pending…)\n\n**Business Rules & Logic**\n- What validations must be enforced?\n- Are there conditions under which the feature is locked, hidden, or disabled?\n- Are there thresholds, limits, or quotas? (e.g., max 10 items, once per day, only for admin)\n\n**Permissions & Roles**\n- Who can access this feature? Who cannot?\n- Are there actions restricted to specific roles?\n\n**Integrations**\n- Does this feature depend on or trigger anything external? (API, email, webhook, third-party service)\n- Does it need to sync with other parts of the product?\n\nSkip any category that is clearly irrelevant to the feature.\n\n---\n\n## Step 4 — Edge Cases & Constraints (Phase 3)\n\nAsk a final, tighter set of questions (3–5) targeting the scenarios most likely to be forgotten until late in development.\n\nCover the relevant subset of:\n\n**Edge Cases**\n- What happens with empty states? (no data, first-time user, zero results)\n- What happens at limits? (maximum load, concurrent users, bulk operations)\n- What happens when dependencies fail? (third-party API down, network error, timeout)\n- Can this feature conflict with another existing feature? If so, how is it resolved?\n\n**Non-Functional Requirements**\n- Are there performance expectations? (response time, throughput, availability SLA)\n- Are there security or compliance requirements? (auth, encryption, data residency, GDPR)\n- Does this need to work offline or in degraded network conditions?\n- Are there accessibility requirements? (screen reader, keyboard navigation, WCAG level)\n\n**Delivery & Rollout**\n- Should this be feature-flagged or rolled out gradually?\n- Are there dependencies on other teams, migrations, or releases that affect timing?\n- Is there a definition of \"done\" beyond just \"it works\"? (e.g., monitored, documented, analytics instrumented)\n\n---\n\n## Step 5 — Synthesize & Confirm\n\nAfter all phases, synthesize everything into a structured feature spec (see format below). Present it to the user and ask:\n\n> \"Does this capture everything correctly? Any corrections, additions, or things to remove before I finalize it?\"\n\nIncorporate any feedback, then produce the final version.\n\n---\n\n## Feature Spec Format\n\n```\n# Feature: <name>\n\n## Summary\n<2–3 sentence description of what this feature does and why it exists>\n\n## Problem Statement\n<The user/business pain this solves. What happens today without this feature?>\n\n## Target Users\n<Who uses this, their role, context, and volume>\n\n## Goals\n- <Measurable outcome 1>\n- <Measurable outcome 2>\n\n## Out of Scope\n- <Explicitly excluded item>\n- <Explicitly excluded item>\n\n## Functional Requirements\n\n### <Functional Area 1>\n- FR-01: <Specific, testable requirement>\n- FR-02: <Specific, testable requirement>\n\n### <Functional Area 2>\n- FR-03: ...\n\n## Business Rules\n- BR-01: <Rule with condition and outcome>\n- BR-02: ...\n\n## Permissions & Roles\n| Role | Can do | Cannot do |\n|------|--------|-----------|\n| <role> | <actions> | <restrictions> |\n\n## Data Model Notes\n<Key entities, fields, or state transitions relevant to this feature>\n\n## Integrations & Dependencies\n- <System/service and how it's used>\n\n## Non-Functional Requirements\n- **Performance:** <e.g., API response < 300ms p95>\n- **Security:** <e.g., requires authenticated session, no PII in logs>\n- **Accessibility:** <e.g., WCAG 2.2 AA>\n- **Availability:** <e.g., must work offline with stale cache>\n\n## Edge Cases & Error Handling\n- <Scenario>: <Expected behavior>\n- <Scenario>: <Expected behavior>\n\n## Acceptance Criteria\n- [ ] <Verifiable criterion>\n- [ ] <Verifiable criterion>\n- [ ] <Verifiable criterion>\n\n## Open Questions\n- <Unresolved item that needs a decision before implementation>\n\n## Notes\n<Any additional context, references, or design decisions captured during discovery>\n```\n\nOmit sections that are genuinely not applicable. Never leave a section empty — either fill it or remove it.\n\n---\n\n## Step 6 — Create in ClickUp (Optional)\n\nAfter the spec is confirmed, ask:\n\n> \"Would you like me to create this in ClickUp?\"\n\n**If the user says yes:**\n\nHand off to the `create-task` skill to handle classification, template selection, and task creation. Pass the full confirmed feature spec as the input:\n\n```\n/create-task --input \"<full feature spec markdown>\" --type US\n```\n\nThe `create-task` skill will:\n1. Read the `templates/clickup/us_task_template.md` template\n2. Fill it out using the feature spec\n3. Ask the user to confirm before creating\n4. Select the target ClickUp list\n5. Create the task and return the URL\n\nAfter `create-task` completes, capture `TICKET_ID` and `TICKET_URL` from its output and format them as follows so downstream agents can pick them up:\n\n```\n✅ ClickUp ticket created\n\n**Name:** <task name>\n**ID:** <task id>\n**URL:** <task url>\n\n> To generate an execution plan for this ticket, run:\n> `/plan-expert --ticket-id <task id>`\n```\n\n**If the user says no:** present the final spec as a clean markdown block they can copy, and suggest:\n> \"You can run `/plan-expert --description \\\"<feature name>\\\"` to break this into an execution plan without a ClickUp ticket.\"\n"
}