← AchriomCONTENT HISTORY

Update to Achriom

Snapshot Sep 30, 2026 · 22:51 UTC · version 2.0.0

Collection source: not recorded for this historical snapshot.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "name": "collection-review",
  "description": "Full audit of your collection, patterns, taste profile, gaps, and what your library says about you",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 280
    }
  ],
  "skill_md_contents": "---\nname: \"collection-review\"\ndescription: \"Full audit of your collection, patterns, taste profile, gaps, and what your library says about you\"\n---\n\n# What Does Your Library Say About You?\n\nA comprehensive review of your entire collection. Patterns, taste evolution, thematic clusters, blind spots, and the personality of your library.\n\n\n## Workflow\n\n### Step 1: Map the Full Territory\n\nPull everything:\n\n```\nget_stats()                                    # Size, composition, media breakdown\nget_by_rating(min_rating=5)                    # The all-time favorites\nget_by_rating(min_rating=4)                    # The broader \"loved it\" tier\nget_by_rating(max_rating=2)                    # What didn't land\nget_by_status(media_type, status=\"unread\")     # The backlog (all types)\nget_timeline()                                 # When things were added\nget_signals()                                  # Behavioral patterns\nget_context()                                  # Broader context\n```\n\nIf the user asked about a specific media type or focus area, concentrate there. Otherwise, go wide.\n\n### Step 2: Find the Patterns\n\nUsing the **collection-insights** skill, analyze systematically:\n\n**Thematic clusters:**\nSearch for recurring themes across media types:\n```\nsearch(media_type=\"book\", query=\"isolation\")\nsearch(media_type=\"movie\", query=\"isolation\")\n# Repeat for themes that emerge from the top-rated items\n```\n\n**Creator loyalty:**\nWhich authors, directors, artists, and studios appear multiple times?\n\n**Era preferences:**\nWhen were the items in the collection made? Where does it cluster?\n\n**Genre gravity:**\nWhere does the collection mass? What genres dominate, what's sparse?\n\n**Rating patterns:**\nWhat do the 5-star items share? What do the low-rated items have in common? Is there a generous or harsh rating tendency?\n\n**The backlog:**\nWhat's sitting unread/unwatched? Is there a pattern to what gets deferred?\n\n### Step 3: Identify the Gaps\n\nWhat's conspicuously absent:\n- Entire genres they avoid\n- Eras they skip\n- Obvious works in genres they love that aren't present\n- Media types that are thin relative to others\n\nFrame gaps as curiosity, not criticism: \"You have deep coverage of [area] but almost nothing in [related area].\"\n\n### Step 4: Build the Taste Profile\n\nSynthesize everything into a profile, if this collection were a person, who would they be? What preoccupies them? What do they reach for when they need comfort vs. when they want to be challenged?\n\n### Step 5: Present the Review\n\n## Output Format\n\n```\n## Your Library\n\n**[N] items** across [media types], [one-line characterization of the collection's personality]\n\n---\n\n### The Numbers\n\n| Media Type | Total | Completed | Backlog | Avg Rating |\n|-----------|-------|-----------|---------|------------|\n| Books | [n] | [n] | [n] | [n]/5 |\n| Films | [n] | [n] | [n] | [n]/5 |\n| Albums | [n] | [n] | [n] | [n]/5 |\n| Shows | [n] | [n] | [n] | [n]/5 |\n| Anime | [n] | [n] | [n] | [n]/5 |\n\n### What Your Collection Says\n\n[2-3 paragraphs characterizing the collection's personality. Be specific , \nreference actual titles. This should feel like an observation about the person,\nnot a database summary.]\n\n### The Throughlines\n\n**[Theme 1]**: appears in [Title A] (book), [Title B] (film), [Title C] (album)\n[1-2 sentences on how this theme manifests differently across media]\n\n**[Theme 2]**: [same structure]\n\n**[Theme 3]**: [same structure]\n\n### Your Favorites Tell a Story\n\n[Analysis of the highest-rated items. What do they share? What does the\n\"best of\" shelf reveal about what moves this person?]\n\n### The Evolution\n\n[How taste has shifted over time, based on timeline data. Early additions\nvs. recent additions. Any notable pivots or deepening interests.]\n\n### The Blind Spots\n\n[What's absent. Frame as discovery opportunities, not deficiencies.]\n\n- **[Gap 1]**: [What's missing and why it's interesting given what IS present]\n- **[Gap 2]**: [Same]\n\n### The Backlog\n\n[What's sitting unread/unwatched. Any patterns? Any items that deserve\nto be bumped up the queue given recent taste?]\n\n\"Based on your recent ratings, **[unread title]** should probably move up your list.\"\n\n---\n\n### Taste Profile\n\n> **In a sentence:** [One-line characterization, \"You're drawn to stories about\n> [theme] told through [style], with a blind spot for [gap] and a soft spot for [weakness]\"]\n\n```\n\n## Notes\n\n- The collection review is the most data-intensive command. Pull everything before synthesizing.\n- Specific titles make this feel real. \"You like dark stories\" is useless. \"You gave 5 stars to No Country for Old Men, Blood Meridian, and There Will Be Blood, you're drawn to the American West as a space where morality dissolves\" is an insight.\n- The taste profile sentence at the end should feel like a revelation, not a summary\n- If the collection is small (under 20 items), note that patterns will be provisional\n- For very large collections, focus on the signal (high ratings, recent additions) rather than trying to characterize everything\n"
}

SHA-256: 8679c6dd44d67ac15e7ca31ccf608bdc05d1accf2db5f477232a5bcf1a625608