Update to Achriom
Snapshot Nov 5, 2026 · 00:16 UTC · version 2.1.1
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Instructions updated for recommendations
Skill instructions — Now says: query("SELECT i.kind, i.title, e.event_type, e.event_date FROM me.events e JOIN me.items i ON i.id = e.item_id AND i.kind = e.kind ORDER BY e.event_date DESC...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Sep 30, 2026 · 22:51 UTC
get_timeline(media_type) # Recent engagement
Nov 5, 2026 · 00:16 UTC
query("SELECT i.kind, i.title, e.event_type, e.event_date FROM me.events e JOIN me.items i ON i.id = e.item_id AND i.kind = e.kind ORDER BY e.event_date DESC NULLS LAST LIMIT 30") # Recent engagement
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -31,7 +31,7 @@ get_stats() # Overall shape get_by_rating(media_type, min_rating=4) # What they love search(media_type, query="relevant theme") -get_timeline(media_type) # Recent engagement +query("SELECT i.kind, i.title, e.event_type, e.event_date FROM me.events e JOIN me.items i ON i.id = e.item_id AND i.kind = e.kind ORDER BY e.event_date DESC NULLS LAST LIMIT 30") # Recent engagement ``` ### 3. Find Unread/Unwatched Gems
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: \"recommendations\"\ndescription: \"Cross-media recommendation methodology. Use when suggesting what to read, watch, or listen to next. Considers mood, themes, and patterns across all media types. Triggers on \\\"what should I...\\\" or \\\"recommend\\\" questions.\"\n---\n\n# Recommendations\n\n## When to Activate\n\n- User asks what to read/watch/listen to next\n- Looking for something similar to an item they loved\n- Seeking a specific mood or vibe\n- Want to explore a theme across media types\n- \"I'm in the mood for...\"\n\n## Recommendation Philosophy\n\n**Mine their collection first.** They already own things they haven't explored. Surface those before suggesting new acquisitions.\n\n**Cross-media connections.** If they loved a book's themes, find the film or album that shares that spirit.\n\n**Respect their taste.** Their ratings and notes tell you what resonates. Use that signal.\n\n## Recommendation Process\n\n### 1. Understand the Request\nWhat are they really asking for? Mood? Theme? Similar to something specific?\n\n### 2. Check Their Collection\n```\nget_stats() # Overall shape\nget_by_rating(media_type, min_rating=4) # What they love\nsearch(media_type, query=\"relevant theme\")\nget_timeline(media_type) # Recent engagement\n```\n\n### 3. Find Unread/Unwatched Gems\nSearch for items with matching themes that are still `unread`, `unwatched`, or `unheard`:\n```\nsearch(media_type=\"book\", query=\"theme\", filter=\"unread\")\n```\n\n### 4. Cross-Media Bridge\nIf they loved a book, search films:\n```\nsearch(media_type=\"movie\", query=\"theme from book\")\n```\nMake explicit connections: \"The melancholy in [book] shows up visually in [film]...\"\n\n### 5. Research New Suggestions\nIf nothing in collection fits, research:\n```\ntavily-search(query=\"books similar to [title] theme\")\n```\n\n## Recommendation Patterns\n\n**The unread shelf:** \"You have [book] sitting unread - given how much you loved [similar book], this might be the moment.\"\n\n**The mood match:** \"You rated [dark album] highly. [Other album] has that same weight.\"\n\n**The thematic thread:** \"This theme of isolation runs through your highest-rated items. Here's where else it appears...\"\n\n**The cross-pollination:** \"The director of [film] was influenced by [author] - you have both in your library.\"\n\n## Always Include\n\n- **Why** this recommendation fits (don't just list titles)\n- **Something to sample** - a track preview, a YouTube clip, a book passage\n- **The connection** to what they already love\n"
"---\nname: \"recommendations\"\ndescription: \"Cross-media recommendation methodology. Use when suggesting what to read, watch, or listen to next. Considers mood, themes, and patterns across all media types. Triggers on \\\"what should I...\\\" or \\\"recommend\\\" questions.\"\n---\n\n# Recommendations\n\n## When to Activate\n\n- User asks what to read/watch/listen to next\n- Looking for something similar to an item they loved\n- Seeking a specific mood or vibe\n- Want to explore a theme across media types\n- \"I'm in the mood for...\"\n\n## Recommendation Philosophy\n\n**Mine their collection first.** They already own things they haven't explored. Surface those before suggesting new acquisitions.\n\n**Cross-media connections.** If they loved a book's themes, find the film or album that shares that spirit.\n\n**Respect their taste.** Their ratings and notes tell you what resonates. Use that signal.\n\n## Recommendation Process\n\n### 1. Understand the Request\nWhat are they really asking for? Mood? Theme? Similar to something specific?\n\n### 2. Check Their Collection\n```\nget_stats() # Overall shape\nget_by_rating(media_type, min_rating=4) # What they love\nsearch(media_type, query=\"relevant theme\")\nquery(\"SELECT i.kind, i.title, e.event_type, e.event_date FROM me.events e JOIN me.items i ON i.id = e.item_id AND i.kind = e.kind ORDER BY e.event_date DESC NULLS LAST LIMIT 30\") # Recent engagement\n```\n\n### 3. Find Unread/Unwatched Gems\nSearch for items with matching themes that are still `unread`, `unwatched`, or `unheard`:\n```\nsearch(media_type=\"book\", query=\"theme\", filter=\"unread\")\n```\n\n### 4. Cross-Media Bridge\nIf they loved a book, search films:\n```\nsearch(media_type=\"movie\", query=\"theme from book\")\n```\nMake explicit connections: \"The melancholy in [book] shows up visually in [film]...\"\n\n### 5. Research New Suggestions\nIf nothing in collection fits, research:\n```\ntavily-search(query=\"books similar to [title] theme\")\n```\n\n## Recommendation Patterns\n\n**The unread shelf:** \"You have [book] sitting unread - given how much you loved [similar book], this might be the moment.\"\n\n**The mood match:** \"You rated [dark album] highly. [Other album] has that same weight.\"\n\n**The thematic thread:** \"This theme of isolation runs through your highest-rated items. Here's where else it appears...\"\n\n**The cross-pollination:** \"The director of [film] was influenced by [author] - you have both in your library.\"\n\n## Always Include\n\n- **Why** this recommendation fits (don't just list titles)\n- **Something to sample** - a track preview, a YouTube clip, a book passage\n- **The connection** to what they already love\n"
Full snapshot data
{
"description": "Cross-media recommendation methodology. Use when suggesting what to read, watch, or listen to next. Considers mood, themes, and patterns across all media types. Triggers on \"what should I...\" or \"recommend\" questions.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 205
}
],
"name": "recommendations",
"skill_md_contents": "---\nname: \"recommendations\"\ndescription: \"Cross-media recommendation methodology. Use when suggesting what to read, watch, or listen to next. Considers mood, themes, and patterns across all media types. Triggers on \\\"what should I...\\\" or \\\"recommend\\\" questions.\"\n---\n\n# Recommendations\n\n## When to Activate\n\n- User asks what to read/watch/listen to next\n- Looking for something similar to an item they loved\n- Seeking a specific mood or vibe\n- Want to explore a theme across media types\n- \"I'm in the mood for...\"\n\n## Recommendation Philosophy\n\n**Mine their collection first.** They already own things they haven't explored. Surface those before suggesting new acquisitions.\n\n**Cross-media connections.** If they loved a book's themes, find the film or album that shares that spirit.\n\n**Respect their taste.** Their ratings and notes tell you what resonates. Use that signal.\n\n## Recommendation Process\n\n### 1. Understand the Request\nWhat are they really asking for? Mood? Theme? Similar to something specific?\n\n### 2. Check Their Collection\n```\nget_stats() # Overall shape\nget_by_rating(media_type, min_rating=4) # What they love\nsearch(media_type, query=\"relevant theme\")\nquery(\"SELECT i.kind, i.title, e.event_type, e.event_date FROM me.events e JOIN me.items i ON i.id = e.item_id AND i.kind = e.kind ORDER BY e.event_date DESC NULLS LAST LIMIT 30\") # Recent engagement\n```\n\n### 3. Find Unread/Unwatched Gems\nSearch for items with matching themes that are still `unread`, `unwatched`, or `unheard`:\n```\nsearch(media_type=\"book\", query=\"theme\", filter=\"unread\")\n```\n\n### 4. Cross-Media Bridge\nIf they loved a book, search films:\n```\nsearch(media_type=\"movie\", query=\"theme from book\")\n```\nMake explicit connections: \"The melancholy in [book] shows up visually in [film]...\"\n\n### 5. Research New Suggestions\nIf nothing in collection fits, research:\n```\ntavily-search(query=\"books similar to [title] theme\")\n```\n\n## Recommendation Patterns\n\n**The unread shelf:** \"You have [book] sitting unread - given how much you loved [similar book], this might be the moment.\"\n\n**The mood match:** \"You rated [dark album] highly. [Other album] has that same weight.\"\n\n**The thematic thread:** \"This theme of isolation runs through your highest-rated items. Here's where else it appears...\"\n\n**The cross-pollination:** \"The director of [film] was influenced by [author] - you have both in your library.\"\n\n## Always Include\n\n- **Why** this recommendation fits (don't just list titles)\n- **Something to sample** - a track preview, a YouTube clip, a book passage\n- **The connection** to what they already love\n"
}SHA-256 of public snapshot: af0ce07c863a7ef4f6498a843d6a639d2e3e3bea86d1ad79b51ee181eabded34