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 discover
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() # Temporal patterns - For time-based questions, lean on `get_timeline()` and present chronologically
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") # Temporal patterns...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -34,7 +34,7 @@ search(media_type="show", query="theme") search(media_type="anime", query="theme") get_by_rating(min_rating=4) # Top-rated for pattern matching -get_timeline() # Temporal patterns +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") # Temporal patterns get_signals() # Behavioral patterns ``` @@ -119,5 +119,5 @@ - Lead with the most interesting connection, not the most obvious one - Cross-media connections are more valuable than within-media ones, finding that a book and an album share DNA is more interesting than two similar books - If the search doesn't surface clear connections, say so. "This theme doesn't have deep roots in your collection yet" is a valid finding. -- For time-based questions, lean on `get_timeline()` and present chronologically +- For time-based questions, lean on `query` over `me.events` (history with dates) and present chronologically - Always include at least one experiential element (audio, video, or quote)
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: \"discover\"\ndescription: \"Explore a theme, mood, or idea across your entire collection\"\n---\n\n# Follow a Thread Across Your Library\n\nTake a theme, mood, or idea and trace it through everything you own. Books, films, albums, shows, anime, find where the thread appears across media.\n\n\n## Workflow\n\n### Step 1: Define the Thread\n\nUnderstand what the user wants to explore:\n\n- **A theme**: loneliness, identity, rebellion, memory, home\n- **A mood**: melancholy, restless, hopeful, unsettling\n- **A pattern question**: \"what do my 5-star items have in common?\"\n- **A time-based question**: \"what was I into last year?\"\n- **An abstract idea**: \"the relationship between art and commerce\"\n\nIf the request is broad, start searching and let the collection shape the direction. Don't over-plan, discover alongside the user.\n\n### Step 2: Search Across All Media Types\n\nUsing the **collection-insights** skill methodology, search systematically:\n\n```\nget_stats() # Collection shape\nsearch(media_type=\"book\", query=\"theme\")\nsearch(media_type=\"movie\", query=\"theme\")\nsearch(media_type=\"album\", query=\"theme\")\nsearch(media_type=\"show\", query=\"theme\")\nsearch(media_type=\"anime\", query=\"theme\")\nget_by_rating(min_rating=4) # Top-rated for pattern matching\nget_timeline() # Temporal patterns\nget_signals() # Behavioral patterns\n```\n\nFor pattern questions, lean on:\n```\nget_by_rating(min_rating=5) # What do their favorites share?\nget_context() # Broader behavioral signals\n```\n\n### Step 3: Map the Connections\n\nIdentify where the thread appears:\n\n1. **Direct matches**: items explicitly about the theme\n2. **Indirect matches**: items where the theme lives beneath the surface\n3. **Surprising matches**: items you wouldn't expect to connect but do\n4. **Cross-media pairs**: a book and a film circling the same idea from different angles\n\nFor each connection, get details:\n```\nget_details(media_type, title) # For the most relevant items\n```\n\n### Step 4: Find the Story\n\nThe thread should tell a story. Using the **collection-insights** skill patterns:\n\n- **The throughline**: Where does this theme keep appearing?\n- **The evolution**: Has their relationship to this theme changed over time?\n- **The constellation**: Which items from different media types orbit the same idea?\n- **The absence**: Is there a notable gap, a direction this theme could go that they haven't explored?\n\n### Step 5: Make It Experiential\n\nFor the strongest connections, bring them to life:\n- Play a track that captures the mood: `get_track_previews()`\n- Embed a scene or video essay: `search_youtube()`\n- Quote a passage: `search_book_content()`\n\n### Step 6: Present the Discovery\n\n## Output Format\n\n```\n## [Theme/Mood]: Across Your Collection\n\n[Opening observation, what you found when you pulled this thread.\nOne paragraph, no preamble.]\n\n### The Thread\n\n[Map of where this theme appears. Group by connection strength,\nnot by media type. The most compelling connections first.]\n\n**[Title 1]** ([media type]) and **[Title 2]** ([media type])\n[How these two items connect through the theme, be specific]\n\n[Embedded media if available]\n\n**[Title 3]** ([media type])\n[How this item carries the theme in a different direction]\n\n---\n\n### The Surprise Connection\n\n[The pairing or connection the user probably hasn't noticed.\nThis is the insight that makes discovery worthwhile.]\n\n### The Gap\n\n[Where this thread could go but hasn't yet in their collection.\nFrame as invitation, not criticism.]\n\n\"You've explored [theme] through [angle], but there's a whole tradition\nof [unexplored angle] you might find interesting, [1-2 specific suggestions].\"\n\n```\n\n## Notes\n\n- Lead with the most interesting connection, not the most obvious one\n- Cross-media connections are more valuable than within-media ones, finding that a book and an album share DNA is more interesting than two similar books\n- If the search doesn't surface clear connections, say so. \"This theme doesn't have deep roots in your collection yet\" is a valid finding.\n- For time-based questions, lean on `get_timeline()` and present chronologically\n- Always include at least one experiential element (audio, video, or quote)\n"
"---\nname: \"discover\"\ndescription: \"Explore a theme, mood, or idea across your entire collection\"\n---\n\n# Follow a Thread Across Your Library\n\nTake a theme, mood, or idea and trace it through everything you own. Books, films, albums, shows, anime, find where the thread appears across media.\n\n\n## Workflow\n\n### Step 1: Define the Thread\n\nUnderstand what the user wants to explore:\n\n- **A theme**: loneliness, identity, rebellion, memory, home\n- **A mood**: melancholy, restless, hopeful, unsettling\n- **A pattern question**: \"what do my 5-star items have in common?\"\n- **A time-based question**: \"what was I into last year?\"\n- **An abstract idea**: \"the relationship between art and commerce\"\n\nIf the request is broad, start searching and let the collection shape the direction. Don't over-plan, discover alongside the user.\n\n### Step 2: Search Across All Media Types\n\nUsing the **collection-insights** skill methodology, search systematically:\n\n```\nget_stats() # Collection shape\nsearch(media_type=\"book\", query=\"theme\")\nsearch(media_type=\"movie\", query=\"theme\")\nsearch(media_type=\"album\", query=\"theme\")\nsearch(media_type=\"show\", query=\"theme\")\nsearch(media_type=\"anime\", query=\"theme\")\nget_by_rating(min_rating=4) # Top-rated for pattern matching\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\") # Temporal patterns\nget_signals() # Behavioral patterns\n```\n\nFor pattern questions, lean on:\n```\nget_by_rating(min_rating=5) # What do their favorites share?\nget_context() # Broader behavioral signals\n```\n\n### Step 3: Map the Connections\n\nIdentify where the thread appears:\n\n1. **Direct matches**: items explicitly about the theme\n2. **Indirect matches**: items where the theme lives beneath the surface\n3. **Surprising matches**: items you wouldn't expect to connect but do\n4. **Cross-media pairs**: a book and a film circling the same idea from different angles\n\nFor each connection, get details:\n```\nget_details(media_type, title) # For the most relevant items\n```\n\n### Step 4: Find the Story\n\nThe thread should tell a story. Using the **collection-insights** skill patterns:\n\n- **The throughline**: Where does this theme keep appearing?\n- **The evolution**: Has their relationship to this theme changed over time?\n- **The constellation**: Which items from different media types orbit the same idea?\n- **The absence**: Is there a notable gap, a direction this theme could go that they haven't explored?\n\n### Step 5: Make It Experiential\n\nFor the strongest connections, bring them to life:\n- Play a track that captures the mood: `get_track_previews()`\n- Embed a scene or video essay: `search_youtube()`\n- Quote a passage: `search_book_content()`\n\n### Step 6: Present the Discovery\n\n## Output Format\n\n```\n## [Theme/Mood]: Across Your Collection\n\n[Opening observation, what you found when you pulled this thread.\nOne paragraph, no preamble.]\n\n### The Thread\n\n[Map of where this theme appears. Group by connection strength,\nnot by media type. The most compelling connections first.]\n\n**[Title 1]** ([media type]) and **[Title 2]** ([media type])\n[How these two items connect through the theme, be specific]\n\n[Embedded media if available]\n\n**[Title 3]** ([media type])\n[How this item carries the theme in a different direction]\n\n---\n\n### The Surprise Connection\n\n[The pairing or connection the user probably hasn't noticed.\nThis is the insight that makes discovery worthwhile.]\n\n### The Gap\n\n[Where this thread could go but hasn't yet in their collection.\nFrame as invitation, not criticism.]\n\n\"You've explored [theme] through [angle], but there's a whole tradition\nof [unexplored angle] you might find interesting, [1-2 specific suggestions].\"\n\n```\n\n## Notes\n\n- Lead with the most interesting connection, not the most obvious one\n- Cross-media connections are more valuable than within-media ones, finding that a book and an album share DNA is more interesting than two similar books\n- If the search doesn't surface clear connections, say so. \"This theme doesn't have deep roots in your collection yet\" is a valid finding.\n- For time-based questions, lean on `query` over `me.events` (history with dates) and present chronologically\n- Always include at least one experiential element (audio, video, or quote)\n"
Full snapshot data
{
"description": "Explore a theme, mood, or idea across your entire collection",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 282
}
],
"name": "discover",
"skill_md_contents": "---\nname: \"discover\"\ndescription: \"Explore a theme, mood, or idea across your entire collection\"\n---\n\n# Follow a Thread Across Your Library\n\nTake a theme, mood, or idea and trace it through everything you own. Books, films, albums, shows, anime, find where the thread appears across media.\n\n\n## Workflow\n\n### Step 1: Define the Thread\n\nUnderstand what the user wants to explore:\n\n- **A theme**: loneliness, identity, rebellion, memory, home\n- **A mood**: melancholy, restless, hopeful, unsettling\n- **A pattern question**: \"what do my 5-star items have in common?\"\n- **A time-based question**: \"what was I into last year?\"\n- **An abstract idea**: \"the relationship between art and commerce\"\n\nIf the request is broad, start searching and let the collection shape the direction. Don't over-plan, discover alongside the user.\n\n### Step 2: Search Across All Media Types\n\nUsing the **collection-insights** skill methodology, search systematically:\n\n```\nget_stats() # Collection shape\nsearch(media_type=\"book\", query=\"theme\")\nsearch(media_type=\"movie\", query=\"theme\")\nsearch(media_type=\"album\", query=\"theme\")\nsearch(media_type=\"show\", query=\"theme\")\nsearch(media_type=\"anime\", query=\"theme\")\nget_by_rating(min_rating=4) # Top-rated for pattern matching\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\") # Temporal patterns\nget_signals() # Behavioral patterns\n```\n\nFor pattern questions, lean on:\n```\nget_by_rating(min_rating=5) # What do their favorites share?\nget_context() # Broader behavioral signals\n```\n\n### Step 3: Map the Connections\n\nIdentify where the thread appears:\n\n1. **Direct matches**: items explicitly about the theme\n2. **Indirect matches**: items where the theme lives beneath the surface\n3. **Surprising matches**: items you wouldn't expect to connect but do\n4. **Cross-media pairs**: a book and a film circling the same idea from different angles\n\nFor each connection, get details:\n```\nget_details(media_type, title) # For the most relevant items\n```\n\n### Step 4: Find the Story\n\nThe thread should tell a story. Using the **collection-insights** skill patterns:\n\n- **The throughline**: Where does this theme keep appearing?\n- **The evolution**: Has their relationship to this theme changed over time?\n- **The constellation**: Which items from different media types orbit the same idea?\n- **The absence**: Is there a notable gap, a direction this theme could go that they haven't explored?\n\n### Step 5: Make It Experiential\n\nFor the strongest connections, bring them to life:\n- Play a track that captures the mood: `get_track_previews()`\n- Embed a scene or video essay: `search_youtube()`\n- Quote a passage: `search_book_content()`\n\n### Step 6: Present the Discovery\n\n## Output Format\n\n```\n## [Theme/Mood]: Across Your Collection\n\n[Opening observation, what you found when you pulled this thread.\nOne paragraph, no preamble.]\n\n### The Thread\n\n[Map of where this theme appears. Group by connection strength,\nnot by media type. The most compelling connections first.]\n\n**[Title 1]** ([media type]) and **[Title 2]** ([media type])\n[How these two items connect through the theme, be specific]\n\n[Embedded media if available]\n\n**[Title 3]** ([media type])\n[How this item carries the theme in a different direction]\n\n---\n\n### The Surprise Connection\n\n[The pairing or connection the user probably hasn't noticed.\nThis is the insight that makes discovery worthwhile.]\n\n### The Gap\n\n[Where this thread could go but hasn't yet in their collection.\nFrame as invitation, not criticism.]\n\n\"You've explored [theme] through [angle], but there's a whole tradition\nof [unexplored angle] you might find interesting, [1-2 specific suggestions].\"\n\n```\n\n## Notes\n\n- Lead with the most interesting connection, not the most obvious one\n- Cross-media connections are more valuable than within-media ones, finding that a book and an album share DNA is more interesting than two similar books\n- If the search doesn't surface clear connections, say so. \"This theme doesn't have deep roots in your collection yet\" is a valid finding.\n- For time-based questions, lean on `query` over `me.events` (history with dates) and present chronologically\n- Always include at least one experiential element (audio, video, or quote)\n"
}SHA-256 of public snapshot: e9cfcfc2846c8d1c3a57e8da178eb13ab508b95f81811dc1cc62bc57d4a66170