[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75KB8VHYJ1TYVBTF97BFV0G":3,"skill-same:01M75KB8VHYJ1TYVBTF97BFV0G":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M75KB8VHYJ1TYVBTF97BFV0G","nate-jones-second-brain",null,"Set up and operate a personal knowledge system using Supabase (pgvector) and OpenRouter. Five structured tables — thoughts (inbox log), people, projects, ideas, admin — with AI-powered classification, confidence-based routing, and semantic search across all categories. Captures thoughts from any source, classifies them via LLM, routes them to the right table (the Sorter), rejects low-confidence classifications (the Bouncer), and logs everything (the Receipt). Two opinionated primitives — Supabase for persistent context architecture, OpenRouter as the AI gateway — that unlock unlimited applications on top. The foundation layer for a personal knowledge system. By Limited Edition Jonathan • natebjones.com","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjustfinethanku\u002Fnate-jones-second-brain\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: nate-jones-second-brain\ndescription: Set up and operate a personal knowledge system using Supabase (pgvector) and OpenRouter. Five structured tables — thoughts (inbox log), people, projects, ideas, admin — with AI-powered classification, confidence-based routing, and semantic search across all categories. Captures thoughts from any source, classifies them via LLM, routes them to the right table (the Sorter), rejects low-confidence classifications (the Bouncer), and logs everything (the Receipt). Two opinionated primitives — Supabase for persistent context architecture, OpenRouter as the AI gateway — that unlock unlimited applications on top. The foundation layer for a personal knowledge system. By Limited Edition Jonathan • natebjones.com\nmetadata: {\"openclaw\": {\"requires\": {\"env\": [\"SUPABASE_URL\", \"SUPABASE_SERVICE_ROLE_KEY\", \"OPENROUTER_API_KEY\"]}, \"homepage\": \"https:\u002F\u002Fnatebjones.com\"}}\n---\n\n# Nate Jones Second Brain\n\nWhen intelligence is abundant, context becomes the scarce resource. This skill is context architecture — a persistent, searchable knowledge layer that turns your agent into a personal knowledge manager.\n\nTwo opinionated primitives:\n\n- **Supabase** — your database, and so much more. PostgreSQL + pgvector. Stores thoughts, people, projects, ideas, and tasks as structured data with vector embeddings. REST API built in. Your data, your infrastructure. Models come and go; your context persists. And once you have a Supabase project, you've unlocked the foundation for everything else you'll want to build — the Second Brain is just the beginning.\n- **OpenRouter** — your AI gateway. One API key, every model. Embeddings and LLM calls for classification and routing. Swap models by changing a string. Future-proof by design.\n\nEverything else — how you capture thoughts, how you retrieve them, what you build on top — is application layer. The skill covers the foundation.\n\n> If the tables don't exist yet, see `{baseDir}\u002Freferences\u002Fsetup.md`\n\n## Building Blocks\n\nThese are the operational concepts behind the system. Understanding them helps you operate correctly.\n\n| Block | What It Does | Implementation |\n|-------|-------------|----------------|\n| **Drop Box** | One frictionless capture point | Everything goes to `thoughts` first |\n| **Sorter** | AI classification + routing | LLM classifies type, then routes to structured table |\n| **Form** | Consistent data contracts | Each table has a defined schema |\n| **Filing Cabinet** | Source of truth per category | `people`, `projects`, `ideas`, `admin` tables |\n| **Bouncer** | Confidence threshold | confidence \u003C 0.6 = don't route, stay in inbox |\n| **Receipt** | Audit trail | `thoughts` row logs what came in, where it went |\n| **Tap on the Shoulder** | Proactive surfacing | Daily digest queries (application layer) |\n| **Fix Button** | Agent-mediated corrections | Move records between tables on user request |\n\nFull conceptual framework: `{baseDir}\u002Freferences\u002Fconcepts.md`\n\n## Five Tables\n\n| Table | Role | Key Fields |\n|-------|------|------------|\n| `thoughts` | Inbox Log \u002F audit trail | content, embedding, metadata (type, topics, people, confidence, routed_to) |\n| `people` | Relationship tracking | name (unique), context, follow_ups, tags, embedding |\n| `projects` | Work tracking | name, status, next_action, notes, tags, embedding |\n| `ideas` | Insight capture | title, summary, elaboration, topics, embedding |\n| `admin` | Task management | name, due_date, status, notes, embedding |\n\nEvery table has semantic search via its own `match_*` function. Cross-table search via `search_all`.\n\n## Routing Rules\n\nWhen a thought is classified:\n\n| Type | Route | Action |\n|------|-------|--------|\n| `person_note` | `people` | Upsert: create person or append to existing context |\n| `task` | `admin` | Insert new task (status=pending) |\n| `idea` | `ideas` | Insert new idea |\n| `observation` | none | Stays in thoughts only |\n| `reference` | none | Stays in thoughts only |\n\nIf confidence \u003C 0.6, don't route. Leave in thoughts, tell user.\n\n## Quick Start\n\n### Capture a thought (full pipeline)\n\n```bash\n# 1. Embed\nEMBEDDING=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fembeddings\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Ftext-embedding-3-small\", \"input\": \"Sarah mentioned she is thinking about leaving her job to start consulting\"}' \\\n  | jq -c '.data[0].embedding')\n\n# 2. Classify (run in parallel with step 1)\nMETADATA=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Fgpt-4o-mini\", \"response_format\": {\"type\": \"json_object\"}, \"messages\": [{\"role\": \"system\", \"content\": \"Extract metadata from the captured thought. Return JSON with: type (observation\u002Ftask\u002Fidea\u002Freference\u002Fperson_note), topics (1-3 tags), people (array), action_items (array), dates_mentioned (array), confidence (0-1), suggested_route (people\u002Fprojects\u002Fideas\u002Fadmin\u002Fnull), extracted_fields (structured data for destination table).\"}, {\"role\": \"user\", \"content\": \"Sarah mentioned she is thinking about leaving her job to start consulting\"}]}' \\\n  | jq -r '.choices[0].message.content')\n\n# 3. Store in thoughts (the Receipt)\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fthoughts\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Prefer: return=representation\" \\\n  -d \"[{\\\"content\\\": \\\"Sarah mentioned she is thinking about leaving her job to start consulting\\\", \\\"embedding\\\": $EMBEDDING, \\\"metadata\\\": $METADATA}]\"\n\n# 4. Route based on classification (if confidence >= 0.6)\n```\n\nFull pipeline with routing logic: `{baseDir}\u002Freferences\u002Fingest.md`\n\n### Semantic search (single table)\n\n```bash\nQUERY_EMBEDDING=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fembeddings\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Ftext-embedding-3-small\", \"input\": \"career changes\"}' \\\n  | jq -c '.data[0].embedding')\n\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Frpc\u002Fmatch_thoughts\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query_embedding\\\": $QUERY_EMBEDDING, \\\"match_threshold\\\": 0.5, \\\"match_count\\\": 10, \\\"filter\\\": {}}\"\n```\n\n### Cross-table search\n\n```bash\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Frpc\u002Fsearch_all\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query_embedding\\\": $QUERY_EMBEDDING, \\\"match_threshold\\\": 0.5, \\\"match_count\\\": 20}\"\n```\n\nReturns `table_name`, `record_id`, `label`, `detail`, `similarity`, `created_at` from all tables.\n\n### List active projects\n\n```bash\ncurl -s \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fprojects?status=eq.active&select=name,next_action,notes&order=updated_at.desc\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\"\n```\n\n### List pending tasks\n\n```bash\ncurl -s \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fadmin?status=eq.pending&select=name,due_date,notes&order=due_date.asc\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\"\n```\n\n## Ingest Pipeline\n\nWhen content arrives from any source:\n\n1. **Embed** the text via OpenRouter (1536-dim vector)\n2. **Classify** via OpenRouter LLM (type, topics, people, confidence, suggested route)\n3. **Log** in `thoughts` (the Receipt — always, regardless of routing)\n4. **Bounce check** — if confidence \u003C 0.6, stop here\n5. **Route** to structured table based on type (the Sorter)\n6. **Confirm** to the user what was captured and where it was filed\n\nFull pipeline details: `{baseDir}\u002Freferences\u002Fingest.md`\n\n## Metadata Schema\n\nEvery thought gets classified with:\n\n| Field | Type | Values |\n|-------|------|--------|\n| `type` | string | `observation`, `task`, `idea`, `reference`, `person_note` |\n| `topics` | string[] | 1-3 short topic tags (always at least one) |\n| `people` | string[] | People mentioned (empty if none) |\n| `action_items` | string[] | Implied to-dos (empty if none) |\n| `dates_mentioned` | string[] | Dates in YYYY-MM-DD format (empty if none) |\n| `source` | string | Where it came from: `slack`, `signal`, `cli`, `manual`, etc. |\n| `confidence` | float | LLM classification confidence (0-1). The Bouncer uses this. |\n| `routed_to` | string | Which table the thought was filed into (null if unrouted) |\n| `routed_id` | string | UUID of the record in the destination table (null if unrouted) |\n\n## References\n\n- **Conceptual framework:** `{baseDir}\u002Freferences\u002Fconcepts.md`\n- **First-time setup:** `{baseDir}\u002Freferences\u002Fsetup.md`\n- **Database schema (SQL):** `{baseDir}\u002Freferences\u002Fschema.md`\n- **Ingest pipeline details:** `{baseDir}\u002Freferences\u002Fingest.md`\n- **Retrieval operations:** `{baseDir}\u002Freferences\u002Fretrieval.md`\n- **OpenRouter API patterns:** `{baseDir}\u002Freferences\u002Fopenrouter.md`\n\n## Env Vars\n\n| Variable | Service |\n|----------|---------|\n| `SUPABASE_URL` | Supabase project REST base URL |\n| `SUPABASE_SERVICE_ROLE_KEY` | Supabase auth (full access) |\n| `OPENROUTER_API_KEY` | OpenRouter API key |\n\n## Security Notes\n\n**Why service_role key?** Supabase provides two keys: `anon` (public, respects RLS) and `service_role` (full access, bypasses RLS). This skill uses `service_role` because:\n\n- This is a **single-user personal knowledge base**, not a multi-tenant app\n- Your agent IS the trusted server-side component\n- The RLS policy restricts access to `service_role` only — the most restrictive option\n- Using the `anon` key would require loosening RLS to allow anonymous access to your thoughts, which is worse\n\n**Data sent to OpenRouter:** All captured text (thoughts, names, action items) is sent to OpenRouter for embedding and classification. This is inherent to the design — you need AI to understand meaning. Don't capture highly sensitive information unless you accept OpenRouter's data handling policies.\n\n**Key handling:** Store `SUPABASE_SERVICE_ROLE_KEY` and `OPENROUTER_API_KEY` securely. Never commit them to public repos. Rotate periodically. In OpenClaw, store them in `openclaw.json` under `skills.entries` or as environment variables.\n\n---\n\nBuilt by Limited Edition Jonathan • natebjones.com\n","# Nate Jones Second Brain\n\nWhen intelligence is abundant, context becomes the scarce resource. This skill is context architecture — a persistent, searchable knowledge layer that turns your agent into a personal knowledge manager.\n\nTwo opinionated primitives:\n\n- **Supabase** — your database, and so much more. PostgreSQL + pgvector. Stores thoughts, people, projects, ideas, and tasks as structured data with vector embeddings. REST API built in. Your data, your infrastructure. Models come and go; your context persists. And once you have a Supabase project, you've unlocked the foundation for everything else you'll want to build — the Second Brain is just the beginning.\n- **OpenRouter** — your AI gateway. One API key, every model. Embeddings and LLM calls for classification and routing. Swap models by changing a string. Future-proof by design.\n\nEverything else — how you capture thoughts, how you retrieve them, what you build on top — is application layer. The skill covers the foundation.\n\n> If the tables don't exist yet, see `{baseDir}\u002Freferences\u002Fsetup.md`\n\n## Building Blocks\n\nThese are the operational concepts behind the system. Understanding them helps you operate correctly.\n\n| Block | What It Does | Implementation |\n|-------|-------------|----------------|\n| **Drop Box** | One frictionless capture point | Everything goes to `thoughts` first |\n| **Sorter** | AI classification + routing | LLM classifies type, then routes to structured table |\n| **Form** | Consistent data contracts | Each table has a defined schema |\n| **Filing Cabinet** | Source of truth per category | `people`, `projects`, `ideas`, `admin` tables |\n| **Bouncer** | Confidence threshold | confidence \u003C 0.6 = don't route, stay in inbox |\n| **Receipt** | Audit trail | `thoughts` row logs what came in, where it went |\n| **Tap on the Shoulder** | Proactive surfacing | Daily digest queries (application layer) |\n| **Fix Button** | Agent-mediated corrections | Move records between tables on user request |\n\nFull conceptual framework: `{baseDir}\u002Freferences\u002Fconcepts.md`\n\n## Five Tables\n\n| Table | Role | Key Fields |\n|-------|------|------------|\n| `thoughts` | Inbox Log \u002F audit trail | content, embedding, metadata (type, topics, people, confidence, routed_to) |\n| `people` | Relationship tracking | name (unique), context, follow_ups, tags, embedding |\n| `projects` | Work tracking | name, status, next_action, notes, tags, embedding |\n| `ideas` | Insight capture | title, summary, elaboration, topics, embedding |\n| `admin` | Task management | name, due_date, status, notes, embedding |\n\nEvery table has semantic search via its own `match_*` function. Cross-table search via `search_all`.\n\n## Routing Rules\n\nWhen a thought is classified:\n\n| Type | Route | Action |\n|------|-------|--------|\n| `person_note` | `people` | Upsert: create person or append to existing context |\n| `task` | `admin` | Insert new task (status=pending) |\n| `idea` | `ideas` | Insert new idea |\n| `observation` | none | Stays in thoughts only |\n| `reference` | none | Stays in thoughts only |\n\nIf confidence \u003C 0.6, don't route. Leave in thoughts, tell user.\n\n## Quick Start\n\n### Capture a thought (full pipeline)\n\n```bash\n# 1. Embed\nEMBEDDING=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fembeddings\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Ftext-embedding-3-small\", \"input\": \"Sarah mentioned she is thinking about leaving her job to start consulting\"}' \\\n  | jq -c '.data[0].embedding')\n\n# 2. Classify (run in parallel with step 1)\nMETADATA=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Fgpt-4o-mini\", \"response_format\": {\"type\": \"json_object\"}, \"messages\": [{\"role\": \"system\", \"content\": \"Extract metadata from the captured thought. Return JSON with: type (observation\u002Ftask\u002Fidea\u002Freference\u002Fperson_note), topics (1-3 tags), people (array), action_items (array), dates_mentioned (array), confidence (0-1), suggested_route (people\u002Fprojects\u002Fideas\u002Fadmin\u002Fnull), extracted_fields (structured data for destination table).\"}, {\"role\": \"user\", \"content\": \"Sarah mentioned she is thinking about leaving her job to start consulting\"}]}' \\\n  | jq -r '.choices[0].message.content')\n\n# 3. Store in thoughts (the Receipt)\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fthoughts\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Prefer: return=representation\" \\\n  -d \"[{\\\"content\\\": \\\"Sarah mentioned she is thinking about leaving her job to start consulting\\\", \\\"embedding\\\": $EMBEDDING, \\\"metadata\\\": $METADATA}]\"\n\n# 4. Route based on classification (if confidence >= 0.6)\n```\n\nFull pipeline with routing logic: `{baseDir}\u002Freferences\u002Fingest.md`\n\n### Semantic search (single table)\n\n```bash\nQUERY_EMBEDDING=$(curl -s -X POST \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fembeddings\" \\\n  -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"openai\u002Ftext-embedding-3-small\", \"input\": \"career changes\"}' \\\n  | jq -c '.data[0].embedding')\n\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Frpc\u002Fmatch_thoughts\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query_embedding\\\": $QUERY_EMBEDDING, \\\"match_threshold\\\": 0.5, \\\"match_count\\\": 10, \\\"filter\\\": {}}\"\n```\n\n### Cross-table search\n\n```bash\ncurl -s -X POST \"$SUPABASE_URL\u002Frest\u002Fv1\u002Frpc\u002Fsearch_all\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"query_embedding\\\": $QUERY_EMBEDDING, \\\"match_threshold\\\": 0.5, \\\"match_count\\\": 20}\"\n```\n\nReturns `table_name`, `record_id`, `label`, `detail`, `similarity`, `created_at` from all tables.\n\n### List active projects\n\n```bash\ncurl -s \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fprojects?status=eq.active&select=name,next_action,notes&order=updated_at.desc\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\"\n```\n\n### List pending tasks\n\n```bash\ncurl -s \"$SUPABASE_URL\u002Frest\u002Fv1\u002Fadmin?status=eq.pending&select=name,due_date,notes&order=due_date.asc\" \\\n  -H \"apikey: $SUPABASE_SERVICE_ROLE_KEY\" \\\n  -H \"Authorization: Bearer $SUPABASE_SERVICE_ROLE_KEY\"\n```\n\n## Ingest Pipeline\n\nWhen content arrives from any source:\n\n1. **Embed** the text via OpenRouter (1536-dim vector)\n2. **Classify** via OpenRouter LLM (type, topics, people, confidence, suggested route)\n3. **Log** in `thoughts` (the Receipt — always, regardless of routing)\n4. **Bounce check** — if confidence \u003C 0.6, stop here\n5. **Route** to structured table based on type (the Sorter)\n6. **Confirm** to the user what was captured and where it was filed\n\nFull pipeline details: `{baseDir}\u002Freferences\u002Fingest.md`\n\n## Metadata Schema\n\nEvery thought gets classified with:\n\n| Field | Type | Values |\n|-------|------|--------|\n| `type` | string | `observation`, `task`, `idea`, `reference`, `person_note` |\n| `topics` | string[] | 1-3 short topic tags (always at least one) |\n| `people` | string[] | People mentioned (empty if none) |\n| `action_items` | string[] | Implied to-dos (empty if none) |\n| `dates_mentioned` | string[] | Dates in YYYY-MM-DD format (empty if none) |\n| `source` | string | Where it came from: `slack`, `signal`, `cli`, `manual`, etc. |\n| `confidence` | float | LLM classification confidence (0-1). The Bouncer uses this. |\n| `routed_to` | string | Which table the thought was filed into (null if unrouted) |\n| `routed_id` | string | UUID of the record in the destination table (null if unrouted) |\n\n## References\n\n- **Conceptual framework:** `{baseDir}\u002Freferences\u002Fconcepts.md`\n- **First-time setup:** `{baseDir}\u002Freferences\u002Fsetup.md`\n- **Database schema (SQL):** `{baseDir}\u002Freferences\u002Fschema.md`\n- **Ingest pipeline details:** `{baseDir}\u002Freferences\u002Fingest.md`\n- **Retrieval operations:** `{baseDir}\u002Freferences\u002Fretrieval.md`\n- **OpenRouter API patterns:** `{baseDir}\u002Freferences\u002Fopenrouter.md`\n\n## Env Vars\n\n| Variable | Service |\n|----------|---------|\n| `SUPABASE_URL` | Supabase project REST base URL |\n| `SUPABASE_SERVICE_ROLE_KEY` | Supabase auth (full access) |\n| `OPENROUTER_API_KEY` | OpenRouter API key |\n\n## Security Notes\n\n**Why service_role key?** Supabase provides two keys: `anon` (public, respects RLS) and `service_role` (full access, bypasses RLS). This skill uses `service_role` because:\n\n- This is a **single-user personal knowledge base**, not a multi-tenant app\n- Your agent IS the trusted server-side component\n- The RLS policy restricts access to `service_role` only — the most restrictive option\n- Using the `anon` key would require loosening RLS to allow anonymous access to your thoughts, which is worse\n\n**Data sent to OpenRouter:** All captured text (thoughts, names, action items) is sent to OpenRouter for embedding and classification. This is inherent to the design — you need AI to understand meaning. Don't capture highly sensitive information unless you accept OpenRouter's data handling policies.\n\n**Key handling:** Store `SUPABASE_SERVICE_ROLE_KEY` and `OPENROUTER_API_KEY` securely. Never commit them to public repos. Rotate periodically. In OpenClaw, store them in `openclaw.json` under `skills.entries` or as environment variables.\n\n---\n\nBuilt by Limited Edition Jonathan • natebjones.com\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"homepage":26,"requires":27},"https:\u002F\u002Fnatebjones.com",{"env":28},[29,30,31],"SUPABASE_URL","SUPABASE_SERVICE_ROLE_KEY","OPENROUTER_API_KEY","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fjustfinethanku\u002Fnate-jones-second-brain",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill nate-jones-second-brain",{"tool":47,"command":48},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill nate-jones-second-brain",{"tool":50,"command":51},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill nate-jones-second-brain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fjustfinethanku\u002Fnate-jones-second-brain\u002FSKILL.md",true,[],[56,64,71,78,85,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":63},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":63},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":63},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":63},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":63},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]