[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75Y94YGPRFCHJ6AC4ZAGCF2":3,"skill-same:01M75Y94YGPRFCHJ6AC4ZAGCF2":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":28,"updatedAt":29,"install":30,"resources":43},"01M75Y94YGPRFCHJ6AC4ZAGCF2","memex:brain:capture",null,"Capture a free-form note or observation into the personal Brain (~\u002F.memex\u002Farticle.db.captures). Lighter than ingest — no source URL, no raw archive, but still routed through the Librarian subagent for classification and linking.","nitekeeper\u002Fmemex","nitekeeper","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130331363?v=4","01M75Y8ZMS1S9AFVBJN1DY5116","01M75Y8ZNHA5WFYR4A94NKZN76",0,"MIT","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fbrain\u002Fcapture\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: memex:brain:capture\ndescription: Capture a free-form note or observation into the personal Brain (~\u002F.memex\u002Farticle.db.captures). Lighter than ingest — no source URL, no raw archive, but still routed through the Librarian subagent for classification and linking.\n---\n\n# memex:brain:capture\n\n## When to use\n\nThe user wants to record a thought, observation, or short snippet that isn't sourced from elsewhere. No URL, no provenance — just a note that should be findable later.\n\n## Inputs\n\n- `body` — the note text\n- `caller_agent_id` — registered agent id\n- `title` — optional short label\n\n## Recipe (Option-B Task-tool dispatch)\n\n### Step 1 — Prepare\n\n```python\nfrom scripts import brain\nprep = brain.capture_prepare(\n    body=body,\n    caller_agent_id=caller_agent_id,\n    title=title,  # may be None\n)\n```\n\n`prep[\"status\"]` is always `\"ready\"` (no source-hash dedup for captures — every capture is a fresh thought).\n\n### Step 2 — Dispatch the Librarian subagent\n\nUse the **Task tool**:\n\n- `subagent_type`: `general-purpose`\n- `description`: `Librarian: classify capture`\n- `prompt`: `prep[\"subagent_prompt\"]`\n- `model`: `claude-sonnet-4-6`\n\n> sonnet — bounded payload, deliberate downshift, never silent. (Enforced by `tests\u002Ftest_model_tier_dispatch.py`.)\n\nSame Librarian profile + classification policy as ingest; the subagent decides `domain=\"capture\"` (or whatever fits — Librarian's judgment).\n\n### Step 3 — Parse and validate\n\n```python\nfrom scripts.agents import librarian\nlibrarian_output = librarian.parse_response(subagent_response)\n```\n\nRetry once on `ValueError`. After two failures, report BLOCKED.\n\n### Step 4 — Encode embedding (optional)\n\n```python\nfrom scripts import embeddings\nembedding = embeddings.encode_or_skip(\n    librarian_output[\"searchable\"],\n    caller_agent_id=\"brain-capture\",\n    index_id=librarian_output[\"index_id\"],\n)\n```\n\n### Step 5 — Complete\n\n```python\nresult = brain.capture_complete(prep, librarian_output, embedding=embedding)\n```\n\nWrites to `~\u002F.memex\u002Farticle.db.captures` and the Index.\n\n### Step 6 — Report\n\n```\nCaptured to Brain:\n  index_id:   \u003Cresult[\"index_id\"]>\n  key:        \u003Cresult[\"key\"]>\n  domain:     \u003Cresult[\"domain\"]>\n  capture id: \u003Cresult[\"row_id\"]>\n```\n\n## Notes\n\n- Captures and ingests share the same Librarian flow; they only differ in target table (`captures` vs `articles`) and whether the payload includes source-URL\u002Fhash fields.\n- Captures don't go through Archivist — they're not \"sources\" with raw originals. The `body` text in `captures` IS the canonical content.\n","# memex:brain:capture\n\n## When to use\n\nThe user wants to record a thought, observation, or short snippet that isn't sourced from elsewhere. No URL, no provenance — just a note that should be findable later.\n\n## Inputs\n\n- `body` — the note text\n- `caller_agent_id` — registered agent id\n- `title` — optional short label\n\n## Recipe (Option-B Task-tool dispatch)\n\n### Step 1 — Prepare\n\n```python\nfrom scripts import brain\nprep = brain.capture_prepare(\n    body=body,\n    caller_agent_id=caller_agent_id,\n    title=title,  # may be None\n)\n```\n\n`prep[\"status\"]` is always `\"ready\"` (no source-hash dedup for captures — every capture is a fresh thought).\n\n### Step 2 — Dispatch the Librarian subagent\n\nUse the **Task tool**:\n\n- `subagent_type`: `general-purpose`\n- `description`: `Librarian: classify capture`\n- `prompt`: `prep[\"subagent_prompt\"]`\n- `model`: `claude-sonnet-4-6`\n\n> sonnet — bounded payload, deliberate downshift, never silent. (Enforced by `tests\u002Ftest_model_tier_dispatch.py`.)\n\nSame Librarian profile + classification policy as ingest; the subagent decides `domain=\"capture\"` (or whatever fits — Librarian's judgment).\n\n### Step 3 — Parse and validate\n\n```python\nfrom scripts.agents import librarian\nlibrarian_output = librarian.parse_response(subagent_response)\n```\n\nRetry once on `ValueError`. After two failures, report BLOCKED.\n\n### Step 4 — Encode embedding (optional)\n\n```python\nfrom scripts import embeddings\nembedding = embeddings.encode_or_skip(\n    librarian_output[\"searchable\"],\n    caller_agent_id=\"brain-capture\",\n    index_id=librarian_output[\"index_id\"],\n)\n```\n\n### Step 5 — Complete\n\n```python\nresult = brain.capture_complete(prep, librarian_output, embedding=embedding)\n```\n\nWrites to `~\u002F.memex\u002Farticle.db.captures` and the Index.\n\n### Step 6 — Report\n\n```\nCaptured to Brain:\n  index_id:   \u003Cresult[\"index_id\"]>\n  key:        \u003Cresult[\"key\"]>\n  domain:     \u003Cresult[\"domain\"]>\n  capture id: \u003Cresult[\"row_id\"]>\n```\n\n## Notes\n\n- Captures and ingests share the same Librarian flow; they only differ in target table (`captures` vs `articles`) and whether the payload includes source-URL\u002Fhash fields.\n- Captures don't go through Archivist — they're not \"sources\" with raw originals. The `body` text in `captures` IS the canonical content.\n",{"name":5,"description":7},"main","63a7b54c6f668f8d3211623b3199c39105162c68","internal\u002Fbrain\u002Fcapture","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex","https:\u002F\u002Fgithub.com\u002Fnitekeeper","Go with the flow!","2026-09-22 07:17:04",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add nitekeeper\u002Fmemex --skill \"memex:brain:capture\"",{"tool":36,"command":37},"bunx","bunx skills add nitekeeper\u002Fmemex --skill \"memex:brain:capture\"",{"tool":39,"command":40},"pnpm","pnpm dlx skills add nitekeeper\u002Fmemex --skill \"memex:brain:capture\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fbrain\u002Fcapture\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75YC1J4D3Y84T5DV40V337Y","run","Use to invoke any Memex v2.0 operation. Routes user-facing intents (ingest, ask, capture, lint, synthesize, dashboard) and agent-facing CRUD primitives to the right internal procedure.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Fskills\u002Frun\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75YBYMEKDRW88VSACQ8BXHH","memex:steward:reconcile-orphan","Authorized fix-up of a flagged orphan. Four actions — delete-index (remove documents row), repair (backfill row_id when target exists), reindex (re-run Librarian; deferred), note (acknowledge). Raises OrphanNotFoundError when index_id is unknown or, for repair, already linked.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fsteward\u002Freconcile-orphan\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75YBVWGDMMATQAPY3S2KYQX","memex:steward:dashboard","Launch a loopback-only, read-only HTTP dashboard over Memex — per-store summary, the federated index, knowledge communities, the code-navigation graph, and the agent registry, plus keyword search, a click-to-read content overlay, and an interactive 3D knowledge-graph view.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fsteward\u002Fdashboard\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75YBS1Y5QYT1JZWN7D90DT0","memex:steward:audit","Run a full integrity audit across the Memex Index and all registered stores. Detects orphans, broken relations, schema drift. Writes a structured audit report to ~\u002F.memex\u002Faudits\u002F. Read-only — never auto-fixes.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fsteward\u002Faudit\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M75YBQ7622SDEJDCHC02W8HQ","memex:steward:audit-store","Run an integrity audit scoped to a single registered store (reverse orphans + schema drift). Lighter than full audit.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Fsteward\u002Faudit-store\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M75YBKEHA8KVK5FM22F4MWJW","memex:index:write","Direct write to the federated Index — the lower-level primitive that memex:brain:ingest and memex:brain:capture build on. Use when a consumer (Atelier, custom plugin) needs to add a document to its own store and have it indexed by the Librarian, without going through the Brain layer. Routes through Librarian subagent + Memex Core.","https:\u002F\u002Fgithub.com\u002Fnitekeeper\u002Fmemex\u002Fblob\u002Fmain\u002Finternal\u002Findex\u002Fwrite\u002FSKILL.md",[],[]]