[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WWKBQK7V251B25FV41FKB0":3,"skill-same:01M6WWKBQK7V251B25FV41FKB0":128},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":73,"commitSha":74,"skillDirectory":75,"forksCount":14,"repositoryHtmlUrl":76,"repositoryHomepageUrl":77,"ownerHtmlUrl":78,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":79,"install":80,"resources":93},"01M6WWKBQK7V251B25FV41FKB0","index-management",null,"SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.","projectious-work\u002Fprocesskit","projectious-work","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263889726?v=4","01M6N97TJJ118WQ35CHRV8RD0E","projectious.work","01M6N97TPWJPF0BMKYQ4PBY5W8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"index management","index","management","list","errors","events","get","project","query","files","up","MCP","read","work","text","sqlite","server","search","status","mcp server","2026-11-10 10:12:30",false,"---\nname: index-management\ndescription: |\n  SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv2\n    id: SKILL-index-management\n    version: \"1.0.0\"\n    created: 2026-04-06T00:00:00Z\n    category: processkit\n    layer: 0\n    provides:\n      primitives: []\n      mcp_tools: [reindex, query_entities, get_entity, search_entities,\n            semantic_status, semantic_search_entities, hybrid_search_entities,\n            query_events, list_errors, stats]\n---\n\n# Index Management\n\n## Intro\n\n`index-management` is the **read-side** foundation. It walks the project's\n`context\u002F` directory, parses every entity file, and writes a SQLite\ndatabase that other tools query. Its peer at Layer 0 is `id-management`\n(the write side, which allocates new IDs). Both are foundational to\nevery entity-creating skill.\n\n> **MCP server.** This skill ships a self-contained MCP server at\n> `mcp\u002Fserver.py` (PEP 723 script — requires `uv` and Python ≥ 3.10 on\n> PATH). Agent harnesses may reach it directly from this skill's\n> `mcp\u002Fmcp-config.json` or through the processkit gateway. Gateway\n> deployments must surface only the processkit servers present in the\n> installed\u002Fmerged MCP configuration; this skill does not imply that\n> unrelated processkit tools are available.\n\n## Overview\n\n### What it provides\n\n- **`reindex()`** — rebuild the SQLite index from scratch\n- **`query_entities(kind?, state?, limit?)`** — list entities matching filters\n- **`get_entity(id)`** — fetch a single entity by ID\n- **`search_entities(text, limit?)`** — FTS5 search across titles, bodies, specs\n- **`semantic_status()`** — report semantic chunk\u002Fvector availability\n- **`semantic_search_entities(text, limit?)`** — sqlite-vec semantic search when available\n- **`hybrid_search_entities(text, limit?)`** — RRF over FTS5 + semantic results, with FTS-only fallback\n- **`query_events(event_type?, subject?, actor?, limit?)`** — query the event log\n- **`list_errors(limit?)`** — files that failed to parse during the last reindex\n- **`stats()`** — counts of entities\u002Fevents\u002Ferrors in the index\n\nList\u002Fsearch tools clamp caller-provided limits before querying the\ndatabase. Broad unfiltered event queries are capped more tightly than\nfiltered event queries, and long event summaries are returned as\npreviews. Fetch a specific entity by ID when full detail is needed.\n\n### When to use\n\nAgents call the MCP server whenever they need fast lookup. Other MCP\nservers (`workitem-management`, `decision-record`, etc.) refresh the\nindex after writing a new entity to keep reads current. In gateway\ndeployments, the gateway only routes to index-management if this server\nis present in the installed MCP configuration.\n\n### Where the database lives\n\n`\u003Cproject-root>\u002Fcontext\u002F.cache\u002Fprocesskit\u002Findex.sqlite`. Gitignored.\nRebuildable from source files at any time via `reindex()`.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Grepping the filesystem instead of calling `query_entities`.** The\n  index is faster, context-cheaper, and reflects parsed semantics\n  (state, kind, links) that grep can't see. Reach for `query_entities`\n  first; fall back to grep only if the query you need isn't supported.\n- **Trusting the index immediately after a hand-edit.** When you edit\n  an entity file directly (bypassing the MCP write tools), the index\n  is stale until the next `reindex()` call. Either go through the\n  write tools, or call `reindex()` yourself before querying.\n- **Forgetting to call `reindex` after writing a new entity.** Every\n  entity-creating MCP server should call `index_management.reindex`\n  (or the lighter `upsert_entity`) after a write. Not doing so means\n  the next query won't see the just-created entity.\n- **Treating index queries as transactional.** The index is eventually\n  consistent. A query immediately after a write may or may not return\n  the new row depending on whether reindex completed. If you need\n  strict consistency, reindex explicitly first.\n- **Trusting `list_errors()` as proof of correctness.** A clean errors\n  table means parsing succeeded, not that the entities are\n  semantically valid. Schema validation is a separate concern from\n  parse success.\n- **Using `search_entities` for exact-ID lookup.** `search_entities`\n  is ranked FTS5 search over parsed content, with a fallback substring\n  search for invalid FTS syntax. Use `get_entity(id)` for exact lookup.\n- **Assuming semantic search is always active.** The semantic chunk table\n  is always rebuilt, but vector KNN requires the optional `sqlite-vec`\n  extension to load. Check `semantic_status()`; use\n  `hybrid_search_entities()` when you want an FTS-backed fallback.\n- **Re-indexing inside a hot loop.** A full reindex walks the whole\n  `context\u002F` tree and is expensive. Batch your writes and reindex\n  once at the end, not after every entity.\n\n## Full reference\n\n### Database schema\n\nThree tables — see `src\u002Flib\u002Fprocesskit\u002Findex.py` for the DDL.\n\n```sql\nentities(id, kind, api_version, path, storage_location, created, updated, title, state, labels_json, spec_json, body)\nentities_fts(id, kind, state, title, body, spec_json)\nsemantic_chunks(rowid, chunk_id, entity_id, kind, state, path, ordinal, text)\nentity_vec(embedding)\nevents(id, timestamp, event_type, actor, subject, subject_kind, summary, details_json, correlation_id, path)\nerrors(path, message)\n```\n\n`spec_json` holds the full `spec` block as JSON for queries we did not\nanticipate. `storage_location` is `NULL` for hot-tree files and points at cold\narchive payloads for archived entities. `entities` and `events` overlap for\nLogEntry rows: a LogEntry appears in both, with the `events` table\ndenormalizing the event-specific fields for fast filtering.\n\n`entities_fts` is a rebuildable SQLite FTS5 virtual table. It mirrors\nthe searchable fields from `entities` and is cleared\u002Frebuilt during\n`reindex()`. If a stripped-down SQLite build lacks FTS5, the index still\nopens and `search_entities` falls back to the previous `LIKE %text%`\nbehaviour.\n\n`semantic_chunks` is a rebuildable chunk table. When the optional\n`sqlite-vec` package can be imported and loaded, `entity_vec` is created\nas a `vec0` virtual table containing deterministic local embeddings for\nthose chunks. The initial embedding strategy is provider-neutral\n`local-hashed-bag-of-words`; it gives a stable offline baseline and a\nstorage contract for later provider\u002Flocal embedding model upgrades.\n\n### Reindex strategy\n\n`reindex()` is **destructive and atomic** — it deletes all rows and\nre-inserts. For typical projects this is fast (sub-second). For very\nlarge projects, an incremental update mode lands later (Phase 4+).\n\n### Errors table\n\nFiles that fail to parse get a row in the `errors` table instead of\ncrashing the reindex. `list_errors(limit?)` returns a bounded window so\nthe agent can fix them in batches. The errors table is cleared at the\nstart of each reindex.\n\n### Tools that other servers call\n\n`workitem-management`, `decision-record`, `binding-management`, and\n`event-log` all call the shared index library after writing a new file.\nThis keeps the index in sync without a full reindex on every mutation.\nFrom an MCP-protocol perspective each configured server has its own\nprocess, or is reached through the gateway, and they communicate by\nsharing the same SQLite database file.\n\n### Configuration\n\nThe index database path is configurable via:\n\n- `processkit.toml` `[index] path = \"...\"` (relative to project root)\n- The `PROCESSKIT_INDEX_DB` environment variable\n- Default: `context\u002F.cache\u002Fprocesskit\u002Findex.sqlite` (gitignored cache)\n\n### Limitations at v0.3.0\n\n- **WAL mode enabled (v0.4.0+).** Multiple readers and a single writer\n  are safe; concurrent writes still serialize via WAL. Typical\n  AI-assisted sessions are single-writer anyway.\n- **FTS5 search.** Search uses SQLite FTS5 ranking when available and\n  falls back to `LIKE %text%` for invalid FTS syntax or unsupported\n  SQLite builds.\n- **Optional sqlite-vec.** Semantic search uses sqlite-vec only when the\n  extension is installed and loadable; otherwise semantic search returns\n  no vector results and hybrid search falls back to FTS5.\n- **No incremental indexing.** Every reindex is a full sweep.\n","# Index Management\n\n## Intro\n\n`index-management` is the **read-side** foundation. It walks the project's\n`context\u002F` directory, parses every entity file, and writes a SQLite\ndatabase that other tools query. Its peer at Layer 0 is `id-management`\n(the write side, which allocates new IDs). Both are foundational to\nevery entity-creating skill.\n\n> **MCP server.** This skill ships a self-contained MCP server at\n> `mcp\u002Fserver.py` (PEP 723 script — requires `uv` and Python ≥ 3.10 on\n> PATH). Agent harnesses may reach it directly from this skill's\n> `mcp\u002Fmcp-config.json` or through the processkit gateway. Gateway\n> deployments must surface only the processkit servers present in the\n> installed\u002Fmerged MCP configuration; this skill does not imply that\n> unrelated processkit tools are available.\n\n## Overview\n\n### What it provides\n\n- **`reindex()`** — rebuild the SQLite index from scratch\n- **`query_entities(kind?, state?, limit?)`** — list entities matching filters\n- **`get_entity(id)`** — fetch a single entity by ID\n- **`search_entities(text, limit?)`** — FTS5 search across titles, bodies, specs\n- **`semantic_status()`** — report semantic chunk\u002Fvector availability\n- **`semantic_search_entities(text, limit?)`** — sqlite-vec semantic search when available\n- **`hybrid_search_entities(text, limit?)`** — RRF over FTS5 + semantic results, with FTS-only fallback\n- **`query_events(event_type?, subject?, actor?, limit?)`** — query the event log\n- **`list_errors(limit?)`** — files that failed to parse during the last reindex\n- **`stats()`** — counts of entities\u002Fevents\u002Ferrors in the index\n\nList\u002Fsearch tools clamp caller-provided limits before querying the\ndatabase. Broad unfiltered event queries are capped more tightly than\nfiltered event queries, and long event summaries are returned as\npreviews. Fetch a specific entity by ID when full detail is needed.\n\n### When to use\n\nAgents call the MCP server whenever they need fast lookup. Other MCP\nservers (`workitem-management`, `decision-record`, etc.) refresh the\nindex after writing a new entity to keep reads current. In gateway\ndeployments, the gateway only routes to index-management if this server\nis present in the installed MCP configuration.\n\n### Where the database lives\n\n`\u003Cproject-root>\u002Fcontext\u002F.cache\u002Fprocesskit\u002Findex.sqlite`. Gitignored.\nRebuildable from source files at any time via `reindex()`.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Grepping the filesystem instead of calling `query_entities`.** The\n  index is faster, context-cheaper, and reflects parsed semantics\n  (state, kind, links) that grep can't see. Reach for `query_entities`\n  first; fall back to grep only if the query you need isn't supported.\n- **Trusting the index immediately after a hand-edit.** When you edit\n  an entity file directly (bypassing the MCP write tools), the index\n  is stale until the next `reindex()` call. Either go through the\n  write tools, or call `reindex()` yourself before querying.\n- **Forgetting to call `reindex` after writing a new entity.** Every\n  entity-creating MCP server should call `index_management.reindex`\n  (or the lighter `upsert_entity`) after a write. Not doing so means\n  the next query won't see the just-created entity.\n- **Treating index queries as transactional.** The index is eventually\n  consistent. A query immediately after a write may or may not return\n  the new row depending on whether reindex completed. If you need\n  strict consistency, reindex explicitly first.\n- **Trusting `list_errors()` as proof of correctness.** A clean errors\n  table means parsing succeeded, not that the entities are\n  semantically valid. Schema validation is a separate concern from\n  parse success.\n- **Using `search_entities` for exact-ID lookup.** `search_entities`\n  is ranked FTS5 search over parsed content, with a fallback substring\n  search for invalid FTS syntax. Use `get_entity(id)` for exact lookup.\n- **Assuming semantic search is always active.** The semantic chunk table\n  is always rebuilt, but vector KNN requires the optional `sqlite-vec`\n  extension to load. Check `semantic_status()`; use\n  `hybrid_search_entities()` when you want an FTS-backed fallback.\n- **Re-indexing inside a hot loop.** A full reindex walks the whole\n  `context\u002F` tree and is expensive. Batch your writes and reindex\n  once at the end, not after every entity.\n\n## Full reference\n\n### Database schema\n\nThree tables — see `src\u002Flib\u002Fprocesskit\u002Findex.py` for the DDL.\n\n```sql\nentities(id, kind, api_version, path, storage_location, created, updated, title, state, labels_json, spec_json, body)\nentities_fts(id, kind, state, title, body, spec_json)\nsemantic_chunks(rowid, chunk_id, entity_id, kind, state, path, ordinal, text)\nentity_vec(embedding)\nevents(id, timestamp, event_type, actor, subject, subject_kind, summary, details_json, correlation_id, path)\nerrors(path, message)\n```\n\n`spec_json` holds the full `spec` block as JSON for queries we did not\nanticipate. `storage_location` is `NULL` for hot-tree files and points at cold\narchive payloads for archived entities. `entities` and `events` overlap for\nLogEntry rows: a LogEntry appears in both, with the `events` table\ndenormalizing the event-specific fields for fast filtering.\n\n`entities_fts` is a rebuildable SQLite FTS5 virtual table. It mirrors\nthe searchable fields from `entities` and is cleared\u002Frebuilt during\n`reindex()`. If a stripped-down SQLite build lacks FTS5, the index still\nopens and `search_entities` falls back to the previous `LIKE %text%`\nbehaviour.\n\n`semantic_chunks` is a rebuildable chunk table. When the optional\n`sqlite-vec` package can be imported and loaded, `entity_vec` is created\nas a `vec0` virtual table containing deterministic local embeddings for\nthose chunks. The initial embedding strategy is provider-neutral\n`local-hashed-bag-of-words`; it gives a stable offline baseline and a\nstorage contract for later provider\u002Flocal embedding model upgrades.\n\n### Reindex strategy\n\n`reindex()` is **destructive and atomic** — it deletes all rows and\nre-inserts. For typical projects this is fast (sub-second). For very\nlarge projects, an incremental update mode lands later (Phase 4+).\n\n### Errors table\n\nFiles that fail to parse get a row in the `errors` table instead of\ncrashing the reindex. `list_errors(limit?)` returns a bounded window so\nthe agent can fix them in batches. The errors table is cleared at the\nstart of each reindex.\n\n### Tools that other servers call\n\n`workitem-management`, `decision-record`, `binding-management`, and\n`event-log` all call the shared index library after writing a new file.\nThis keeps the index in sync without a full reindex on every mutation.\nFrom an MCP-protocol perspective each configured server has its own\nprocess, or is reached through the gateway, and they communicate by\nsharing the same SQLite database file.\n\n### Configuration\n\nThe index database path is configurable via:\n\n- `processkit.toml` `[index] path = \"...\"` (relative to project root)\n- The `PROCESSKIT_INDEX_DB` environment variable\n- Default: `context\u002F.cache\u002Fprocesskit\u002Findex.sqlite` (gitignored cache)\n\n### Limitations at v0.3.0\n\n- **WAL mode enabled (v0.4.0+).** Multiple readers and a single writer\n  are safe; concurrent writes still serialize via WAL. Typical\n  AI-assisted sessions are single-writer anyway.\n- **FTS5 search.** Search uses SQLite FTS5 ranking when available and\n  falls back to `LIKE %text%` for invalid FTS syntax or unsupported\n  SQLite builds.\n- **Optional sqlite-vec.** Semantic search uses sqlite-vec only when the\n  extension is installed and loadable; otherwise semantic search returns\n  no vector results and hybrid search falls back to FTS5.\n- **No incremental indexing.** Every reindex is a full sweep.\n",{"name":5,"metadata":52,"description":72},{"processkit":53},{"id":54,"layer":14,"created":55,"version":56,"category":57,"provides":58,"apiVersion":71},"SKILL-index-management",1775433600000,"1.0.0","processkit",{"mcp_tools":59,"primitives":70},[60,61,62,63,64,65,66,67,68,69],"reindex","query_entities","get_entity","search_entities","semantic_status","semantic_search_entities","hybrid_search_entities","query_events","list_errors","stats",[],"processkit.projectious.work\u002Fv2","SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-11 23:24:18",{"source":8,"skillName":5,"commands":81,"prompt":91,"zipAvailable":92},[82,85,88],{"tool":83,"command":84},"npx","npx skills add projectious-work\u002Fprocesskit --skill index-management",{"tool":86,"command":87},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill index-management",{"tool":89,"command":90},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill index-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002FSKILL.md",true,[94,100,106,110,116,120,124],{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"config\u002Fsettings.toml","OTHER","其他",1289,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fconfig\u002Fsettings.toml",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"mcp\u002Fmcp-config.json","REFERENCE","参考文档",235,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fmcp\u002Fmcp-config.json",{"path":107,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":108,"sourceHtmlUrl":109},"mcp\u002FSERVER.md",3411,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fmcp\u002FSERVER.md",{"path":111,"resourceType":112,"resourceTypeDesc":113,"sizeBytes":114,"sourceHtmlUrl":115},"mcp\u002Fserver.py","SCRIPT","脚本",20582,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fmcp\u002Fserver.py",{"path":117,"resourceType":112,"resourceTypeDesc":113,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Ftest_db_result_limits.py",3236,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fscripts\u002Ftest_db_result_limits.py",{"path":121,"resourceType":112,"resourceTypeDesc":113,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Ftest_get_entity_by_path_and_list_entities.py",9657,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fscripts\u002Ftest_get_entity_by_path_and_list_entities.py",{"path":125,"resourceType":112,"resourceTypeDesc":113,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Ftest_index_management_v1_penalty.py",12753,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Fskills\u002Fprocesskit\u002Findex-management\u002Fscripts\u002Ftest_index_management_v1_penalty.py",[129,136,143,149,169,188],{"skillNo":130,"name":131,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":135},"01M7665G2ED3624R3X93304265","standard-ui-design","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-ui-design\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":135},"01M76651QTC6W0HJ4AFW2MMR3V","standard-agent-use","Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-use\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":135},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":47},"01M6X5MTC89B4ZGXW3JVSQCPF8","skill-management","Manage Skill package manifests as v1 ontology entities.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fskill-management\u002FSKILL.md",[155],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[29,157,158,159,160,161,40,162,33,163,164,165,151,30,166,167,168],"skill management","ontology","v1","create","as","transition","manage","update","alpha","package","skill package","manifests",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":47},"01M6X5MCV74NHW5MEDNHZRF2C8","schema-management","Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fschema-management\u002FSKILL.md",[175],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[177,178,29,179,180,181,182,183,184,38,185,186,40,33,163,165,187],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","validation","deterministic","mode",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":47},"01M6X5M5G6YJ96AMZGSCZJ1D13","proposition-management","Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fproposition-management\u002FSKILL.md",[],[195,29,196,197,160,198,199,200,40,33,201,202,164,203,165,28,204,35,205,206],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","updates","facts","log"]