[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AB2CB5VKTSQCDAMCY7WTQ2":3,"skill-same:01M7AB2CB5VKTSQCDAMCY7WTQ2":54},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AB2CB5VKTSQCDAMCY7WTQ2","recall",null,"Search the shared eidetic memory store and get back ranked, provenanced records. Drives `eidetic recall` with four search modes — exact (verbatim substring), approximate (vector\u002Fsemantic), keyword (BM25 lexical), and hybrid (a weighted blend of vector+keyword, the default) — each hit carrying its text, full metadata, a relevance `score`, and a freshness `signal`. Recall passively reinforces matched records (bumps last_recall + recall_count). Shadowed and archived records are excluded by default; use --include-shadowed \u002F --include-archived to retrieve them. The store lives at ~\u002F.eidetic\u002Fmemory (a home-dir path outside any git worktree); the wrapper defaults queries to this agent's PERSONAL, PRIVATE scope (`--scope culture-nodes --visibility private`, suffix read from culture.yaml) — matching where \u002Fremember writes — so a no-flag recall returns this agent's own private records plus the shared public pool, and Claude and the colleague backend recall each other's memories because both resolve the same suffix via this skill. Use when the user says \"recall\", \"what do we know about X\", \"search memory\", \"have we seen X before\", \"look it up in memory\", \"eidetic recall\", or before answering from scratch when prior context may already be stored. Pairs with the sibling \u002Fremember skill.","agentculture\u002Fculture-nodes","agentculture","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F277824871?v=4","01M7AAZDPCFA8RDCA27DQKKWCJ","AgentCulture","01M7AAZDQ1B6FYE24021YCDAPR",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecall\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: recall\ntype: command\ndescription: >\n  Search the shared eidetic memory store and get back ranked, provenanced\n  records. Drives `eidetic recall` with four search modes — exact (verbatim\n  substring), approximate (vector\u002Fsemantic), keyword (BM25 lexical), and hybrid\n  (a weighted blend of vector+keyword, the default) — each hit carrying its\n  text, full metadata, a relevance `score`, and a freshness `signal`. Recall\n  passively reinforces matched records (bumps last_recall + recall_count).\n  Shadowed and archived records are excluded by default; use\n  --include-shadowed \u002F --include-archived to retrieve them. The store lives at\n  ~\u002F.eidetic\u002Fmemory (a home-dir path outside any git worktree); the wrapper\n  defaults queries to this agent's PERSONAL, PRIVATE scope (`--scope culture-nodes\n  --visibility private`, suffix read from culture.yaml) — matching where\n  \u002Fremember writes — so a no-flag recall returns this agent's own private records\n  plus the shared public pool, and Claude and the colleague backend recall each\n  other's memories because both resolve the same suffix via this skill. Use\n  when the user says \"recall\", \"what do we know about X\", \"search memory\",\n  \"have we seen X before\", \"look it up in memory\", \"eidetic recall\", or before\n  answering from scratch when prior context may already be stored. Pairs with\n  the sibling \u002Fremember skill.\n---\n\n# recall — search the shared eidetic memory\n\n`recall` drives **`eidetic recall`**: given a query, it returns the top-k stored\nrecords ranked by relevance, each with its `text`, full `metadata` (provenance),\na numeric `score`, and a freshness `signal`. It is the read half of the memory\nsurface; the write half is the sibling **\u002Fremember** skill.\n\nThe point of a *shared* store is that memory is a **team faculty**, not a\nper-agent silo: a record Claude wrote is recallable by the colleague backend\n(and vice versa), because both resolve the same `~\u002F.eidetic\u002Fmemory` path.\n\n## How to run\n\n```bash\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"\u003Cquery>\" [flags...]\n```\n\nThe wrapper resolves the CLI portably (installed `eidetic` on `PATH`, else\n`uv run eidetic` from the checkout) and forwards every flag verbatim, so it is\nexactly `eidetic recall …`. Run it from anywhere; the store is the same.\n\n## Search modes (`--mode`, default `hybrid`)\n\n| Mode | What it matches | Needs embed server? |\n|------|-----------------|---------------------|\n| `exact` | case-insensitive verbatim substring (`--case-sensitive` to tighten) | no — offline-safe |\n| `approximate` | vector cosine \u002F semantic similarity | yes (falls back offline) |\n| `keyword` | BM25 lexical; only records sharing a query term | no — offline-safe |\n| `hybrid` | `alpha*approximate + (1-alpha)*keyword` (`--alpha`, default 0.5) | uses it when up |\n\n`hybrid` is the default because the two signals cover each other's blind spots:\nvector catches paraphrases, keyword catches exact ids\u002Fquotes. When the embed\nserver is unreachable, `hybrid` collapses to keyword-only (it never fuses\nmeaningless offline-fallback cosine).\n\n## Output fields\n\nEach hit in `--json` output includes:\n\n| Field | Notes |\n|-------|-------|\n| `id` | stable record identity |\n| `text` | the stored chunk |\n| `type` | record type |\n| `metadata` | full provenance, round-tripped verbatim from ingest |\n| `score` | relevance score from the chosen search mode (freshness-blended) |\n| `signal` | freshness strength in [0, 1]; computed at recall time from age, recall frequency, and staleness |\n| `created` | ISO-8601 ingest date (may be DATE_UNKNOWN for legacy records) |\n| `last_recall` | ISO-8601 timestamp of the most recent recall hit (null if never recalled) |\n| `recall_count` | number of times this record has been recalled (passive reinforcement counter) |\n| `lifecycle` | `active`, `shadowed`, or `archived` |\n| `links` | list of related-memory ids |\n\n## Freshness signal\n\nEvery `recall` hit carries a `signal` field (float in `[0, 1]`). The signal\nblends **multiplicatively** into the lexical\u002Fvector score so recently-created\nand frequently-recalled records surface ahead of stale ones. The formula:\n\n```\naccess_bonus = min(0.5, recall_count * 0.05)\nage_factor   = 1 \u002F (1 + days_since_creation * 0.01)\nstaleness    = days_since_last_recall * 0.01\nsignal       = clamp((0.5 - staleness + access_bonus) * age_factor, 0, 1)\nblended_score = score * (1 + 0.25 * (signal - 0.5))\n```\n\nRecords with no temporal data (legacy, undated) are an exact no-op — the blend\nis skipped for them so pre-existing fixture scores are unchanged.\n\nEach `recall` call is also **passive reinforcement**: it bumps `last_recall` and\n`recall_count` on every matched record, so frequently-recalled memories organically\ngain signal strength over time.\n\n## Lifecycle flags\n\nBy default, `recall` returns only `active` records. Use these flags to retrieve\nnon-active records:\n\n- `--include-shadowed` — include records whose `lifecycle == \"shadowed\"` (records\n  superseded within their scope by a newer record). Shadowed records are preserved\n  and still searchable; they are just hidden from the default result set.\n- `--include-archived` — include records whose `lifecycle == \"archived\"` (records\n  older than ~1 year or below the signal threshold). Archived records are fully\n  preserved; the flag makes them retrievable again.\n\nBoth flags can be combined. Neither affects ranking — shadowed\u002Farchived records\ncompete on score\u002Fsignal just like active ones when included.\n\n## Common flags (forwarded to `eidetic recall`)\n\n- `--mode exact|approximate|keyword|hybrid` — default `hybrid`.\n- `--top-k N` — max results (default 5).\n- `--alpha F` — hybrid blend weight in `[0,1]` (default 0.5).\n- `--case-sensitive` — for `--mode exact`.\n- `--filter KEY=VALUE` — metadata facet filter (repeatable): e.g. `--filter source=docs`.\n- `--scope NAME` \u002F `--visibility public|private` — scope isolation (no private\n  leak). **The wrapper defaults this to the agent's PERSONAL, PRIVATE scope**\n  (`--scope culture-nodes --visibility private`, suffix read from `culture.yaml`),\n  matching where `\u002Fremember` writes — so a no-flag recall returns this agent's\n  own private records **plus** the shared public pool, while those private records\n  stay invisible to a `default`\u002Fother-scope recall. Pass `--scope`\u002F`--visibility`\n  to query elsewhere; a wheel install with no `culture.yaml` falls back to the\n  CLI default `default`\u002F`public`.\n- `--backend files|mongo|neo4j` — default `files` (the shared home-dir store).\n- `--include-shadowed` — include shadowed records in results (excluded by default).\n- `--include-archived` — include archived records in results (excluded by default).\n- `--json` — structured list to stdout (use this when an agent parses the result).\n\n## Examples\n\n```bash\n# Default hybrid recall, JSON for an agent to parse:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"jetson nano power draw\" --json\n\n# Find the exact message that mentions a phrase:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"Orin Nano\" --mode exact\n\n# Keyword search, offline-safe, narrowed to a source:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"thermal throttle\" --mode keyword \\\n    --filter source=discord --top-k 10\n\n# Retrieve a record that was recently shadowed (its superseding record is now active):\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"old topic\" --include-shadowed --json\n\n# Retrieve all records including archived (to audit stale memories):\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"power\" --include-archived --include-shadowed --json\n```\n\n## Notes\n\n- **Provenance is mandatory** on every hit — recall is for *cited* answers.\n- The embed endpoint defaults to the local model-gear embed gear\n  (`http:\u002F\u002Flocalhost:8002\u002Fv1`, model `Qwen\u002FQwen3-Embedding-0.6B`); override with\n  `EIDETIC_EMBED_URL` \u002F `EIDETIC_EMBED_MODEL`. `exact`\u002F`keyword` ignore it.\n- **Use the wrapper, not a bare `eidetic`.** The console script may not be on\n  `PATH` (in a dev checkout it isn't) — the wrapper resolves it for you (`PATH`\n  first, else `uv run eidetic`). For the docs, run `eidetic explain recall` if\n  installed, otherwise `uv run --project \u003Ceidetic-cli checkout> eidetic explain\n  recall`. (`explain` is an **`eidetic`** verb — a sibling tool like `devex`\n  won't know it.)\n- **Reading scores:** `exact`, `keyword`, and `hybrid` drop non-matching records\n  (hybrid drops any record with a `0.0` blended score), so their hits are real\n  matches. `approximate` keeps every candidate ranked by raw cosine, so it can\n  return low\u002Fnear-zero scores when the store is small — lower `--top-k` to trim.\n  A `--min-score` threshold is a tracked follow-up.\n- **Sharing scope = one OS user.** The default store is `~\u002F.eidetic\u002Fmemory`, so\n  every agent\u002Fprocess running as the *same* OS user shares it (that is the point —\n  Claude + colleague). It is not isolated between OS users by anything but file\n  permissions; keep genuinely private data in a `--visibility private` scope and\n  treat the host as the trust boundary.\n\n## Provenance\n\nFirst-party to **eidetic-cli** — eidetic owns its memory surface. Cite, don't\nimport: downstream repos copy this skill, they don't symlink it. See\n[`docs\u002Fskill-sources.md`](..\u002F..\u002F..\u002Fdocs\u002Fskill-sources.md).\n","# recall — search the shared eidetic memory\n\n`recall` drives **`eidetic recall`**: given a query, it returns the top-k stored\nrecords ranked by relevance, each with its `text`, full `metadata` (provenance),\na numeric `score`, and a freshness `signal`. It is the read half of the memory\nsurface; the write half is the sibling **\u002Fremember** skill.\n\nThe point of a *shared* store is that memory is a **team faculty**, not a\nper-agent silo: a record Claude wrote is recallable by the colleague backend\n(and vice versa), because both resolve the same `~\u002F.eidetic\u002Fmemory` path.\n\n## How to run\n\n```bash\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"\u003Cquery>\" [flags...]\n```\n\nThe wrapper resolves the CLI portably (installed `eidetic` on `PATH`, else\n`uv run eidetic` from the checkout) and forwards every flag verbatim, so it is\nexactly `eidetic recall …`. Run it from anywhere; the store is the same.\n\n## Search modes (`--mode`, default `hybrid`)\n\n| Mode | What it matches | Needs embed server? |\n|------|-----------------|---------------------|\n| `exact` | case-insensitive verbatim substring (`--case-sensitive` to tighten) | no — offline-safe |\n| `approximate` | vector cosine \u002F semantic similarity | yes (falls back offline) |\n| `keyword` | BM25 lexical; only records sharing a query term | no — offline-safe |\n| `hybrid` | `alpha*approximate + (1-alpha)*keyword` (`--alpha`, default 0.5) | uses it when up |\n\n`hybrid` is the default because the two signals cover each other's blind spots:\nvector catches paraphrases, keyword catches exact ids\u002Fquotes. When the embed\nserver is unreachable, `hybrid` collapses to keyword-only (it never fuses\nmeaningless offline-fallback cosine).\n\n## Output fields\n\nEach hit in `--json` output includes:\n\n| Field | Notes |\n|-------|-------|\n| `id` | stable record identity |\n| `text` | the stored chunk |\n| `type` | record type |\n| `metadata` | full provenance, round-tripped verbatim from ingest |\n| `score` | relevance score from the chosen search mode (freshness-blended) |\n| `signal` | freshness strength in [0, 1]; computed at recall time from age, recall frequency, and staleness |\n| `created` | ISO-8601 ingest date (may be DATE_UNKNOWN for legacy records) |\n| `last_recall` | ISO-8601 timestamp of the most recent recall hit (null if never recalled) |\n| `recall_count` | number of times this record has been recalled (passive reinforcement counter) |\n| `lifecycle` | `active`, `shadowed`, or `archived` |\n| `links` | list of related-memory ids |\n\n## Freshness signal\n\nEvery `recall` hit carries a `signal` field (float in `[0, 1]`). The signal\nblends **multiplicatively** into the lexical\u002Fvector score so recently-created\nand frequently-recalled records surface ahead of stale ones. The formula:\n\n```\naccess_bonus = min(0.5, recall_count * 0.05)\nage_factor   = 1 \u002F (1 + days_since_creation * 0.01)\nstaleness    = days_since_last_recall * 0.01\nsignal       = clamp((0.5 - staleness + access_bonus) * age_factor, 0, 1)\nblended_score = score * (1 + 0.25 * (signal - 0.5))\n```\n\nRecords with no temporal data (legacy, undated) are an exact no-op — the blend\nis skipped for them so pre-existing fixture scores are unchanged.\n\nEach `recall` call is also **passive reinforcement**: it bumps `last_recall` and\n`recall_count` on every matched record, so frequently-recalled memories organically\ngain signal strength over time.\n\n## Lifecycle flags\n\nBy default, `recall` returns only `active` records. Use these flags to retrieve\nnon-active records:\n\n- `--include-shadowed` — include records whose `lifecycle == \"shadowed\"` (records\n  superseded within their scope by a newer record). Shadowed records are preserved\n  and still searchable; they are just hidden from the default result set.\n- `--include-archived` — include records whose `lifecycle == \"archived\"` (records\n  older than ~1 year or below the signal threshold). Archived records are fully\n  preserved; the flag makes them retrievable again.\n\nBoth flags can be combined. Neither affects ranking — shadowed\u002Farchived records\ncompete on score\u002Fsignal just like active ones when included.\n\n## Common flags (forwarded to `eidetic recall`)\n\n- `--mode exact|approximate|keyword|hybrid` — default `hybrid`.\n- `--top-k N` — max results (default 5).\n- `--alpha F` — hybrid blend weight in `[0,1]` (default 0.5).\n- `--case-sensitive` — for `--mode exact`.\n- `--filter KEY=VALUE` — metadata facet filter (repeatable): e.g. `--filter source=docs`.\n- `--scope NAME` \u002F `--visibility public|private` — scope isolation (no private\n  leak). **The wrapper defaults this to the agent's PERSONAL, PRIVATE scope**\n  (`--scope culture-nodes --visibility private`, suffix read from `culture.yaml`),\n  matching where `\u002Fremember` writes — so a no-flag recall returns this agent's\n  own private records **plus** the shared public pool, while those private records\n  stay invisible to a `default`\u002Fother-scope recall. Pass `--scope`\u002F`--visibility`\n  to query elsewhere; a wheel install with no `culture.yaml` falls back to the\n  CLI default `default`\u002F`public`.\n- `--backend files|mongo|neo4j` — default `files` (the shared home-dir store).\n- `--include-shadowed` — include shadowed records in results (excluded by default).\n- `--include-archived` — include archived records in results (excluded by default).\n- `--json` — structured list to stdout (use this when an agent parses the result).\n\n## Examples\n\n```bash\n# Default hybrid recall, JSON for an agent to parse:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"jetson nano power draw\" --json\n\n# Find the exact message that mentions a phrase:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"Orin Nano\" --mode exact\n\n# Keyword search, offline-safe, narrowed to a source:\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"thermal throttle\" --mode keyword \\\n    --filter source=discord --top-k 10\n\n# Retrieve a record that was recently shadowed (its superseding record is now active):\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"old topic\" --include-shadowed --json\n\n# Retrieve all records including archived (to audit stale memories):\nbash .claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh \"power\" --include-archived --include-shadowed --json\n```\n\n## Notes\n\n- **Provenance is mandatory** on every hit — recall is for *cited* answers.\n- The embed endpoint defaults to the local model-gear embed gear\n  (`http:\u002F\u002Flocalhost:8002\u002Fv1`, model `Qwen\u002FQwen3-Embedding-0.6B`); override with\n  `EIDETIC_EMBED_URL` \u002F `EIDETIC_EMBED_MODEL`. `exact`\u002F`keyword` ignore it.\n- **Use the wrapper, not a bare `eidetic`.** The console script may not be on\n  `PATH` (in a dev checkout it isn't) — the wrapper resolves it for you (`PATH`\n  first, else `uv run eidetic`). For the docs, run `eidetic explain recall` if\n  installed, otherwise `uv run --project \u003Ceidetic-cli checkout> eidetic explain\n  recall`. (`explain` is an **`eidetic`** verb — a sibling tool like `devex`\n  won't know it.)\n- **Reading scores:** `exact`, `keyword`, and `hybrid` drop non-matching records\n  (hybrid drops any record with a `0.0` blended score), so their hits are real\n  matches. `approximate` keeps every candidate ranked by raw cosine, so it can\n  return low\u002Fnear-zero scores when the store is small — lower `--top-k` to trim.\n  A `--min-score` threshold is a tracked follow-up.\n- **Sharing scope = one OS user.** The default store is `~\u002F.eidetic\u002Fmemory`, so\n  every agent\u002Fprocess running as the *same* OS user shares it (that is the point —\n  Claude + colleague). It is not isolated between OS users by anything but file\n  permissions; keep genuinely private data in a `--visibility private` scope and\n  treat the host as the trust boundary.\n\n## Provenance\n\nFirst-party to **eidetic-cli** — eidetic owns its memory surface. Cite, don't\nimport: downstream repos copy this skill, they don't symlink it. See\n[`docs\u002Fskill-sources.md`](..\u002F..\u002F..\u002Fdocs\u002Fskill-sources.md).\n",{"name":5,"type":24,"description":7},"command","main","a2056e6191a4e106faf886773efed2f44ff120b2",".claude\u002Fskills\u002Frecall",0,"https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes","https:\u002F\u002Fgithub.com\u002Fagentculture","https:\u002F\u002Fagentculture.org","Agent first OSS software","2026-09-29 08:50:58",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add agentculture\u002Fculture-nodes --skill recall",{"tool":40,"command":41},"bunx","bunx skills add agentculture\u002Fculture-nodes --skill recall",{"tool":43,"command":44},"pnpm","pnpm dlx skills add agentculture\u002Fculture-nodes --skill recall","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecall\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"scripts\u002Frecall.sh","SCRIPT","脚本",7592,"https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecall\u002Fscripts\u002Frecall.sh",[55,62,67,72,79,86],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AB6FGWR0P3SPYFX2W801D5","sample","Fixture skill proving the .qwen\u002Fskills leg carries at least one skill.","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002Fadapters\u002Fqwen\u002Ftests\u002Ffixtures\u002Fconfig-repo-no-culture-yaml\u002F.qwen\u002Fskills\u002Fsample\u002FSKILL.md",[],[],{"skillNo":63,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7AB6E9PFCDZE193CGPM0K35","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002Fadapters\u002Fqwen\u002Ftests\u002Ffixtures\u002Fconfig-repo-no-agents-md\u002F.qwen\u002Fskills\u002Fsample\u002FSKILL.md",[],[],{"skillNo":68,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7AB6CJ3G1ZZJD63NEZZK1JH","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002Fadapters\u002Fqwen\u002Ftests\u002Ffixtures\u002Fconfig-repo-complete\u002F.qwen\u002Fskills\u002Fsample\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AB64WWKV9H2J7JDV5KXGPA","think","Think a vague feature idea into a buildable spec by working backwards (the idea→spec leg; drives the `devague` CLI). Start from the announcement (\"pretend it shipped\"), capture and classify claims, interrogate them with honesty conditions and hard questions, park open vagueness as a first-class object, and export a spec only once the frame *converges*. Use when the user says \"think this through\", \"spec this\", \"work backwards\", \"turn this idea into a spec\", \"announcement frame\", or \"devague\", or when a feature request is too vague to build yet. Explore scope first when the idea touches an existing codebase — the sibling `scope` skill is the optional opening leg ahead of `think`. Once a spec exports, hand off to the sibling `spec-to-plan` skill to turn it into a plan. Authored and maintained in agentculture\u002Fdevague (origin = devague); guildmaster pulls this skill from here and broadcasts it to the AgentCulture mesh — it is NOT vendored from guildmaster like the other skills here.","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fthink\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AB5X0FTZ081AFH3BTGQKVA","summarize-delivery","Close the loop after an `assign-to-workforce` run by turning what actually happened into an accountability artifact — planned versus actual delivery, mid-work decisions, plan drift, evidence-backed delivery claims, and remaining work. The plan the user confirmed is the contract; this skill records where execution obeyed it, where it changed, and what is genuinely safe to claim as delivered. Runs on complete, partial, AND failed runs — failure is reported faithfully, never smoothed over. Use when the user says \"summarize delivery\", \"delivery summary\", \"wrap up\", \"close the loop\", \"what did we actually ship\", or \"plan versus actual\", or after `assign-to-workforce` merges (or fails to merge) a plan's waves. Authored and maintained in agentculture\u002Fdevague (origin = devague); guildmaster pulls this skill from here and broadcasts it to the AgentCulture mesh — it is NOT vendored from guildmaster like the inbound skills here.","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fsummarize-delivery\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AB5NA0QY9NN076N24NJPJQ","spec-to-plan","Turn a converged devague spec into a buildable plan by working forwards (the spec→plan leg; drives the `devague plan` CLI group). Seed a plan from a converged frame, add tasks that collectively cover every coverage target (the frame's confirmed claims + honesty conditions), give each task acceptance criteria and an honest dependency order, park genuine unknowns as first-class risks, and export a plan only once it *converges*. Use when the user says \"spec to plan\", \"stp\", \"turn this spec into a plan\", \"plan this spec\", \"make a build plan\", or after the `think` skill exports a spec. Authored and maintained in agentculture\u002Fdevague (origin = devague); guildmaster pulls this skill from here and broadcasts it to the AgentCulture mesh — it is NOT vendored from guildmaster like the other skills here.","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fspec-to-plan\u002FSKILL.md",[],[]]