[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AB17963Z2YBFWVYYAXSSNN":3,"skill-same:01M7AB17963Z2YBFWVYYAXSSNN":49},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7AB17963Z2YBFWVYYAXSSNN","deviate",null,"Stop an in-flight assign-to-workforce run the moment execution must diverge from the confirmed plan, get explicit human approval for the divergence, and record it as a first-class, append-only deviation record via `devague deviate` before resuming — never fold a deviation silently into drift after the fact. Use when the user says \"deviate from the plan\", \"we need to change the plan mid-run\", \"record a deviation\", \"this isn't matching the plan anymore\", or when a task agent discovers the confirmed plan no longer matches reality partway through a workforce run. 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.","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\u002Fdeviate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deviate\ndescription: >\n  Stop an in-flight assign-to-workforce run the moment execution must diverge\n  from the confirmed plan, get explicit human approval for the divergence, and\n  record it as a first-class, append-only deviation record via `devague\n  deviate` before resuming — never fold a deviation silently into drift after\n  the fact. Use when the user says \"deviate from the plan\", \"we need to change\n  the plan mid-run\", \"record a deviation\", \"this isn't matching the plan\n  anymore\", or when a task agent discovers the confirmed plan no longer\n  matches reality partway through a workforce run. Authored and maintained in\n  agentculture\u002Fdevague (origin = devague); guildmaster pulls this skill from\n  here and broadcasts it to the AgentCulture mesh — it is NOT vendored from\n  guildmaster like the inbound skills here.\ntype: command\n---\n\n# deviate — record an approved mid-run departure from the confirmed plan\n\nThe skill is named **`deviate`**; it is the **execution-time leg** of the\ndevague method — the *sixth* leg, sitting between the two execution skills:\n\n```text\nscope -> think -> spec-to-plan -> assign-to-workforce -> deviate -> summarize-delivery\n```\n\nWhere `\u002Fassign-to-workforce` fans out a converged plan's waves and\n`\u002Fsummarize-delivery` closes the loop afterward, `\u002Fdeviate` runs **during**\nthe fan-out, at the exact moment reality stops matching the plan the human\napproved at gate 2 (the implementation split plan). It is not a new standing\ngate — it is the human owner of gate 2 **amending** the approved split\nmid-flight, scoped to the one deviation in front of them.\n\nThe plan the user confirmed is a contract. Task agents hit constraints,\ndiscover a dependency was wrong, or find the acceptance criteria no longer\nmake sense once code is in front of them. Until this skill existed, that\nreality either silently reshaped what got built (undocumented drift) or the\nrun stalled with no recorded path forward. `\u002Fdeviate` is that path: the\ndeparture is named, approved, and recorded **before** anyone keeps building\nagainst it.\n\n## The method\n\n1. **STOP the run.** The moment a task agent (or the main agent) discovers\n   the confirmed plan no longer matches what needs to happen, halt — do not\n   keep implementing against the stale contract and do not let the fan-out\n   continue past this task.\n2. **Present what, why, and what it affects.** Lay out, for the human:\n   - **what** is diverging — the specific change from the confirmed task(s);\n   - **why** — the constraint or discovery that forced it;\n   - **what it affects** — the plan item ref(s) involved (`--task`), any\n     other task ids or coverage targets it touches (`--affects`), and which\n     acceptance criteria are no longer accurate.\n3. **Get explicit human approval.** This is the one non-negotiable step. A\n   deviation is not real until a human says yes to *this specific* departure\n   — not a standing blanket permission, not an inference from silence.\n4. **Record it via `devague deviate`.** Once approved, record the deviation\n   as a first-class ledger entry (never edit the plan itself — the plan\n   stays the untouched historical contract; see `devague\u002Fdelivery.py`). An\n   `--origin llm` record lands `proposed` and still needs the user's\n   `--confirm` — recording is not the same as approval landing as final.\n5. **Adjust the affected task briefs.** Update the working instructions the\n   task agent(s) are building against so they reflect the approved\n   departure, not the stale plan text.\n6. **Resume.** Only after the record exists (and, for an `llm`-origin record,\n   only after it is confirmed) does the fan-out continue.\n\nDeviations are never silently folded into drift after the fact — by the time\n`\u002Fsummarize-delivery` runs, every departure from the plan already has a\n`dN` record with a reason, an approval, and an optional classification. The\ndelivery summary quotes these records; it does not reconstruct drift from\nmemory.\n\n## The shipped CLI surface\n\nThis skill invokes the CLI directly and stays self-contained (if `devague`\nisn't on your PATH: `uv tool install devague`). Deviation state persists\nunder `.devague\u002Fdeliveries\u002F\u003Cplan-slug>.json` — a peer of the plan store, keyed\nby the plan slug, and never touches the plan JSON itself.\n\n| Move | What it does |\n|------|---------------|\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\"` | Record a deviation against plan item `\u003CtN>`. User-origin (the default) auto-approves. |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --affects \u003Cref> [\u003Cref> ...]` | Same, also naming every other plan item ref or coverage target the deviation touches (repeatable). |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --classification acceptable\\|risky\\|needs-follow-up` | Same, tagging the deviation with the classification the drift-entry contract consumes downstream. |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --origin llm` | An LLM-proposed record; lands `proposed`, not `approved`. |\n| `devague deviate --confirm \u003CdN>` | User-only: approve a `proposed` deviation. |\n| `devague deviate --reject \u003CdN>` | User-only: reject a `proposed` (or any) deviation. |\n| `devague deviate --list [--json]` | Read every recorded deviation back (also the default action with no positional\u002Fflag). |\n| `devague deviate ... --plan \u003Cslug>` | Target a plan other than the current one. |\n\n`--reason` is required on every record — omitting it is refused with a hint.\n`--task` naming the plan item ref is likewise required.\n\n## Hard rules (do not violate)\n\n- **Never record a deviation the human did not approve.** `devague deviate`\n  without `--origin llm` auto-approves the instant it is run — so a\n  user-origin record IS the approval. Only run it after the human has said\n  yes to this specific departure, never preemptively \"to be safe.\"\n- **Never continue past a refused approval.** If the human does not approve,\n  the run stays stopped on that task. Do not record the deviation anyway, do\n  not quietly implement the diverging approach, and do not advance the wave.\n- **LLM-origin records stay proposed until the user confirms.** `--origin\n  llm` lands `proposed`; only `devague deviate --confirm \u003CdN>` (user-only)\n  makes it `approved`. Same anti-fabrication contract as every other origin\n  in the method — an agent's own proposal never self-confirms.\n- **Deviations are never silently folded into drift after the fact.** Every\n  departure from the confirmed plan gets a `dN` record at the moment it\n  happens — not reconstructed from memory when `\u002Fsummarize-delivery` runs\n  later.\n- **The CLI stays non-orchestrating (issue #20).** `devague deviate` records\n  a decision the human already made; it does not spawn agents, gate merges,\n  mark tasks done, or make the approval decision itself. Recording is\n  deterministic — no LLM calls inside the CLI.\n- **This is not a fourth standing gate.** `\u002Fassign-to-workforce`'s three\n  human gates are the exported spec, the implementation split plan, and the\n  final PR. `\u002Fdeviate` does not add a fourth — it is the human owner of gate\n  2 amending the approved split for one scoped, in-flight decision.\n\n## Worked example\n\nMid-fan-out on task `t4`, the task agent discovers the acceptance criteria\nassumed a helper that task `t2` never actually shipped:\n\n```bash\n# 1. STOP — the main agent halts t4's worktree before more code lands\n#    against a criterion that can't be met as written.\n\n# 2. Present what\u002Fwhy\u002Fwhat-it-affects to the human:\n#    what:    t4's acceptance criterion 2 assumes a `--json` flag on a\n#             helper that t2 shipped without one\n#    why:     t2's scope was cut to land its wave on time\n#    affects: t4 (this task), and coverage target c9 (the criterion in\n#             question)\n\n# --- HUMAN: approves dropping the --json assumption from t4's criterion ---\n\n# 3. Record the approved deviation\ndevague deviate \"drop the --json assumption from t4's acceptance criterion\" \\\n  --task t4 --reason \"t2 shipped its helper without --json to land its wave on time\" \\\n  --affects t2 --affects c9 --classification acceptable\n\n# 4. Adjust t4's working brief to match what was approved, then resume the\n#    task agent against the corrected instruction.\n\n# Read the ledger back at any point:\ndevague deviate --list\ndevague deviate --list --json\n```\n\nIf the agent had proposed the record itself (`--origin llm`), the same\nrecord would land `proposed` and need an explicit\n`devague deviate --confirm d1` from the user before `\u002Fsummarize-delivery`\ncould cite it as approved.\n\n## After recording — resume, then hand off to \u002Fsummarize-delivery\n\nOnce the affected task briefs are adjusted and the fan-out resumes, nothing\nfurther is needed from this skill — the record already lives in the delivery\nstore. When the run reaches `\u002Fsummarize-delivery`, that skill's Drift From\nPlan and Mid-work Decisions sections quote these records by their `dN` id\ninstead of reconstructing drift from memory, so the connective tissue between\nthe confirmed plan and the delivery summary is the ledger this skill wrote,\nnot anyone's recollection of the run.\n\n## Provenance\n\nThis is a **first-party** skill — its origin is `agentculture\u002Fdevague`, the\n*sixth* in the outbound family after `\u002Fscope`, `\u002Fthink`, `\u002Fspec-to-plan`,\n`\u002Fassign-to-workforce`, and `\u002Fsummarize-delivery`, covering the execution-time\nleg that runs inside an `\u002Fassign-to-workforce` fan-out. guildmaster pulls it\nfrom here and broadcasts it to the AgentCulture mesh; because devague is\nupstream, it is **never re-vendored back** from guildmaster's re-broadcast\ncopy. The `cite, don't import` policy still holds: downstream repos copy it,\nthey don't symlink or depend on it. See `docs\u002Fskill-sources.md`.\n","# deviate — record an approved mid-run departure from the confirmed plan\n\nThe skill is named **`deviate`**; it is the **execution-time leg** of the\ndevague method — the *sixth* leg, sitting between the two execution skills:\n\n```text\nscope -> think -> spec-to-plan -> assign-to-workforce -> deviate -> summarize-delivery\n```\n\nWhere `\u002Fassign-to-workforce` fans out a converged plan's waves and\n`\u002Fsummarize-delivery` closes the loop afterward, `\u002Fdeviate` runs **during**\nthe fan-out, at the exact moment reality stops matching the plan the human\napproved at gate 2 (the implementation split plan). It is not a new standing\ngate — it is the human owner of gate 2 **amending** the approved split\nmid-flight, scoped to the one deviation in front of them.\n\nThe plan the user confirmed is a contract. Task agents hit constraints,\ndiscover a dependency was wrong, or find the acceptance criteria no longer\nmake sense once code is in front of them. Until this skill existed, that\nreality either silently reshaped what got built (undocumented drift) or the\nrun stalled with no recorded path forward. `\u002Fdeviate` is that path: the\ndeparture is named, approved, and recorded **before** anyone keeps building\nagainst it.\n\n## The method\n\n1. **STOP the run.** The moment a task agent (or the main agent) discovers\n   the confirmed plan no longer matches what needs to happen, halt — do not\n   keep implementing against the stale contract and do not let the fan-out\n   continue past this task.\n2. **Present what, why, and what it affects.** Lay out, for the human:\n   - **what** is diverging — the specific change from the confirmed task(s);\n   - **why** — the constraint or discovery that forced it;\n   - **what it affects** — the plan item ref(s) involved (`--task`), any\n     other task ids or coverage targets it touches (`--affects`), and which\n     acceptance criteria are no longer accurate.\n3. **Get explicit human approval.** This is the one non-negotiable step. A\n   deviation is not real until a human says yes to *this specific* departure\n   — not a standing blanket permission, not an inference from silence.\n4. **Record it via `devague deviate`.** Once approved, record the deviation\n   as a first-class ledger entry (never edit the plan itself — the plan\n   stays the untouched historical contract; see `devague\u002Fdelivery.py`). An\n   `--origin llm` record lands `proposed` and still needs the user's\n   `--confirm` — recording is not the same as approval landing as final.\n5. **Adjust the affected task briefs.** Update the working instructions the\n   task agent(s) are building against so they reflect the approved\n   departure, not the stale plan text.\n6. **Resume.** Only after the record exists (and, for an `llm`-origin record,\n   only after it is confirmed) does the fan-out continue.\n\nDeviations are never silently folded into drift after the fact — by the time\n`\u002Fsummarize-delivery` runs, every departure from the plan already has a\n`dN` record with a reason, an approval, and an optional classification. The\ndelivery summary quotes these records; it does not reconstruct drift from\nmemory.\n\n## The shipped CLI surface\n\nThis skill invokes the CLI directly and stays self-contained (if `devague`\nisn't on your PATH: `uv tool install devague`). Deviation state persists\nunder `.devague\u002Fdeliveries\u002F\u003Cplan-slug>.json` — a peer of the plan store, keyed\nby the plan slug, and never touches the plan JSON itself.\n\n| Move | What it does |\n|------|---------------|\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\"` | Record a deviation against plan item `\u003CtN>`. User-origin (the default) auto-approves. |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --affects \u003Cref> [\u003Cref> ...]` | Same, also naming every other plan item ref or coverage target the deviation touches (repeatable). |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --classification acceptable\\|risky\\|needs-follow-up` | Same, tagging the deviation with the classification the drift-entry contract consumes downstream. |\n| `devague deviate \"\u003Cwhat>\" --task \u003CtN> --reason \"\u003Ctext>\" --origin llm` | An LLM-proposed record; lands `proposed`, not `approved`. |\n| `devague deviate --confirm \u003CdN>` | User-only: approve a `proposed` deviation. |\n| `devague deviate --reject \u003CdN>` | User-only: reject a `proposed` (or any) deviation. |\n| `devague deviate --list [--json]` | Read every recorded deviation back (also the default action with no positional\u002Fflag). |\n| `devague deviate ... --plan \u003Cslug>` | Target a plan other than the current one. |\n\n`--reason` is required on every record — omitting it is refused with a hint.\n`--task` naming the plan item ref is likewise required.\n\n## Hard rules (do not violate)\n\n- **Never record a deviation the human did not approve.** `devague deviate`\n  without `--origin llm` auto-approves the instant it is run — so a\n  user-origin record IS the approval. Only run it after the human has said\n  yes to this specific departure, never preemptively \"to be safe.\"\n- **Never continue past a refused approval.** If the human does not approve,\n  the run stays stopped on that task. Do not record the deviation anyway, do\n  not quietly implement the diverging approach, and do not advance the wave.\n- **LLM-origin records stay proposed until the user confirms.** `--origin\n  llm` lands `proposed`; only `devague deviate --confirm \u003CdN>` (user-only)\n  makes it `approved`. Same anti-fabrication contract as every other origin\n  in the method — an agent's own proposal never self-confirms.\n- **Deviations are never silently folded into drift after the fact.** Every\n  departure from the confirmed plan gets a `dN` record at the moment it\n  happens — not reconstructed from memory when `\u002Fsummarize-delivery` runs\n  later.\n- **The CLI stays non-orchestrating (issue #20).** `devague deviate` records\n  a decision the human already made; it does not spawn agents, gate merges,\n  mark tasks done, or make the approval decision itself. Recording is\n  deterministic — no LLM calls inside the CLI.\n- **This is not a fourth standing gate.** `\u002Fassign-to-workforce`'s three\n  human gates are the exported spec, the implementation split plan, and the\n  final PR. `\u002Fdeviate` does not add a fourth — it is the human owner of gate\n  2 amending the approved split for one scoped, in-flight decision.\n\n## Worked example\n\nMid-fan-out on task `t4`, the task agent discovers the acceptance criteria\nassumed a helper that task `t2` never actually shipped:\n\n```bash\n# 1. STOP — the main agent halts t4's worktree before more code lands\n#    against a criterion that can't be met as written.\n\n# 2. Present what\u002Fwhy\u002Fwhat-it-affects to the human:\n#    what:    t4's acceptance criterion 2 assumes a `--json` flag on a\n#             helper that t2 shipped without one\n#    why:     t2's scope was cut to land its wave on time\n#    affects: t4 (this task), and coverage target c9 (the criterion in\n#             question)\n\n# --- HUMAN: approves dropping the --json assumption from t4's criterion ---\n\n# 3. Record the approved deviation\ndevague deviate \"drop the --json assumption from t4's acceptance criterion\" \\\n  --task t4 --reason \"t2 shipped its helper without --json to land its wave on time\" \\\n  --affects t2 --affects c9 --classification acceptable\n\n# 4. Adjust t4's working brief to match what was approved, then resume the\n#    task agent against the corrected instruction.\n\n# Read the ledger back at any point:\ndevague deviate --list\ndevague deviate --list --json\n```\n\nIf the agent had proposed the record itself (`--origin llm`), the same\nrecord would land `proposed` and need an explicit\n`devague deviate --confirm d1` from the user before `\u002Fsummarize-delivery`\ncould cite it as approved.\n\n## After recording — resume, then hand off to \u002Fsummarize-delivery\n\nOnce the affected task briefs are adjusted and the fan-out resumes, nothing\nfurther is needed from this skill — the record already lives in the delivery\nstore. When the run reaches `\u002Fsummarize-delivery`, that skill's Drift From\nPlan and Mid-work Decisions sections quote these records by their `dN` id\ninstead of reconstructing drift from memory, so the connective tissue between\nthe confirmed plan and the delivery summary is the ledger this skill wrote,\nnot anyone's recollection of the run.\n\n## Provenance\n\nThis is a **first-party** skill — its origin is `agentculture\u002Fdevague`, the\n*sixth* in the outbound family after `\u002Fscope`, `\u002Fthink`, `\u002Fspec-to-plan`,\n`\u002Fassign-to-workforce`, and `\u002Fsummarize-delivery`, covering the execution-time\nleg that runs inside an `\u002Fassign-to-workforce` fan-out. guildmaster pulls it\nfrom here and broadcasts it to the AgentCulture mesh; because devague is\nupstream, it is **never re-vendored back** from guildmaster's re-broadcast\ncopy. The `cite, don't import` policy still holds: downstream repos copy it,\nthey don't symlink or depend on it. See `docs\u002Fskill-sources.md`.\n",{"name":5,"type":24,"description":25},"command","Stop an in-flight assign-to-workforce run the moment execution must diverge from the confirmed plan, get explicit human approval for the divergence, and record it as a first-class, append-only deviation record via `devague deviate` before resuming — never fold a deviation silently into drift after the fact. Use when the user says \"deviate from the plan\", \"we need to change the plan mid-run\", \"record a deviation\", \"this isn't matching the plan anymore\", or when a task agent discovers the confirmed plan no longer matches reality partway through a workforce run. 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.\n","main","a2056e6191a4e106faf886773efed2f44ff120b2",".claude\u002Fskills\u002Fdeviate",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":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add agentculture\u002Fculture-nodes --skill deviate",{"tool":41,"command":42},"bunx","bunx skills add agentculture\u002Fculture-nodes --skill deviate",{"tool":44,"command":45},"pnpm","pnpm dlx skills add agentculture\u002Fculture-nodes --skill deviate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdeviate\u002FSKILL.md",true,[],[50,57,62,67,74,81],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"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":58,"name":52,"nameZh":6,"description":53,"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},"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":63,"name":52,"nameZh":6,"description":53,"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},"01M7AB6CJ3G1ZZJD63NEZZK1JH","https:\u002F\u002Fgithub.com\u002Fagentculture\u002Fculture-nodes\u002Fblob\u002Fmain\u002Fadapters\u002Fqwen\u002Ftests\u002Ffixtures\u002Fconfig-repo-complete\u002F.qwen\u002Fskills\u002Fsample\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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",[],[]]