[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72CJCVNC5JB3M36ES649CTY":3,"skill-same:01M72CJCVNC5JB3M36ES649CTY":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M72CJCVNC5JB3M36ES649CTY","workflow-state",null,"Read and update workflow state when planning, executing, completing, pausing or resuming project work.","1aGh\u002Fmaude","1aGh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17166964?v=4","01M72CAQDBB0YG724KFT7WEYRF","Michal Dovrtel","01M72CAQDXC32AWQRZYNJXXDC4",3,"MIT","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fworkflow-state\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: workflow-state\ntype: skill\ndescription: \"Read and update workflow state when planning, executing, completing, pausing or resuming project work.\"\nkeywords: [state, workflow, phase, handoff, continuity, session]\n---\n\n# Workflow State\n\nFollow [host conventions](..\u002F..\u002FHARNESS.md) for Claude Code or Codex.\n\n`.ai\u002Fstate\u002FSTATE.md` is the single source of truth for \"what's happening right now.\" It's read by `\u002Fstatus`, `\u002Fresume`, `\u002Fdone`, and any future agent that joins mid-feature. Keep it accurate.\n\nThis skill complements `workflow-orchestration` (which covers the protocol of phases & gates). This skill focuses on the **STATE.md schema and lifecycle**.\n\n## Backend: file vs. knowledge graph (kgai-aware)\n\nLoad **`flow:kgai-backend`** and check `maude kg resolve --json` before treating STATE.md as authoritative:\n\n- **`active: false`** (default — most repos) → the schema below **is** the source of truth. Everything in this skill applies unchanged. No regression.\n- **`active: true`** → the **knowledge graph is the history authority**, and `.ai\u002Fstate\u002FSTATE.md` is a thin human-readable **pointer-stub** (written by `maude init --kg`): status line + \"history lives in kgai — `kg history` \u002F `kg context`\". History rows, the Decisions section, and pause\u002Fresume state live as graph events (see `flow:kgai-backend` for the `plan:`\u002F`session:` recipes; `\u002Fflow:run --pause` records a `paused` event, `\u002Fflow:run --resume` reconstructs from it, `\u002Fflow:run --status` overlays `kg history`\u002F`kg context`). Do NOT append full History rows to the stub — write the movement to the graph instead. The narrative files STATE.md never owned (PRD, design-system, plans) stay on disk as prose.\n\n**This is behind the `active` gate — an inactive repo keeps the full STATE.md below, untouched (slim, never gut).**\n\n## STATE.md schema\n\n```markdown\n# Workflow State\n\n**Workflow:** ad-hoc\n**Phase:** intake | discovery | design | planning | execution | verification | done | paused | blocked\n**Status:** ready | in-progress | paused | blocked | done\n**Started:** \u003CYYYY-MM-DD>\n**Updated:** \u003CYYYY-MM-DD HH:MM>\n**Active task:** \u003Cone-liner from the plan or \"—\">\n**Active plan:** \u003C.ai\u002Fplans\u002F\u003Cx>.plan.md, or `plan:\u003Cslug>` when the plan lives in orbit, or \"—\">\n\n## Decisions\n\n\u003Cbullet list — short summaries; full DDRs live in .ai\u002Fdecisions\u002F>\n\n## Blockers\n\n\u003Cbullet list — what is in the way, who must decide it>\n\n## History\n\n| When | Phase | Note |\n| ---- | ----- | ---- |\n| \u003CYYYY-MM-DD HH:MM> | \u003Cphase> | \u003Cone-liner> |\n```\n\n## Rules\n\n1. **Every phase change → a new history row.** History is append-only — no row gets rewritten, removed, or reordered.\n2. **Update the Updated field on every edit.** `\u002Fstatus` and `\u002Fresume` use it to detect stale state.\n3. **Pause path:** Phase → `paused`, Status → `paused`, keep the current `Active task` (do not clear it). Details go in `.ai\u002Fstate\u002FHANDOFF.md`.\n4. **Done path:** Phase → `done`, Status → `done`, Active task → `—`, Active plan → `—`. The plan moves to `.ai\u002Fplans\u002Farchive\u002F` — unless `integrations.tracker.artifacts.store` is `orbit`, where there is no local archive and the **Active plan** line holds the orbit slug (`plan:\u003Cslug>`) instead of a path, so `\u002Fflow:run --resume` and `\u002Fflow:run --status` know to pull it (`flow:orbit-backend` [guide 06](..\u002Forbit-backend\u002F_guide-06-artifact-store.md)).\n5. **Blocked:** Phase stays the same, Status → `blocked`, the Blockers section gets a bullet with the specifics.\n\n## HANDOFF.md (only while paused)\n\nA transient file. Created on `\u002Fpause`, removed on `\u002Fresume`. **Never committed standalone** — it lives in `.gitignore`. If it appears in git, that is a leak.\n\nUse `.ai\u002Ftemplates\u002FHANDOFF.md` as the base. Key sections:\n\n- Active feature\n- Last task (with status)\n- Next step (concrete command \u002F file \u002F line)\n- Open questions \u002F blockers\n- Files touched (uncommitted)\n- Recent thinking (1–2 paragraphs — trail of thought)\n\n## Anti-patterns\n\n- ❌ Hand-editing History without a phase change.\n- ❌ Deleting History rows to \"clean up\" — that is institutional amnesia.\n- ❌ STATE.md committed with status `in-progress` on the main branch — either work is `done`, or it lives in a PR.\n- ❌ HANDOFF.md committed — it is gitignored for a reason.\n- ❌ Multiple active plans at once without an explicit reason — if you want to drive two things in parallel, use branches, not one state.\n\n## Integration\n\n| Command | What it does with STATE.md |\n|---------|----------------------------|\n| `\u002Fplan` | Phase → `planning`, Active plan → `\u003Cpath>`, history row |\n| `\u002Fexecute` | Phase → `execution`, Active task per task, history row per completed task |\n| `\u002Fdone` | Phase + Status → `done`, plan archived, final history row |\n| `\u002Fpause` | Status → `paused`, Active task kept, creates HANDOFF.md |\n| `\u002Fresume` | Status → `in-progress`, removes HANDOFF.md, history row |\n| `\u002Fstatus` | Read-only — returns summary |\n| `\u002Fflow:record-ddr` | Appends to `## Decisions` (summary only, full DDR in `.ai\u002Fdecisions\u002F`) |\n","# Workflow State\n\nFollow [host conventions](..\u002F..\u002FHARNESS.md) for Claude Code or Codex.\n\n`.ai\u002Fstate\u002FSTATE.md` is the single source of truth for \"what's happening right now.\" It's read by `\u002Fstatus`, `\u002Fresume`, `\u002Fdone`, and any future agent that joins mid-feature. Keep it accurate.\n\nThis skill complements `workflow-orchestration` (which covers the protocol of phases & gates). This skill focuses on the **STATE.md schema and lifecycle**.\n\n## Backend: file vs. knowledge graph (kgai-aware)\n\nLoad **`flow:kgai-backend`** and check `maude kg resolve --json` before treating STATE.md as authoritative:\n\n- **`active: false`** (default — most repos) → the schema below **is** the source of truth. Everything in this skill applies unchanged. No regression.\n- **`active: true`** → the **knowledge graph is the history authority**, and `.ai\u002Fstate\u002FSTATE.md` is a thin human-readable **pointer-stub** (written by `maude init --kg`): status line + \"history lives in kgai — `kg history` \u002F `kg context`\". History rows, the Decisions section, and pause\u002Fresume state live as graph events (see `flow:kgai-backend` for the `plan:`\u002F`session:` recipes; `\u002Fflow:run --pause` records a `paused` event, `\u002Fflow:run --resume` reconstructs from it, `\u002Fflow:run --status` overlays `kg history`\u002F`kg context`). Do NOT append full History rows to the stub — write the movement to the graph instead. The narrative files STATE.md never owned (PRD, design-system, plans) stay on disk as prose.\n\n**This is behind the `active` gate — an inactive repo keeps the full STATE.md below, untouched (slim, never gut).**\n\n## STATE.md schema\n\n```markdown\n# Workflow State\n\n**Workflow:** ad-hoc\n**Phase:** intake | discovery | design | planning | execution | verification | done | paused | blocked\n**Status:** ready | in-progress | paused | blocked | done\n**Started:** \u003CYYYY-MM-DD>\n**Updated:** \u003CYYYY-MM-DD HH:MM>\n**Active task:** \u003Cone-liner from the plan or \"—\">\n**Active plan:** \u003C.ai\u002Fplans\u002F\u003Cx>.plan.md, or `plan:\u003Cslug>` when the plan lives in orbit, or \"—\">\n\n## Decisions\n\n\u003Cbullet list — short summaries; full DDRs live in .ai\u002Fdecisions\u002F>\n\n## Blockers\n\n\u003Cbullet list — what is in the way, who must decide it>\n\n## History\n\n| When | Phase | Note |\n| ---- | ----- | ---- |\n| \u003CYYYY-MM-DD HH:MM> | \u003Cphase> | \u003Cone-liner> |\n```\n\n## Rules\n\n1. **Every phase change → a new history row.** History is append-only — no row gets rewritten, removed, or reordered.\n2. **Update the Updated field on every edit.** `\u002Fstatus` and `\u002Fresume` use it to detect stale state.\n3. **Pause path:** Phase → `paused`, Status → `paused`, keep the current `Active task` (do not clear it). Details go in `.ai\u002Fstate\u002FHANDOFF.md`.\n4. **Done path:** Phase → `done`, Status → `done`, Active task → `—`, Active plan → `—`. The plan moves to `.ai\u002Fplans\u002Farchive\u002F` — unless `integrations.tracker.artifacts.store` is `orbit`, where there is no local archive and the **Active plan** line holds the orbit slug (`plan:\u003Cslug>`) instead of a path, so `\u002Fflow:run --resume` and `\u002Fflow:run --status` know to pull it (`flow:orbit-backend` [guide 06](..\u002Forbit-backend\u002F_guide-06-artifact-store.md)).\n5. **Blocked:** Phase stays the same, Status → `blocked`, the Blockers section gets a bullet with the specifics.\n\n## HANDOFF.md (only while paused)\n\nA transient file. Created on `\u002Fpause`, removed on `\u002Fresume`. **Never committed standalone** — it lives in `.gitignore`. If it appears in git, that is a leak.\n\nUse `.ai\u002Ftemplates\u002FHANDOFF.md` as the base. Key sections:\n\n- Active feature\n- Last task (with status)\n- Next step (concrete command \u002F file \u002F line)\n- Open questions \u002F blockers\n- Files touched (uncommitted)\n- Recent thinking (1–2 paragraphs — trail of thought)\n\n## Anti-patterns\n\n- ❌ Hand-editing History without a phase change.\n- ❌ Deleting History rows to \"clean up\" — that is institutional amnesia.\n- ❌ STATE.md committed with status `in-progress` on the main branch — either work is `done`, or it lives in a PR.\n- ❌ HANDOFF.md committed — it is gitignored for a reason.\n- ❌ Multiple active plans at once without an explicit reason — if you want to drive two things in parallel, use branches, not one state.\n\n## Integration\n\n| Command | What it does with STATE.md |\n|---------|----------------------------|\n| `\u002Fplan` | Phase → `planning`, Active plan → `\u003Cpath>`, history row |\n| `\u002Fexecute` | Phase → `execution`, Active task per task, history row per completed task |\n| `\u002Fdone` | Phase + Status → `done`, plan archived, final history row |\n| `\u002Fpause` | Status → `paused`, Active task kept, creates HANDOFF.md |\n| `\u002Fresume` | Status → `in-progress`, removes HANDOFF.md, history row |\n| `\u002Fstatus` | Read-only — returns summary |\n| `\u002Fflow:record-ddr` | Appends to `## Decisions` (summary only, full DDR in `.ai\u002Fdecisions\u002F`) |\n",{"name":5,"type":24,"keywords":25,"description":7},"skill",[26,27,28,29,30,31],"state","workflow","phase","handoff","continuity","session","main","cfde9d2b169e4b418a5c5efb35297cc575dc764c","plugins\u002Fflow\u002Fskills\u002Fworkflow-state",0,"https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude","https:\u002F\u002Fmaude.sh","https:\u002F\u002Fgithub.com\u002F1aGh","www.iagh.cz","2026-11-13 20:38:15",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add 1aGh\u002Fmaude --skill workflow-state",{"tool":47,"command":48},"bunx","bunx skills add 1aGh\u002Fmaude --skill workflow-state",{"tool":50,"command":51},"pnpm","pnpm dlx skills add 1aGh\u002Fmaude --skill workflow-state","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fworkflow-state\u002FSKILL.md",true,[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M72CJAJBZT2RHE97ND8EFTA3","ui-rules","UI hard-stop rules and audit method: WCAG 2.1 AA accessibility, responsive layout and motion.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fui-rules\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M72CJ857314HCC8A99T4K0D2","testing-rules","Apply test quality rules during implementation and review: meaningful assertions, isolation and coverage.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Ftesting-rules\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M72CJ6N80HW2WRS8BV4QSS4V","security-rules","Apply application and AI security checks to code reviews, implementation and threat-driven validation.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fsecurity-rules\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M72CJ4C41Q4E1WDTFMKYFX3Q","scenario","Author or run cross-platform UI scenarios with selectors, screenshots, platform coverage and result reports.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fscenario\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M72CJ1QYX752BM7G12250YJR","question-protocol","Batch necessary questions from workflow participants, collect user answers and route them to the requester.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fquestion-protocol\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M72CHYXD666BK85AM6SH97QV","quality-gates","Resolve project quality commands, scoped checks, gate failures and validation fallbacks from workflow config.","https:\u002F\u002Fgithub.com\u002F1aGh\u002Fmaude\u002Fblob\u002Fmain\u002Fplugins\u002Fflow\u002Fskills\u002Fquality-gates\u002FSKILL.md",[],[]]