Parse TODO id. Require it exists in state/todo.md.
--start → in_progress only.
Else → done, append to state/completed.md and module completed.md, remove/mark done in state todo.
If linked finding has no other open todos → resolved.
Refresh overview; confirm the item is no longer in the open blocking/high list.
Shared Workflow (all /pm-* commands)
Follow this order when the command mutates .pm/ state:
Read .pm/config/project.yaml and .pm/config/local.yaml (if missing and command is not init → recommend /pm-init).
If .pm/ metadata is valid, load it; do not force a full-repo rescan. On-demand incremental scan using sources + extra_scan_roots + --path + conversation paste (highest priority for /pm-fix). Prefer .pm/architecture/map.json and the document index before walking the tree.
Desensitize evidence → .pm/evidence/scans/{command}-{timestamp}.json (secrets → ***). Never persist raw secrets.
Optional charter compare only when charter.status == approved (attach confidence). Draft PRD/charter MUST NOT be used as the baseline.
Incremental merge into module findings.md / todo.md; sync authoritative state/todo.md.
Refresh state/overview.md with all open/in_progress blocking+high todos (no 3-item cap). Medium/low: counts only unless --verbose.
Append audit to .pm/state/audit.jsonl (command, time, input/output summary; include reasoning when the step was AI-produced).
Output risk summary + recommended next step (≤20 lines). Never auto-write source/SQL/cloud or land generated docs/rules without explicit user confirmation.
1---2name: pm-done3description: PM Manager /pm-done4---56---7description: Close a todo (TODO-xxx), sync completed.md, refresh overview.8handoffs:9 - label: Status10 agent: pm.status11 prompt: Refresh status after closing todo12 send: true13---1415## User Input1617```text18$ARGUMENTS19```2021Usage: `TODO-001` | `TODO-001 --note "..."` | `TODO-001 --start` (only in_progress).2223## Outline24251. Parse TODO id. Require it exists in `state/todo.md`.262. `--start` → `in_progress` only.273. Else → `done`, append to `state/completed.md` and module `completed.md`, remove/mark done in state todo.284. If linked finding has no other open todos → `resolved`.295. Refresh overview; confirm the item is no longer in the open blocking/high list.303132## Shared Workflow (all /pm-* commands)3334Follow this order when the command mutates `.pm/` state:35361. Read `.pm/config/project.yaml` and `.pm/config/local.yaml` (if missing and command is not init → recommend `/pm-init`).372. If `.pm/` metadata is valid, load it; do **not** force a full-repo rescan. On-demand **incremental** scan using `sources` + `extra_scan_roots` + `--path` + **conversation paste** (highest priority for `/pm-fix`). Prefer `.pm/architecture/map.json` and the document index before walking the tree.383. Desensitize evidence → `.pm/evidence/scans/{command}-{timestamp}.json` (secrets → `***`). Never persist raw secrets.394. Optional charter compare only when `charter.status == approved` (attach `confidence`). Draft PRD/charter MUST NOT be used as the baseline.405. Incremental merge into module `findings.md` / `todo.md`; sync authoritative `state/todo.md`.416. Refresh `state/overview.md` with **all** open/in_progress blocking+high todos (no 3-item cap). Medium/low: counts only unless `--verbose`.427. Append audit to `.pm/state/audit.jsonl` (command, time, input/output summary; include reasoning when the step was AI-produced).438. Output risk summary + recommended next step (≤20 lines). Never auto-write source/SQL/cloud or land generated docs/rules without explicit user confirmation.449. **Closing:** `templates/commands/_closing.md` **轻量**档(1–2 个已存在链接)。中文摘要。4546Design baseline: `docs/prd.md` + 宪章。
Run npx skillmds@latest add wei63w/pm-done in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
PM Manager /pm-done It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
wei63w (@wei63w) published this skill. Their other Agent Skills are listed on their SkillMD profile.