---
description: Full technical governance scan; rebuild .pm/dashboard. Default does not wait on draft PRD. Use --compare-baseline only after a confirmed PRD/charter.
handoffs:
label: Status
agent: pm.status
prompt: Summarize after full scan
send: true
Technical (default): scan architecture + enabled modules. --skip-charter-gate is an alias of this default.
Baseline compare (--compare-baseline): only if prd.status=confirmedorcharter.status=approved. If still draft, wait and offer confirm / revise / skip / 继续技术扫描.
Run module scans (arch, engineering, env, api, test, release, db, ops, cost) then bugs if log sources/--path/paste exist; else skip bugs with recommendation.
Architecture step must produce diagrams and.pm/architecture/map.json: run pm arch / /pm-arch.
Module deep-scan internals live in templates/commands/discover.md — do not tell the user to run /pm-discover.
Merge findings/todos; write evidence/scans/pm-all-*.json.
4b. Qualified reviews: every finding written to .pm/engineering/reviews.md MUST include reasoning + cited snippet. Unqualified rows MUST NOT enter rules.md. If there is no local diff, say there is nothing to review. Load enabled rules from .pm/engineering/rules.md. Only disposition=confirmed may become rules. P0/blocking MUST interrupt; P1/P2 stay in the report. Prefer /pm-review for a dedicated review pass. Full checkup is /pm-checkup only — do not run it here by default.
Chat summary (中文): all blocking+high todos (no 3-item cap) unless --verbose.
Closing: _closing.md 完整档;只列已生成文件。
Finish with /pm-status style Chinese health line.
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. 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 == approvedand the user asked --compare-baseline (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).
Append audit to .pm/state/audit.jsonl.
Never auto-write source/SQL/cloud or land generated docs/rules without explicit user confirmation.
1---2name: pm-all3description: PM Manager /pm-all4---56---7description: Full technical governance scan; rebuild .pm/dashboard. Default does not wait on draft PRD. Use --compare-baseline only after a confirmed PRD/charter.8handoffs:9 - label: Status10 agent: pm.status11 prompt: Summarize after full scan12 send: true13---1415## User Input1617```text18$ARGUMENTS19```2021Flags: `--compare-baseline` | `--skip-charter-gate` (default technical mode) | `--modules=...` | `--path=...` | `--verbose`.2223## Outline2425Default mode is a **technical debt scan**. Do **not** block on `prd.status=draft`. Unconfirmed PRD/charter must not be used to judge “是否合理”.26271. Gate: `.pm` initialized? else **block** → recommend `/pm-init`.282. Modes:29 - **Technical (default)**: scan architecture + enabled modules. `--skip-charter-gate` is an alias of this default.30 - **Baseline compare (`--compare-baseline`)**: only if `prd.status=confirmed` **or** `charter.status=approved`. If still draft, **wait** and offer confirm / revise / skip / 继续技术扫描.313. Run module scans (arch, engineering, env, api, test, release, db, ops, cost) then bugs if log sources/`--path`/paste exist; else skip bugs with recommendation.32 - Architecture step **must** produce diagrams **and** `.pm/architecture/map.json`: run `pm arch` / `/pm-arch`.33 - Module deep-scan internals live in `templates/commands/discover.md` — do **not** tell the user to run `/pm-discover`.344. Merge findings/todos; write `evidence/scans/pm-all-*.json`.354b. Qualified reviews: every finding written to `.pm/engineering/reviews.md` MUST include reasoning + cited snippet. Unqualified rows MUST NOT enter `rules.md`. If there is no local diff, say there is nothing to review. Load enabled rules from `.pm/engineering/rules.md`. Only `disposition=confirmed` may become rules. P0/blocking MUST interrupt; P1/P2 stay in the report. Prefer `/pm-review` for a dedicated review pass. Full checkup is **`/pm-checkup` only** — do not run it here by default.365. **Rebuild the dashboard** (required):37 - Prefer running: `pm dashboard` (from project root)38 - Output: `.pm/dashboard/index.html`、`overview.md`、`findings.md`、`todos.md`、`stats.json`396. Chat summary (中文): all blocking+high todos (no 3-item cap) unless `--verbose`.407. Closing: `_closing.md` 完整档;只列已生成文件。418. Finish with `/pm-status` style Chinese health line.4243## Shared Workflow (all /pm-* commands)4445Follow this order when the command mutates `.pm/` state:46471. Read `.pm/config/project.yaml` and `.pm/config/local.yaml` (if missing and command is not init → recommend `/pm-init`).482. If `.pm/` metadata is valid, load it; do **not** force a full-repo rescan. Prefer `.pm/architecture/map.json` and the document index before walking the tree.493. Desensitize evidence → `.pm/evidence/scans/{command}-{timestamp}.json` (secrets → `***`). Never persist raw secrets.504. Optional charter compare only when `charter.status == approved` **and** the user asked `--compare-baseline` (attach `confidence`). Draft PRD/charter MUST NOT be used as the baseline.515. Incremental merge into module `findings.md` / `todo.md`; sync authoritative `state/todo.md`.526. Refresh `state/overview.md` with **all** open/in_progress blocking+high todos (no 3-item cap).537. Append audit to `.pm/state/audit.jsonl`.548. Never auto-write source/SQL/cloud or land generated docs/rules without explicit user confirmation.559. **Closing:** `templates/commands/_closing.md`(完整档,只列已有路径)。5657Design baseline: `docs/prd.md` + 宪章。
Run npx skillmds@latest add wei63w/pm-all 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-all 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.