pm-all
PM Manager /pm-all
SKILL.mdadapters/cursor/skills/pm-all/SKILL.md
GitHub--- 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
User Input
$ARGUMENTS
Flags: --compare-baseline | --skip-charter-gate (default technical mode) | --modules=... | --path=... | --verbose.
Outline
Default 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”.
- Gate:
.pminitialized? else block → recommend/pm-init. - Modes:
- Technical (default): scan architecture + enabled modules.
--skip-charter-gateis an alias of this default. - Baseline compare (
--compare-baseline): only ifprd.status=confirmedorcharter.status=approved. If still draft, wait and offer confirm / revise / skip / 继续技术扫描.
- Technical (default): scan architecture + enabled modules.
- 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: runpm arch//pm-arch. - Module deep-scan internals live in
templates/commands/discover.md— do not tell the user to run/pm-discover.
- Architecture step must produce diagrams and
- Merge findings/todos; write
evidence/scans/pm-all-*.json. 4b. Qualified reviews: every finding written to.pm/engineering/reviews.mdMUST include reasoning + cited snippet. Unqualified rows MUST NOT enterrules.md. If there is no local diff, say there is nothing to review. Load enabled rules from.pm/engineering/rules.md. Onlydisposition=confirmedmay become rules. P0/blocking MUST interrupt; P1/P2 stay in the report. Prefer/pm-reviewfor a dedicated review pass. Full checkup is/pm-checkuponly — do not run it here by default. - Rebuild the dashboard (required):
- Prefer running:
pm dashboard(from project root) - Output:
.pm/dashboard/index.html、overview.md、findings.md、todos.md、stats.json
- Prefer running:
- 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-statusstyle Chinese health line.
Shared Workflow (all /pm-* commands)
Follow this order when the command mutates .pm/ state:
- Read
.pm/config/project.yamland.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.jsonand 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(attachconfidence). Draft PRD/charter MUST NOT be used as the baseline. - Incremental merge into module
findings.md/todo.md; sync authoritativestate/todo.md. - Refresh
state/overview.mdwith 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.
- Closing:
templates/commands/_closing.md(完整档,只列已有路径)。
Design baseline: docs/prd.md + 宪章。