Pm discover

Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).

Install

npx -y skills add wei63w/pm-manager --skill pm-discover

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

16 days oldThe repository was created 16 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.

Copied from the file, not written here

Deep-scan all enabled governance modules and refresh state (internal; used by pm-all / status --full).

2.1 KB, 467 tokens by cl100k_base, as published. Nobody here has run it

$ARGUMENTS

Require init. For each enabled module, perform on-demand technical scan + optional charter compare.
For architecture: run pm arch (or /pm-arch) so .pm/architecture/ gets real Mermaid diagrams (system context, dependencies, request/deploy flows) — not placeholder stubs.
Incremental merge; suppress duplicate evidence hashes.
Refresh state overview/todo.
Rebuild .pm/dashboard/ with pm dashboard (aggregate findings + todos).
Keep chat brief unless --verbose.
Required closing: follow templates/commands/_closing.md — Summary + Open links for .pm/dashboard/index.html, .pm/dashboard/overview.md, and .pm/architecture/overview.md (if arch ran). Ask the user to open them.

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).
On-demand scan using sources + extra_scan_roots + --path + conversation paste (highest priority for /pm-fix).
Desensitize evidence → .pm/evidence/scans/{command}-{timestamp}.json (secrets → ***).
Optional charter compare when charter.status != absent (attach confidence).
Incremental merge into module findings.md / todo.md; sync authoritative state/todo.md.
Refresh state/overview.md (include Today's Top3, max 3, blocking+high by default).
Output risk summary + recommended next step (≤20 lines). Never auto-write source/SQL/cloud without confirmation.
Closing (required): end the user-facing reply with Summary + Open these links per templates/commands/_closing.md (dashboard and/or architecture overviews). Ask the user to open them.

Design baseline: repo root pm-manager-v2.md (or packaged copy under memory/).