AgentStack
SKILL verified MIT Self-run

Pm Export

skill-wei63w-pm-manager-pm-export · by wei63w

>-

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-wei63w-pm-manager-pm-export

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Pm Export? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/pm-export

Follow the workflow below exactly. Scaffold helper: \pm init\ or \scripts/python/createpmscaffold.py\.

When resolving pack files, prefer the \pm-manager\ directory that contains this skill's sibling \ emplates/\ (or the project skill pack root).

User Input

$ARGUMENTS

Outline

  1. Build markdown: overview, Top todos, blocking findings, charter summary, milestones.
  2. Exclude local.yaml, credentials, raw logs.
  3. Write to user-specified path (default Desktop pm-export-YYYYMMDD.md).

Shared Workflow (all /pm-* commands)

Follow this order when the command mutates .pm/ state:

  1. Read .pm/config/project.yaml and .pm/config/local.yaml (if missing and command is not init → recommend /pm-init).
  2. On-demand scan using sources + extra_scan_roots + --path + conversation paste (highest priority for /pm-fix).
  3. Desensitize evidence → .pm/evidence/scans/{command}-{timestamp}.json (secrets → ***).
  4. Optional charter compare when charter.status != absent (attach confidence).
  5. Incremental merge into module findings.md / todo.md; sync authoritative state/todo.md.
  6. Refresh state/overview.md (include Today's Top3, max 3, blocking+high by default).
  7. Output risk summary + recommended next step (≤20 lines). Never auto-write source/SQL/cloud without confirmation.

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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.