360 Feedback Template

> Your landlord kept your deposit. Your mom got a medical bill that makes no sense. You got laid off on a Tuesday. Someone you love died, and no one handed you the checklist. > > Generic AI is a very confident intern. PM Skills is the senior colleague's notes — 1170 of them, one markdown file each, for the moments at work and in life where "it depends" is not an answer. (PM stands for Professional, not just Product Management. Yes, we get asked.)

PM Skills is an open-source library of 1170 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.

1170 skills 132 bundles 35 professions 12 platforms 4.8 / 5 eval-scored 0 runtime · telemetry · accounts MIT forever

🚪 Pick a door — 30 seconds each

Nothing here can scare your setup. A skill is a markdown file your AI reads. No runtime, no telemetry, no accounts. Installing copies text files; uninstalling is deleting them. Skeptical? Good instinct — read one first, it's written for humans too.

🥊 Without a skill vs. with one

✨ See it in action

▶ Pick a skill → fill a short form → run it → a senior-grade artifact streams out. Your key stays in your browser, or run free with no key.

🌌 Galaxy 3D — all 1170 skills as a constellation. The ones you've run burn brighter. Zero productivity value, 100% recommended. 🎁 Wrapped — your practice as a shareable story. 100% local; nobody learns you ran saying-no-kindly eleven times.

♻️ New: promote what you keep asking for

You have five prompts you type every week with small changes. Each one is a skill that hasn't been written down yet. The pm-skill-promoter bundle closes the loop: scan your own transcripts, pick a pattern, draft the skill, test its triggers, publish it. One command: /promote ~/.claude/projects/my-project.

Here is the loop on the fixture in examples/promoter/, a made-up three-week transcript with a few secrets planted in it:

$ python3 skills/promoter-scan/scripts/promoter_scan.py examples/promoter

| # | Pattern                            | Times | Score |
|---|------------------------------------|------:|------:|
| 1 | write release notes log            |    14 |    82 |   ← you asked for this FOURTEEN times
| 2 | draft update notes stakeholder     |     6 |    71 |
| 3 | summarise thread decisions owners  |     5 |    60 |

  "my api key is [api-key] please use it"      ← the planted secrets come out redacted
  "email the report to [email] and cc [phone]"

Pattern 1 becomes release-notes-from-git-log: a trigger built from the phrases you actually typed, three worked examples with your product name removed, and the corrections you kept making ("shorter", "group by feature", "user-facing tone") turned into quality checks. Then the test:

$ python3 skills/promoter-test/scripts/promoter_test.py drafted-skill/SKILL.md drafted-skill/evals.json
precision 1.0  recall 1.0        ← fires on "changelog entry from these commits", stays quiet on "write a haiku about deploys"

Then promoter-publish prints the entire release package and asks once before pushing. The whole story, with every file: docs/PROMOTE-LOOP.md. Nothing leaves your machine during the scan; the redaction runs before anything is written.