agentsclimarketplace

Skill activation test

Skill muqian2026-rgb/qian-public/skills/skill-activation-test

Book-learn-distill + Cursor Skills for PM workflow. Fork to clone PRD gates, issue-ready checks, and skill factory patterns.

Install
npx -y skills add muqian2026-rgb/qian-public --skill skill-activation-test

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Test whether a Cursor skill triggers correctly: 5 positive prompts, 3 negative, metadata audit. Use after writing or updating any SKILL.md. Pairs with book-learn-distill.

SKILL.md

1.9 KB, as published. Nobody here has run it

Skill Activation Test

QA gate for your own Agent Skills — not for third-party installs.

When to use

  • After Equip stage in book-learn-distill
  • After editing description or trigger phrases in any Skill
  • Before publishing a Skill copy to a public repo

Test protocol

1 · Positive triggers (5 phrases → should activate)

#User saysActivated?
1
2
3
4
5

Use varied wording — not copy-paste of description.

2 · Negative triggers (3 adjacent tasks → should NOT activate)

#User saysShould route toFalse positive?
1
2
3

3 · Self-check question

Ask Agent: "When would you use this skill?"

Compare answer to intended triggers in SKILL.md.

4 · Metadata audit

  • description contains clear trigger phrases
  • Negative constraints in SKILL.md body
  • Boundary vs similar Skills documented

5 · Verdict

  • Pass → record date in project meta.json (skillTestedAt) if applicable
  • Fail → revise SKILL.md; log in references/template.md

Agent instructions

When user says "run skill activation test for X":

  1. Read skills/<slug>/SKILL.md (or path given)
  2. Propose 5 positive + 3 negative test phrases before user runs them
  3. After user reports results, output pass/fail table + fix list for description/triggers

Reference

Blank template: references/template.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.