test-skill
Skill158 starsChanged 7 months agoApache-2.0View on GitHub
Extended diagnostic skill that validates the full Cognithor skill lifecycle — SkillRegistry scanning, keyword matching (exact + fuzzy at 70% threshold), and async execution. Use when testing skill discovery, debugging keyword matching accuracy, validating the SkillRegistry scan cycle, or verifying async execute() behavior.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- tingly-dev/tingly-boxtheir own version, first seen Oct 23, 2026
- NaveenGumaste/keyskillstheir own version, first seen Oct 13, 2026
- Karanjot786/agent-skills-clitheir own version, first seen Oct 13, 2026
- wardawgmalvicious/agent-configtheir own version, first seen Oct 13, 2026
- uptownhr/claude-code-agenttheir own version, first seen Oct 9, 2026
- warpdotdev/oz-agent-actiontheir own version, first seen Oct 8, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- tingly-dev/tingly-box★ 379same name
- Karanjot786/agent-skills-cli★ 182same name
- warpdotdev/oz-agent-action★ 120same name
- martinemde/skillet★ 19same name
- joeynyc/skillscore★ 17same name
- Peng416/skills-runtime★ 6same name
- lubancafe/agent-skills★ 2same name
- NaveenGumaste/keyskills★ 2same name
- Facets-cloud/claude-skill-tester★ 1same name
- uptownhr/claude-code-agent★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- backupSkill
- gmail-syncSkill
- testSkill
- wetter-abfrageSkill
The file
Files
Test Skill
Extended diagnostic that validates the full skill lifecycle: directory scan → SkillRegistry registration → keyword matching → async execute().
Steps
- Trigger the skill — Cognithor must match via keyword similarity:
cognithor test_skill <eingabe> - Verify registration — confirm the skill appears in the registry:
User > Zeige alle registrierten Skills # Expected: test_skill listed with NAME="test_skill", VERSION="0.1.0" - Check keyword matching — the SkillRegistry uses exact match (case-insensitive) then fuzzy match (70% threshold). Verify the input routes to this skill, not the sibling
testskill - Inspect the response —
execute()returns:{"status": "ok", "result": "TODO"} - Confirm async execution — the skill runs via
async def execute(self, params), so verify no blocking calls appear in logs
Example
User > cognithor test_skill Prüfe den Lifecycle
Cognithor > {"status": "ok", "result": "TODO"}
# Success: skill was discovered, matched, and executed asynchronouslyTroubleshooting
| Symptom | Cause | Fix |
Routes to test instead | Fuzzy match overlap | Use the full slug test_skill to force exact match |
ModuleNotFoundError | __init__.py missing | Verify skills/test_skill/__init__.py exists |
| Timeout on execute | Event loop blocked | Check for synchronous calls in skill.py |
Notes
Diagnostic-only skill — "result": "TODO" is intentional. Differs from test by validating keyword disambiguation and the full scan-to-execute lifecycle.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

