Skill Claude CodeCodex
Part of loopkit
Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.
not rated 755
+2 1mo ago A 36 tokens
original MIT
755Stars on the repository
67Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.
not rated 755 1mo ago A 40 tokens
MIT
Skill Claude CodeCodex
Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including clarifying questions.
not rated 755 1mo ago B 40 tokens
MIT
Skill Claude CodeCodex
Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. Requires running the verification command in THIS turn and reading its output before any success claim.
not rated 755 1mo ago A 45 tokens
MIT
Skill Claude CodeCodex
Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.
not rated 755 1mo ago A 29 tokens
MIT
my-new-skill
54Skill Claude CodeCodex
One sentence that describes WHEN to invoke this skill. Write it as a trigger phrase, not a summary — include the words a user would say ("fix bug", "add feature", "review diff"). The agent routes on this field.
not rated 755 1mo ago A 52 tokens
MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: