Corpus good
Skill ai-creed/ai-shakespii/tests/fixtures/corpus/with-broken/corpus-good
Workbench for Agent Skills — lint, test, benchmark, and gate-install SKILL.md skills for Claude Code, Codex, Cursor, Gemini, and more
npx -y skills add ai-creed/ai-shakespii --skill corpus-goodAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 2 stars2 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
Use when verifying that one broken skill does not abort the corpus run.
SKILL.md
0.7 KB, as published. Nobody here has run it
corpus-good
Intent
Serves as the healthy neighbor of a deliberately broken fixture skill.
Inputs
The corpus root path handed over by the broken-skill test.
Preconditions
The broken fixture tree is checked out unchanged.
Procedure
- Lint cleanly while the neighbor fails to parse.
- Prove the corpus loop isolates per-skill failures.
Output
An empty findings list for the good fixture.
Examples
Given the input good, the expected output is good-lint-clean.
Anti-patterns
Fixing the broken neighbor; it is broken by design.