Code review
Skill MarchRory/liushi_agent_settings/packages/harness/src/.agents/skills/code-review
Use when code, configuration, documentation, policies, or public interfaces changed and the result needs risk-focused review before delivery.From its SKILL.md
npx -y skills add MarchRory/liushi_agent_settings --skill code-reviewAssembled 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.
SKILL.md
0.8 KB, 134 tokens by cl100k_base, as published. Nobody here has run it
Code Review
Core Rule
Review for user-impacting defects first. Lead with blocking issues, cite evidence, and separate verified facts from uncertainty.
Workflow
- Read
references/workflow.mdfor the review procedure and severity rules. - Use
references/output-schema.mdfor the required report shape. - Use
examples/standard-output.yamlas a compact template when returning structured output.
Resource Map
references/workflow.md: review order, severity definitions, and evidence rules.references/output-schema.md: canonicalreviewschema.examples/standard-output.yaml: minimal valid review report.
What ships with it: 4 files
2.0 KB alongside SKILL.md
agents/
- openai.yaml271 B
examples/
- standard-output.yaml254 B
references/
- output-schema.md338 B
- workflow.md1.1 KB