Igapyon miku prompt lint
Skill igapyon/miku-prompt-lint-skills/skills/igapyon-miku-prompt-lint
Agent Skill for reviewing prompts, context packages, and Agent Skill bundles for structure, clarity, and practical quality risks.
npx -y skills add igapyon/miku-prompt-lint-skills --skill igapyon-miku-prompt-lintAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 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
Use only when the user explicitly names miku-prompt-lint or igapyon-miku-prompt-lint, or asks to lint, audit, or diagnose an LLM prompt, AI-agent context package, Agent Skill, or supplied Agent Skill repository/harness for prompt/context-engineering quality risks. Do not activate for generic code review, document review, prose editing, source-code templates, or generic repository review unless explicitly named. Review the artifact itself; do not infer whether the author was human or generated AI.
SKILL.md
2.0 KB, 337 tokens by cl100k_base, as published. Nobody here has run it
igapyon-miku-prompt-lint
Review Prompt, Context, Agent Skill, and supplied Repository/Harness artifacts. Review the artifact, not its author; do not request private reasoning.
Workflow
- If index.json exists, read it for discovery; otherwise continue without creating one.
- Read review-levels.md and identify only supplied Levels.
- Read each selected
checkpoints.mdandanti-patterns.mdbefore emitting a Rule ID or formal finding. - Read output-format.md and the report template before reporting.
- Use the most specific owning Level once. Mark absent prerequisites
Not assessed. - Read rule-migrations.json only to interpret historical Rule IDs.
- Read prompt rewrite patterns only when revised prompt material is useful.
For a follow-up single prompt skeleton, use the template-selection workflow; keep unknown values as TODO:.