From software-design
Use when reviewing or improving Claude Code, Codex, or compatible agent skills. Checks SKILL.md frontmatter, trigger boundary, progressive disclosure, no-op instructions, duplication, sediment, sprawl, examples, and validation readiness. Trigger for skill review, SKILL.md review, skill quality check, trigger debugging, or improving an existing skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/software-design:j5ik2o-reviewing-skillsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review skills for predictable agent behavior, not just readability.
Review skills for predictable agent behavior, not just readability.
Identify the target skill directory and read SKILL.md completely.
Read references/best-practices.md before producing findings.
Check frontmatter name and description for trigger precision and exclusions.
Check the body for clear steps, completion criteria, progressive disclosure, duplication, no-ops, sediment, and sprawl.
Inspect bundled references, scripts, assets, and evals when present.
Return prioritized findings before optional rewrites.
Use: Critical, Warning, Info, and Suggested rewrite when a concrete replacement is useful.
For non-trivial implementation, review, or refactoring work, read references/details.md before giving final guidance. It contains the detailed rules, examples, smells, and migration notes that do not belong in the short invocation body.
Lead with actionable findings and file references. If asked to fix, make the smallest changes that improve invocation, execution, and validation.
npx claudepluginhub j5ik2o/ai-tools --plugin software-designAudits Claude Code skills for structure compliance, description quality, workflow design, token efficiency, and anti-patterns.
Reviews and improves Claude Code skills against official best practices. Supports self-review, external review, and auto-PR modes.
Audits Claude Code skills for structure compliance, triggering accuracy, instruction quality, and best practices. Scores 0-100 with prioritized improvement recommendations.