Content
81%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body delivers an exceptionally actionable, well-sequenced workflow with explicit quality-verification and install-intent checkpoints and concrete tool-call examples throughout. Its only real weakness is redundancy: the anti-npx/git warning is stated three times and a tips section covers search basics Claude already knows.
Suggestions
State the "do not run npx skills add / git clone" rule once (in the tools section) and cut its two repetitions in Step 6, keeping only the unique detail about installing exactly one skill deterministically.
Delete or merge the "Tips for Effective Searches" section — advice like "use specific keywords" and "try alternative terms" assumes Claude lacks basic search judgment.
Consider moving the Common Skill Categories table into a reference file if the skill grows, keeping SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient step-by-step guidance, but the prohibition on shelling out to "npx skills"/"git" is repeated three times (tools intro and twice in Step 6), and the "Tips for Effective Searches" section explains basic search strategy Claude already knows. This matches anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened") better than anchor 4's "minor instances". | 3 / 5 |
Actionability | Guidance is fully executable: exact tool calls with literal arguments (search_skills("react performance"), install_skill("claude-plugins:vercel-labs/agent-skills/skills/react-best-practices")), numeric quality thresholds (1K+ installs, <100 stars skepticism), and copy-paste-ready response templates covering common cases plus the no-results fallback. | 5 / 5 |
Workflow Clarity | The six steps are clearly sequenced with explicit checkpoints: Step 4 verifies quality before recommending, and Step 6 gates installation on expressed user intent ("A search-only request must not mutate the skill library"). No destructive or batch operation is involved, so the validation cap does not apply; this matches anchor 5's "clear sequence with explicit validation steps". | 5 / 5 |
Progressive Disclosure | This is a single-file skill (no references/, scripts/, or assets/ exist) with well-organized headers and a category table kept inline. At ~155 lines it exceeds the under-50-line simple-skill exception, and supplementary content like the category table and search tips remain inline, matching anchor 4 ("good structure; most content is appropriately placed; minor organization gaps") rather than anchor 5's appropriately-split profile. | 4 / 5 |
Total | 17 / 20 Passed |