find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced workflow skill with concrete tool calls, quality gates, and a security-aware install path. Its main gaps are mild repetition of the shell-out warning, no error-recovery guidance for failed searches or installs, and inlined reference-style content that could be split out.

Suggestions

Add an error-recovery branch for install failures or empty search results (e.g. retry with broader keywords, suggest the skills.sh browse fallback) to close the workflow feedback loop.

State the 'do not shell out to npx skills / git' rule once and reference it from Step 6 rather than repeating the full rationale twice.

Move the Common Skill Categories table and the sample response templates into a reference file (e.g. references/examples.md) to slim the main SKILL.md body.

Dimension	Reasoning	Score
Conciseness	The body is efficient and does not explain concepts Claude already knows, but the 'do NOT shell out to npx skills, git, or any package manager' warning is repeated in both 'The skill tools' and Step 6, and the example response blocks run long. This matches anchor 4 (minor trimmable over-explanation) rather than 3 (no real padding) or 5 (every token earns its place).	4 / 5
Actionability	Guidance is fully executable: copy-ready tool calls like search_skills("react performance") and install_skill("claude-plugins:vercel-labs/agent-skills/skills/react-best-practices"), concrete quality thresholds (prefer 1K+ installs, skeptical below 100 stars), and a covered no-results fallback path with example response text.	5 / 5
Workflow Clarity	The six steps are clearly sequenced with real checkpoints (Step 4 quality verification, Step 6 security warning, review link, and explicit install-intent gate). It falls short of anchor 5 only because there is no error-recovery feedback loop, e.g. what to do when a search returns nothing relevant or an install fails.	4 / 5
Progressive Disclosure	The single file is well-organized with clear section headers and no buried references (no bundle files exist), but at ~150 lines the Common Skill Categories table, search tips, and example responses are inlined content that could live in a reference file. The skill exceeds the under-50-line simple-skill exception, so anchor 5 does not apply; structure is solid, matching anchor 4.	4 / 5
	Total	17 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit what/when structure and natural trigger phrases. Its main weaknesses are limited action coverage (only discover and install) and an overly broad 'how do I do X' trigger that risks false positives on generic how-to questions.

Suggestions

Add one or two more concrete actions to the description (e.g., 'search the skills marketplace and evaluate skill quality') to lift specificity beyond two actions.

Narrow the 'how do I do X' trigger to skill-seeking contexts, e.g. "how do I do X" when looking for reusable tooling, to reduce false-positive triggering on ordinary how-to questions.

Include a synonym trigger such as 'install a skill', 'browse skills', or 'skill marketplace' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('agent skills') and exactly two concrete actions ('discover and install'), matching the 1-2-concrete-actions anchor rather than the several-actions anchor at 4. It uses proper third-person voice ('Helps users'), so no voice penalty applies.	3 / 5
Completeness	It explicitly answers both what ('discover and install agent skills') and when, with a direct 'This skill should be used when...' clause plus concrete quoted trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ('how do I do X', 'find a skill for X', 'is there a skill that can...', 'extending capabilities'), but common variants like 'can you do X', 'install a skill for me', or 'skill marketplace' are missing, placing it just below the comprehensive anchor of 5.	4 / 5
Distinctiveness Conflict Risk	The skill discovery/installation niche is distinct from related skills like skill-creation, but the trigger 'how do I do X' is broad enough to fire on ordinary how-to questions rather than skill-seeking, leaving minor overlap risk rather than minimal.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: CherryHQ/cherry-studio
Path: resources/skills/find-skills/SKILL.md
Commit: 113ef7e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.