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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/public/find-skills/SKILL.md

Quality

Content

71%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 well-structured, actionable guide: the find → present → install workflow is sequenced clearly with real commands, sample output, and fallback handling, and the single bundled script it references actually exists. Its weakness is token efficiency — the duplicated trigger section, full response template, and categories table could be trimmed without losing guidance value.

Suggestions

Cut or drastically shorten the 'When to Use This Skill' section — it repeats the frontmatter description's trigger list verbatim in spirit and consumes context the model already has from frontmatter loading.

Replace the multi-line example response template with a one-line note of what to include (name, install command, skills.sh link) and trim the categories table to a single sentence of example query keywords.

Add a one-line post-install verification step (e.g., confirm the skill appears in `skills/custom/`) to close the workflow's only validation gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — commands are shown tersely and there is no concept-explanation filler — but it could be tightened: the 'When to Use This Skill' section largely duplicates the frontmatter description's trigger list, and the full example-response template and the seven-row categories table pad the token budget. Fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4, where only minor trims would be needed.	3 / 5
Actionability	Gives concrete, executable commands (`npx skills find [query]`, `bash /path/to/skill/scripts/install-skill.sh vercel-labs/agent-skills@vercel-react-best-practices`) with realistic sample output and a concrete no-results fallback (`npx skills init`). Held below 5 because the install commands embed a literal `/path/to/skill/` placeholder that is not copy-paste ready as written — a minor gap, matching the 'mostly executable guidance' anchor.	4 / 5
Workflow Clarity	A clear four-step sequence (understand the need → search → present options → install) plus an explicit no-results fallback path with an example. Missing a post-install verification checkpoint (e.g., confirming the skill landed in skills/custom/ and is linked), which matches 'clear sequence with most checkpoints present; minor validation gaps'. Install is not a destructive or batch operation, so the workflow-clarity cap does not apply.	4 / 5
Progressive Disclosure	A single well-sectioned SKILL.md with clear headers and one referenced bundle artifact (`scripts/install-skill.sh`), which exists in the bundle one level deep. No content here warrants splitting into separate reference files, and navigation is trivial — matching the top anchor for a self-contained, well-organized skill.	5 / 5
	Total	16 / 20 Passed

Description

75%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: explicit third-person what-and-when structure with genuinely natural quoted trigger phrases. Its main weaknesses are modest action coverage beyond 'discover and install' and overly broad triggers like 'how do I do X' that create overlap risk with general task-assistance skills.

Suggestions

Enumerate one or two more concrete capabilities (e.g., 'browse the skills.sh registry and install skills into the project') to lift specificity from naming the domain toward comprehensive action coverage.

Narrow the broadest trigger — 'how do I do X' — to contexts where an installable skill is plausibly the answer (e.g., 'when the user asks how to do X and would benefit from a packaged skill or workflow') to reduce conflict risk with general task-assistance behavior.

Dimension	Reasoning	Score
Specificity	Names the domain ("agent skills" ecosystem) and two concrete actions ("discover and install agent skills") but offers no broader coverage of what the skill actually does. It fits the 'names domain and 1-2 concrete actions, but not comprehensive' anchor — not 4, since no further specific actions are enumerated; not 2, since 'discover and install' are concrete rather than generic. Third person voice is used, so no voice penalty applies.	3 / 5
Completeness	Explicitly answers both: what ("Helps users discover and install agent skills") and when ("This skill should be used when the user is looking for functionality that might exist as an installable skill"), with concrete quoted trigger phrases — a clear match to the top anchor.	5 / 5
Trigger Term Quality	Quotes natural phrases users would actually say ("how do I do X", "find a skill for X", "is there a skill that can...") plus "express interest in extending capabilities". Good coverage but a few natural variations (e.g., "can you do X") are missing, matching the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	"How do I do X" is a trigger for virtually any how-to question, so this description risks firing on general task questions where direct help (not a skill) is wanted. It is somewhat specific to the skills-install niche but could overlap with task-execution skills, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bytedance/deer-flow
Path: skills/public/find-skills/SKILL.md
Commit: ee44d1e

Reviewed: 18 hours 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.