CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The skill is highly actionable with concrete commands and a clean section structure pointing to a real helper script. Its main gaps are conciseness (redundant trigger list and padded example blocks) and the absence of an explicit post-install verification step in the workflow.

Suggestions

Remove or condense the "When to Use This Skill" bullets since the same triggers already appear in the description, and trim the "What is the Skills CLI?" concept intro.

Add an explicit validation checkpoint after Step 4 (e.g., confirm the skill appears under skills/custom/ and is importable before telling the user it succeeded).

Shorten the example response and "When No Skills Are Found" blocks to the essential structure rather than full prose templates.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes tightening opportunities: the "When to Use This Skill" bullet list duplicates the description's triggers, the "What is the Skills CLI?" section explains concepts Claude largely knows, and the example response/fallback blocks are padded.

2 / 3

Actionability

It provides fully executable commands (e.g., `npx skills find react performance`, `bash /path/to/skill/scripts/install-skill.sh <owner/repo@skill-name>`) with concrete query-to-command mappings, fitting the copy-paste-ready level-3 anchor.

3 / 3

Workflow Clarity

The four steps (Understand, Search, Present, Install) are clearly sequenced, but there is no explicit validation/verification checkpoint after the install step, matching the level-2 anchor with missing checkpoints.

2 / 3

Progressive Disclosure

The body is organized into clear headed sections and references the one bundle file (scripts/install-skill.sh) at one level of depth, which exists and is clearly signaled, fitting the well-organized level-3 anchor.

3 / 3

Total

10

/

12

Passed

Description

90%

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

The description is strong: it pairs concrete capabilities with explicit, naturally-worded trigger phrasings and a clear, low-conflict niche. The only weakness is that the action list is brief and slightly abstract rather than enumerating several concrete actions.

Suggestions

Expand the capability clause beyond "discover and install" to enumerate more concrete actions (e.g., "search the skills ecosystem by keyword, present matching skills with install commands, and install them into the project").

Tighten "discover" to a more concrete verb like "search" to reduce abstraction in the specificity dimension.

DimensionReasoningScore

Specificity

"discover and install agent skills" names the domain and two actions, but "discover" is somewhat abstract and the list is not comprehensive, fitting the level-2 anchor rather than a multi-action level-3 example.

2 / 3

Completeness

It answers what ("discover and install agent skills") and provides equivalent explicit trigger guidance ("This skill should be used when the user is looking for functionality that might exist as an installable skill"), so it is not capped at 2.

3 / 3

Trigger Term Quality

It quotes natural phrasings a user would actually say ("how do I do X", "find a skill for X", "is there a skill that can..."), giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

It occupies a clear niche (skill discovery/installation from the skills ecosystem) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
Reviewed

Table of Contents

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.