CtrlK
BlogDocsLog inGet started
Tessl Logo

find-skills

Helps users discover and install agent skills. Use when the user asks questions like "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending capabilities — i.e. whenever they're looking for functionality that might exist as an installable skill.

67

Quality

80%

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

75%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, highly actionable skill body with concrete commands and a clear multi-step workflow that includes a quality-verification gate. Its main weakness is moderate verbosity from concept explanation and full scripted response templates.

Suggestions

Trim the "What is the Skills CLI?" concept explanation and condensed scripted example responses, since Claude already understands package managers and can compose recommendation messages from the command examples.

Add an explicit validate-then-act feedback loop (e.g., if a found skill fails the quality checks, re-search with refined terms before recommending) to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

Mostly command-oriented but includes concept explanation ("What is the Skills CLI?", what skills are) and full scripted example-response templates that pad length beyond minor trimming.

3 / 5

Actionability

Provides copy-paste-ready commands (find, add, add -g -y) with concrete example-to-command mappings covering common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

A clear 6-step sequence with an explicit validation gate in Step 4 (install count, source reputation, GitHub stars), but lacks an explicit validate-fix-retry feedback loop, capping it below 5.

4 / 5

Progressive Disclosure

Well-organized into clean sections with no nested or buried references and no bundle files needed, though the single-file body is somewhat long with dense scripted responses that keep it just below the lean-overview 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

86%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 that pairs a clear capability statement with explicit, natural trigger phrases. The main weakness is modest action specificity and a slightly broad "how do I do X" trigger that risks overlap with general-purpose skills.

Suggestions

Expand the capability verbs beyond "discover and install" (e.g., "browse, search, evaluate, and install") to lift specificity toward 4-5.

Narrow the generic "how do I do X" trigger or qualify it (e.g., "how do I do X where X might have an existing skill") to reduce overlap with general capabilities.

DimensionReasoningScore

Specificity

Names the skills domain and two concrete actions ("discover and install agent skills") but does not enumerate several specific actions, so it sits at the 3-anchor rather than 4.

3 / 5

Completeness

Explicitly states what the skill does and provides a concrete "Use when..." clause with multiple trigger phrases, matching the canonical 5-anchor pattern.

5 / 5

Trigger Term Quality

Quotes multiple verbatim natural phrases users would say ("how do I do X", "find a skill for X", "is there a skill that can..."), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Distinct skill-hunting triggers ("find a skill for X", "is there a skill that can...") anchor near 5, but the generic "how do I do X" phrasing introduces minor overlap risk, pulling it to 4.

4 / 5

Total

17

/

20

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
joe-bell/cva
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.