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.

4.66x

Quality

58%

Does it follow best practices?

Impact

98%

4.66x

Average score across 11 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tiles/vercel-labs/skills/find-skills/skill/SKILL.md

Quality

Content

27%Scale 1-3

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

This skill is overly verbose, explaining many things Claude already knows (how to understand user intent, what search keywords to use, what a package manager is). The core actionable content—the CLI commands and install flags—is solid but buried in excessive scaffolding. The workflow lacks validation steps for installation success/failure and the content would benefit significantly from trimming to focus only on the CLI interface and quality verification heuristics.

Suggestions

Cut the 'When to Use This Skill' section entirely (this belongs in frontmatter/metadata, not body content) and remove the 'What is the Skills CLI?' explanation—just show the commands.

Remove the 'Tips for Effective Searches' and 'Common Skill Categories' sections; Claude already knows how to formulate search queries and these add ~30 lines of low-value content.

Add a validation step after installation: e.g., verify the skill appears in the installed list or check for error output from the install command.

Provide a concrete method for checking install counts and source reputation programmatically rather than vaguely instructing to 'check GitHub stars.'

Dimension	Reasoning	Score
Conciseness	Significantly verbose. Explains what the Skills CLI is (Claude can read help output), describes obvious search strategies, includes a table of common categories that adds little value, and over-explains concepts like 'understand what they need' which Claude inherently does. The 'What is the Skills CLI?' section and 'Tips for Effective Searches' are largely unnecessary padding.	1 / 3
Actionability	Provides concrete CLI commands (npx skills find, npx skills add) and example responses, which is good. However, the quality verification steps (check GitHub stars, install counts) are vague guidance rather than executable steps—there's no command to check install counts or stars programmatically. The 'Verify Quality' section describes what to do but not how to actually retrieve that information.	2 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced and logical, but lacks validation checkpoints. There's no verification that a skill installed correctly, no error handling for failed installs, and no feedback loop for when 'npx skills find' returns unexpected results. The workflow reads more like a guide for a human than precise agent instructions.	2 / 3
Progressive Disclosure	Everything is in a single monolithic file with no references to supporting documents. The common categories table, tips section, and detailed examples could be split out. With no bundle files provided, all content is inline, making this a wall of text at ~120 lines that could be significantly more compact with better structure.	1 / 3
	Total	6 / 12 Passed

Description

89%Scale 1-3

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

This is a solid description that clearly communicates when to use the skill with good trigger phrases and explicit 'when' guidance. Its main weakness is that the 'what' portion could be more specific about the concrete actions it performs (e.g., searching a skill registry, listing available skills, installing/configuring skills). The trigger terms are well-chosen and naturally match how users would phrase requests.

Suggestions

Add more specific concrete actions like 'Searches skill registries, lists available skills, installs and configures new agent capabilities' to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (discovering and installing agent skills) and some actions (discover, install), but doesn't list specific concrete actions like searching a registry, listing available skills, comparing skills, or configuring installed skills.	2 / 3
Completeness	Clearly answers both 'what' (helps users discover and install agent skills) and 'when' (when users ask questions like 'how do I do X', 'find a skill for X', or express interest in extending capabilities). The 'Use when' equivalent is explicitly stated.	3 / 3
Trigger Term Quality	Includes strong natural trigger phrases users would actually say: 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'extending capabilities', 'installable skill'. These cover common variations of how users would express this need.	3 / 3
Distinctiveness Conflict Risk	This skill has a very clear niche — it's specifically about discovering and installing other skills, which is a meta-capability unlikely to conflict with any domain-specific skill. The trigger terms are distinct and focused on skill discovery.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: neil-tessl/skill-index-evals-dev
Path: tiles/vercel-labs/skills/find-skills/skill/SKILL.md
Commit: 2bad92e

Reviewed: 10 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.