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

58%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/sdlc/skills/find-skills/SKILL.md

Quality

Content

56%Scale 1-5

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

This skill provides a functional guide for discovering and installing agent skills with clear CLI commands and a logical workflow. Its main weakness is verbosity — it over-explains concepts Claude already understands (what a CLI is, how to use specific keywords in searches, what categories exist) and includes sections like the tips and categories table that add marginal value while consuming significant token budget. The actionability is solid but undermined by verification steps that aren't practically executable.

Suggestions

Cut the 'What is the Skills CLI?' explanatory paragraph and the 'Tips for Effective Searches' section — Claude already knows how to formulate search queries and doesn't need to be told what a package manager is.

Remove or drastically condense the 'Common Skill Categories' table — Claude can infer appropriate search terms from user requests without a lookup table.

Make the quality verification step (Step 4) actionable by specifying how to check install counts from CLI output, or remove criteria that can't be verified programmatically.

Trim the 'When to Use This Skill' section to 2-3 key triggers instead of 6 bullet points that largely overlap.

Dimension	Reasoning	Score
Conciseness	The skill over-explains many concepts Claude already knows. The 'What is the Skills CLI?' section explains what a package manager is, the 'When to Use This Skill' section lists obvious trigger phrases at length, and the common categories table adds little value since Claude can infer search terms. The tips section ('Use specific keywords') is patronizing for Claude's intelligence level.	2 / 5
Actionability	The skill provides concrete CLI commands (npx skills find, npx skills add) with specific flags (-g, -y) and realistic examples. However, the quality verification steps (Step 4) are somewhat vague — there's no way for Claude to programmatically check install counts or GitHub stars from the CLI output, making those instructions aspirational rather than executable.	4 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced and logically ordered (understand → check leaderboard → search → verify → present → install). However, there are no explicit validation checkpoints or error handling between steps — e.g., what if `npx skills find` fails, returns no results mid-flow, or the install command errors out. The fallback for 'no skills found' is covered but not integrated into the main flow as a branch.	4 / 5
Progressive Disclosure	All content is inlined in a single file with no references to supporting documents, which is borderline acceptable for a skill of this size (~120 lines). However, the common categories table and tips section could be separated or omitted. The skill references external URLs (skills.sh) appropriately but doesn't leverage any bundle structure for organizing supplementary content.	3 / 5
	Total	13 / 20 Passed

Description

61%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.

The description has decent trigger term coverage with natural user phrasings and addresses both 'what' and 'when', but the specificity of capabilities is weak — it only says 'discover and install' without detailing the mechanism. The biggest weakness is the overly broad 'when' clause ('looking for functionality that might exist as an installable skill'), which could cause this skill to compete with many other skills for selection.

Suggestions

Add more specific actions like 'Searches a skill registry, lists available skills with descriptions, and installs selected skills' to improve specificity.

Narrow the 'when' clause to reduce conflict risk — instead of 'looking for functionality that might exist as an installable skill', specify that it should only trigger when the user explicitly asks about skills, plugins, or extensions rather than simply asking how to do something.

Include synonyms like 'plugin', 'extension', 'add-on', 'browse skills', 'skill store' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('discover and install agent skills') but the actions are generic — 'discover' and 'install' are the only concrete verbs, with no detail about how discovery works (e.g., searching a registry, listing available skills, showing descriptions).	2 / 5
Completeness	Both 'what' (discover and install agent skills) and 'when' (when users ask questions like 'how do I do X', 'find a skill', or want to extend capabilities) are present. The 'when' is reasonably explicit with example trigger phrases, though the 'what' could be more detailed about the actual actions performed.	4 / 5
Trigger Term Quality	Includes several natural trigger phrases like 'how do I do X', 'find a skill for X', 'is there a skill that can...', and 'extending capabilities'. These are realistic user phrasings, though it could include more synonyms like 'plugin', 'extension', 'add-on', or 'browse skills'.	4 / 5
Distinctiveness Conflict Risk	The phrase 'when the user is looking for functionality that might exist as an installable skill' is extremely broad and could trigger for almost any request where the user asks how to do something, creating high overlap risk with actual task-performing skills.	3 / 5
	Total	13 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: whimzyLive/nightshift-ai
Path: plugins/sdlc/skills/find-skills/SKILL.md
Commit: 7741177

Reviewed: 2 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.