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.
86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%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 well-crafted description that excels at trigger term quality and completeness, providing clear guidance on when Claude should select this skill. The main weakness is that the specific capabilities could be more concrete - it says 'discover and install' but doesn't detail what discovery entails (searching, browsing, filtering, etc.).
Suggestions
Add more specific actions like 'search skill repositories', 'browse available skills', 'compare skill features', or 'configure installed skills' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill discovery/installation) and some actions ('discover and install agent skills'), but lacks comprehensive concrete actions like searching, browsing, comparing, or configuring skills. | 2 / 3 |
Completeness | Clearly answers both what ('discover and install agent skills') and when ('when they ask questions like...', 'when the user is looking for functionality that might exist as an installable skill'). Explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes natural phrases users would say: 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'extending capabilities'. Good coverage of discovery-related language. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on skill discovery and installation. The trigger phrases are distinct meta-level queries about capabilities rather than task execution, making conflicts unlikely. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear workflow guidance and executable commands. The main weakness is verbosity - it over-explains the Skills CLI concept and includes reference material (categories table, tips) that could be trimmed or externalized. The step-by-step workflow is well-structured with good error handling for the 'no skills found' case.
Suggestions
Remove or significantly trim the 'What is the Skills CLI?' section - Claude can infer this from the commands themselves
Move the 'Common Skill Categories' table to a separate reference file or remove it entirely, as Claude can generate appropriate search terms
Condense the 'Tips for Effective Searches' into the main workflow or remove - these are intuitive search behaviors
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'What is the Skills CLI?' section explains concepts Claude could infer). The common categories table and tips section add bulk that could be trimmed, though the core workflow guidance is reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable commands throughout (npx skills find, npx skills add with flags), concrete examples of queries mapped to user requests, and copy-paste ready install commands with clear flag explanations. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow (Understand → Search → Present → Install) with explicit guidance at each stage. Includes handling for the 'no results' case, providing a complete decision tree for the skill discovery process. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. The common categories table and tips could be separate reference material. No external file references are used despite the skill being moderately long (~120 lines). | 2 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.