skill-finder
This skill should be used when the user asks to "find a skill", "discover plugins", "search for an MCP", "what plugins exist for X", "fill my skill gaps", "improve my setup", or when Claude recognizes it lacks tools for a task. Searches GitHub and marketplaces to suggest installations.
Overall
score
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
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.
This is a strong description with excellent trigger term coverage and clear completeness. The main weakness is that the 'what it does' portion is somewhat thin - it only mentions searching and suggesting installations without detailing other capabilities like comparison, compatibility checking, or installation guidance. The description effectively communicates when to use it but could be more specific about the full range of actions it performs.
Suggestions
Expand the capabilities section to list more specific actions (e.g., 'Searches GitHub and marketplaces, compares options, checks compatibility, and guides installation')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill/plugin discovery) and mentions one concrete action ('Searches GitHub and marketplaces to suggest installations'), but lacks comprehensive detail about what specific actions it performs beyond searching. | 2 / 3 |
Completeness | Clearly answers both what (searches GitHub and marketplaces to suggest installations) and when (explicit trigger phrases plus the contextual trigger 'when Claude recognizes it lacks tools for a task'). Has explicit 'Use when' equivalent at the start. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'find a skill', 'discover plugins', 'search for an MCP', 'what plugins exist for X', 'fill my skill gaps', 'improve my setup'. These are realistic user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on skill/plugin discovery with distinct triggers like 'MCP', 'plugins', 'skill gaps'. Unlikely to conflict with other skills due to the specific domain of finding and installing new capabilities. | 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 well-structured, highly actionable skill for discovering and installing Claude Code plugins. Its strengths are clear workflows, concrete examples, and copy-pasteable commands. However, it's verbose for its purpose—the extensive tables and repeated patterns inflate token cost, and the content could be split across reference files for better progressive disclosure.
Suggestions
Extract the 'Common Gap Categories & Search Terms' tables into a separate SEARCH_TERMS.md reference file to reduce main skill size
Consolidate the three installation guidance sections (appearing in 'Result Presentation Format', 'MCP Result Format', and 'Post-Discovery Actions') into a single canonical section to eliminate redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., multiple similar tables for search terms, repeated installation guidance patterns). Some sections like 'Common Gap Categories & Search Terms' could be condensed, and the extensive tables add bulk without proportional value. | 2 / 3 |
Actionability | Provides concrete, copy-pasteable commands for installation, specific search query templates, exact URL patterns for sources, and detailed examples showing the full workflow from gap detection to installation. The search execution protocol is highly actionable. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit sequencing: Step 1 (analyze current state) → Step 2 (identify gap category) → Step 3 (formulate search) → Execute → Evaluate → Verify → Present. Includes validation checkpoints like 'Verify Compatibility' before recommending and 'NEVER install without user confirmation'. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but it's a monolithic document (~400 lines) that could benefit from splitting detailed reference tables (search terms, MCP servers list) into separate files. The integration reference to 'skill-curator' is good but the document itself is dense. | 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.