CtrlK
BlogDocsLog inGet started
Tessl Logo

skills-search

This skill should be used when users want to search, discover, install, or manage Claude Code skills from the CCPM registry. Triggers include requests like "find skills for PDF", "search for code review skills", "install cloudflare-troubleshooting", "list my installed skills", "what does skill-creator do", or any mention of finding/installing/managing Claude Code skills or plugins.

86

2.52x
Quality

83%

Does it follow best practices?

Impact

86%

2.52x

Average score across 6 eval scenarios

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

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-constructed description with strong trigger term coverage and clear 'when to use' guidance. Its main weakness is that the capability verbs (search, discover, install, manage) are somewhat generic and could benefit from more specific concrete actions. The description effectively carves out a distinct niche around CCPM registry operations.

Suggestions

Add more specific concrete actions beyond generic verbs, e.g., 'browse skill metadata and ratings', 'resolve skill dependencies', 'check for skill updates', 'view skill documentation' to improve specificity.

DimensionReasoningScore

Specificity

The description names the domain (CCPM registry) and lists actions (search, discover, install, manage), but these are somewhat generic verbs. It doesn't detail specific concrete capabilities like 'browse skill metadata', 'resolve dependencies', or 'update installed skills'.

2 / 3

Completeness

Clearly answers both 'what' (search, discover, install, manage skills from CCPM registry) and 'when' (explicit trigger examples and a 'Use when' equivalent opening clause). The description opens with 'This skill should be used when...' which serves as explicit trigger guidance.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms: 'find skills for PDF', 'search for code review skills', 'install cloudflare-troubleshooting', 'list my installed skills', 'what does skill-creator do', plus general mentions of 'finding/installing/managing Claude Code skills or plugins'. These are phrases users would naturally say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — the CCPM registry is a specific niche, and the triggers are clearly scoped to skill management operations. Unlikely to conflict with other skills since it targets a unique domain (Claude Code skill/plugin management).

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 that clearly maps user intents to executable commands with good error handling and workflow sequencing. Its main weaknesses are moderate verbosity (the MCP server section and some explanatory text could be trimmed) and the monolithic structure that could benefit from splitting reference material into separate files. Overall it serves its purpose effectively as a behavioral directive for managing skills via ccpm.

Suggestions

Remove or significantly trim the MCP Server Alternative section — it's tangential to the skill's core purpose and adds tokens without aiding Claude's primary task.

Consider extracting the full Command Reference into a separate COMMANDS.md file and keeping only the intent mapping table in the main skill body.

DimensionReasoningScore

Conciseness

Generally efficient with good use of tables and structured sections, but includes some unnecessary content like the MCP server section and explanatory text that could be trimmed. The 'Both this skill and the MCP server wrap the same ccpm CLI' explanation is unnecessary context for Claude.

2 / 3

Actionability

Highly actionable with concrete, executable bash commands for every intent. The intent mapping table provides clear command-to-action mappings, and the command reference includes real flags and options. The bootstrap check is copy-paste ready.

3 / 3

Workflow Clarity

Clear sequencing: bootstrap first, then match intent, then execute, then summarize and suggest next steps. The execution rules provide explicit behavioral directives (always execute directly, handle errors with fallback to npx, post-install reminder). Error recovery paths are well-defined in the troubleshooting section.

3 / 3

Progressive Disclosure

Content is well-organized with clear sections and headers, but everything is in a single monolithic file with no bundle files for reference. The command reference section and MCP server configuration could be split into separate reference files to keep the main skill leaner.

2 / 3

Total

10

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
fernandezbaptiste/claude-code-skills
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.