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
83%
Does it follow best practices?
Impact
86%
2.52xAverage score across 6 eval scenarios
Critical
Do not install without reviewing
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 strong description that excels at trigger term coverage and completeness, with explicit 'when to use' guidance and numerous natural-language example triggers. The main weakness is that the capability verbs (search, discover, install, manage) are somewhat high-level and could benefit from more specific concrete actions. The description also uses passive/imperative voice appropriately rather than first or second person.
| Dimension | Reasoning | Score |
|---|---|---|
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 | The description explicitly answers both 'what' (search, discover, install, manage skills from CCPM registry) and 'when' (with a clear 'Triggers include' clause listing specific example requests and general trigger conditions). The opening sentence also serves as a 'Use when' clause. | 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 | The description is clearly scoped to the CCPM registry and skill management, which is a distinct niche. Terms like 'CCPM registry', 'Claude Code skills', and 'install/manage skills' are unlikely to conflict with other skills that handle PDFs, code review, etc. | 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-crafted skill that excels in actionability and workflow clarity — the intent mapping table is particularly effective for guiding Claude's behavior, and the execution rules are explicit and well-ordered. Minor weaknesses include some redundancy (npx fallback mentioned multiple times) and the MCP server section which adds length without being core to the skill's purpose. Overall, it's a strong, practical skill that clearly instructs Claude on how to behave.
Suggestions
Consolidate the npx fallback guidance into a single location (e.g., only in the bootstrap section or a single note) rather than repeating it in Core Behavior, Execution Rules, and Troubleshooting.
Consider moving the MCP Server Alternative section to a separate reference file or making it a brief one-liner, as it's supplementary context rather than core behavioral guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the fallback to `npx @daymade/ccpm` is mentioned in three separate places (Core Behavior, Execution Rules, Troubleshooting). The MCP Server section adds context that may not be essential for the core skill. However, most content earns its place. | 2 / 3 |
Actionability | Highly actionable with concrete, executable commands throughout. The intent mapping table directly maps user phrases to specific CLI commands, the command reference provides complete syntax with flags, and the bootstrap check is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear sequencing: bootstrap first, then intent mapping, then execution rules with explicit behavioral directives (always execute directly, summarize, suggest next steps, handle errors). The numbered execution rules provide a clear workflow for every interaction. Error recovery paths are specified in troubleshooting. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and headers, but everything is in a single file. The command reference section and MCP server configuration could potentially be split out. However, the skill is borderline in length where a single file is reasonable, and sections are clearly delineated. | 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
80e94fd
Table of Contents
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.