ccw-help
CCW command help system. Search, browse, recommend commands, skills, teams. Triggers "ccw-help", "ccw-issue".
52
42%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/ccw-help/SKILL.mdQuality
Discovery
57%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 identifies a clear niche (CCW command help) with distinct trigger terms, reducing conflict risk. However, it lacks a proper 'Use when...' clause, relies on system-specific jargon rather than natural user language, and the listed capabilities (search, browse, recommend) are somewhat terse without enough context about what CCW is or when users would need this skill.
Suggestions
Add an explicit 'Use when...' clause describing the situations that should trigger this skill, e.g., 'Use when the user asks about CCW commands, needs help finding available skills or teams, or mentions ccw-help or ccw-issue.'
Include more natural language trigger terms that users might actually say, such as 'what commands are available', 'help with CCW', 'find a team', or 'list skills'.
Briefly explain what CCW is so the description is self-contained and Claude can better judge relevance, e.g., 'CCW command help system for the internal CLI tool.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CCW command help system) and lists some actions (search, browse, recommend commands, skills, teams), but the actions are somewhat generic and not fully elaborated with concrete details. | 2 / 3 |
Completeness | The 'what' is partially addressed (search, browse, recommend commands/skills/teams), and there are explicit trigger terms listed, but there is no proper 'Use when...' clause explaining the circumstances under which Claude should select this skill. The triggers are listed but not contextualized. | 2 / 3 |
Trigger Term Quality | Includes specific trigger terms 'ccw-help' and 'ccw-issue' which are useful, but these are technical/system-specific terms rather than natural language a user would say. Missing broader natural language variations like 'how do I use ccw', 'what commands are available', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to a specific system (CCW) with distinct trigger terms ('ccw-help', 'ccw-issue'), making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from significant verbosity by inlining extensive catalog data (36+ skills, 50+ commands, workflow mappings) that belongs in referenced files or is already in command.json. The operation modes provide reasonable structure but lack concrete implementation details and validation steps. The content would benefit greatly from aggressive trimming to a concise overview with references to the existing index files.
Suggestions
Remove the inline Skill Catalog tables and Workflow Mapping table — these duplicate command.json content. Replace with brief references like '**Skill catalog**: See [command.json](command.json) skills array, grouped by category in [skills-by-category.json](index/skills-by-category.json)'.
Make Mode processes more actionable: instead of 'Query command.json commands array, Filter by name', provide the actual JSON path or a concrete code/pseudocode snippet showing how to look up and filter commands.
Add validation/error handling to Mode 5 (CCW Orchestration): what happens if auto-routing fails to match a workflow level? Include a fallback step and confirmation checkpoint before execution.
Move the Generated Index Files table and Update Scripts section to a separate MAINTENANCE.md file, keeping only a one-line reference in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with extensive catalog tables, workflow listings, and mode descriptions that largely duplicate what's in command.json. Much of this content (team skill listings, workflow mapping tables, statistics) could be referenced rather than inlined. The skill explains things Claude could derive from the data source itself. | 1 / 3 |
Actionability | The skill provides concrete slash command examples and trigger keywords, but the actual processes for each mode are described abstractly (e.g., 'Query command.json commands array', 'Filter by name, description, category') rather than with executable code or specific implementation steps. The update mechanism section has concrete commands, which helps. | 2 / 3 |
Workflow Clarity | Each mode has numbered steps which provide some sequence, but validation checkpoints are absent. Mode 5 (CCW Command Orchestration) includes a confirmation step but lacks error handling or feedback loops. The auto-routing logic is described via example tables rather than clear decision criteria with fallback handling. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with extensive inline catalogs (team skills table, standalone skills table, workflow mapping table, generated index files table) that should be in separate reference files or in command.json itself. The skill references command.json and ccw.md but then duplicates much of their content inline rather than pointing to them. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- 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.