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 an explicit 'Use when...' clause, the listed actions are somewhat generic, and the trigger terms are system-specific rather than natural language terms users would say. The description would benefit from more concrete action descriptions and explicit selection guidance.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about CCW commands, needs help finding skills or teams, or mentions ccw-help or ccw-issue.'
Include natural language trigger terms users might say, such as 'what commands are available', 'how to use CCW', 'find a team', 'list skills', in addition to the system-specific triggers.
Expand the concrete actions with more detail, e.g., 'Searches available CCW commands by keyword, browses skill catalogs, recommends relevant teams and workflows.'
| 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 trigger terms listed, but there is no explicit 'Use when...' clause explaining when Claude should select this skill. The triggers are listed but not framed as selection guidance. | 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 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 functions more as a comprehensive reference document than an actionable skill file. It catalogs an impressive system of 50+ commands, 36+ skills, and 22 agents, but the sheer volume of inline reference tables severely undermines conciseness and progressive disclosure. The mode-based structure is reasonable but lacks validation checkpoints and concrete implementation details for each mode's process steps.
Suggestions
Move the Skill Catalog tables (workflow, team, standalone), Workflow Mapping table, and Generated Index Files table into separate reference files (e.g., CATALOG.md, WORKFLOW-MAP.md) and link to them from the main skill body.
Add concrete implementation details for each mode's process—e.g., show the actual jq/JSON query pattern for searching command.json, or the exact output format Claude should produce for search results.
Add validation/error handling steps to Mode 5 (CCW Orchestration): what to do if intent classification is ambiguous, if a workflow step fails, or if command.json is outdated.
Remove the Statistics section and trim the Maintenance section to just the essential update command, moving script details to a separate MAINTENANCE.md file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with extensive tables cataloging every team skill, workflow variant, and index file. Much of this is reference data that belongs in command.json or separate index files rather than inline. The skill catalogs, workflow mapping tables, and maintenance sections bloat the content significantly beyond what's needed for Claude to act. | 1 / 3 |
Actionability | The skill provides concrete slash command examples and trigger keywords, and the workflow mapping table gives clear routing logic. However, the actual processes for each mode are described at a high level ('Query command.json', 'Filter by name') without executable code or specific implementation details for how to perform the queries or present results. | 2 / 3 |
Workflow Clarity | Each mode has a numbered process, and Mode 5 (CCW Orchestration) includes a 5-step sequence with user confirmation. However, there are no validation checkpoints or error recovery steps—e.g., what happens if command.json lookup fails, if the user's intent can't be classified, or if a workflow chain breaks mid-execution. For an orchestration system, missing feedback loops is a significant gap. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of content with massive inline tables that should be in separate reference files. The skill catalogs (workflow, team, standalone), workflow mapping table, generated index files table, and maintenance scripts are all inlined rather than referenced. Only two external references exist (ccw.md and command.json), while the bulk of reference material is dumped directly into the skill body. | 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
227244f
- 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.