ccg
Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ccg/SKILL.mdQuality
Discovery
40%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 unique multi-model orchestration capability but fails to explain when it should be used or what user problems it solves. The technical mechanism is stated but lacks context about use cases, and there's no explicit trigger guidance to help Claude select this skill appropriately.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios like 'when user wants multiple AI perspectives', 'comparing model outputs', or 'needs consensus from different models'
Expand on concrete actions this orchestration enables, such as 'cross-validates answers', 'combines strengths of multiple models', or 'resolves conflicting interpretations'
Include natural user phrases like 'ask multiple models', 'get a second opinion', 'compare AI responses' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (tri-model orchestration) and describes the mechanism (/ask codex + /ask gemini, Claude synthesizes), but lacks detail on what specific tasks this orchestration accomplishes or what problems it solves. | 2 / 3 |
Completeness | Describes what (tri-model orchestration with synthesis) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'codex', 'gemini', and 'orchestration', but missing natural user phrases. Users might say 'compare models', 'get multiple opinions', or 'multi-model' which aren't present. | 2 / 3 |
Distinctiveness Conflict Risk | The specific combination of Claude-Codex-Gemini with the /ask command syntax creates a clear, unique niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 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 orchestration skill with strong actionability and clear workflow sequencing. The main weakness is mild redundancy between the 'How It Works' overview and the detailed 'Execution Protocol' section - one could be eliminated. The fallback handling is a notable strength for robustness.
Suggestions
Remove or significantly condense the 'How It Works' section since it duplicates the 'Execution Protocol' content
Consider moving detailed fallback logic to a separate FALLBACKS.md if the skill grows more complex
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is mostly efficient but includes some unnecessary explanation like the 'How It Works' section that largely duplicates the 'Execution Protocol' section. The 'When to Use' bullets could be tighter. | 2 / 3 |
Actionability | Provides concrete CLI commands, specific file paths for artifacts, clear decomposition categories, and explicit synthesis output format. The execution protocol is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence with explicit phases (decompose → invoke → collect → synthesize). Includes fallback handling for partial/total failure scenarios, which serves as validation/error recovery. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. For a skill of this complexity, the execution protocol details or fallback logic could be split into referenced files. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
48ffaac
- 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.