CtrlK
BlogDocsLog inGet started
Tessl Logo

ccg

Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes results

53

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ccg/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and actionable with concrete commands and a clear multi-step workflow, plus sensible fallbacks. Its main weakness is redundancy between the 'How It Works' and 'Execution Protocol' sections.

Suggestions

Merge the 'How It Works' numbered summary with the 'Execution Protocol' to remove the duplicated omc ask commands and the repeated 'skill nesting not supported' note.

Add an explicit verification checkpoint in Step 3 (e.g., confirm at least one artifact matched the glob before synthesizing).

Include one concrete example of a decomposed codex vs. antigravity prompt pair to make the Decompose step copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient, but the 'How It Works' text block and 'Execution Protocol' section repeat the same omc ask commands, and 'skill nesting not supported' is stated twice, which is unnecessary padding.

3 / 5

Actionability

Provides concrete executable commands (omc ask codex/antigravity/gemini), install instructions, and artifact glob paths; only minor gaps (e.g., no example decomposed prompts) keep it from 5.

4 / 5

Workflow Clarity

Clear four-step sequence (Decompose, Invoke, Collect, Synthesize) with fallback handling, but lacks an explicit checkpoint verifying artifacts exist before synthesis.

4 / 5

Progressive Disclosure

Well-organized sections with clear headers and no nested external references; the content is cohesive enough to stay inline, with only minor organization redundancy keeping it from 5.

4 / 5

Total

15

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 concretely states what the skill does but omits an explicit 'when to use' trigger, so completeness is capped. It is distinct and reasonably specific but relies on command jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause stating natural trigger phrases (e.g., 'Use when you want Codex and Antigravity/Gemini perspectives on a single task').

Include natural-language synonyms a user might say (e.g., 'cross-model review', 'multi-model second opinion') alongside the CLI commands.

Expand the action list slightly (decompose, dispatch, synthesize) to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain (tri-model orchestration) and two concrete actions ('/ask codex + /ask antigravity' routing and 'Claude synthesizes results'), but the action list is not comprehensive enough for a 4.

3 / 5

Completeness

It has a clear 'what' (route to two advisors and synthesize) but no explicit 'Use when...' trigger clause, which caps completeness at 3 per the guidelines.

3 / 5

Trigger Term Quality

Includes relevant command keywords ('/ask codex', '/ask antigravity', 'gemini') but leans on technical jargon rather than natural phrases a user would say, and lacks synonyms.

3 / 5

Distinctiveness Conflict Risk

The '/ask codex + /ask antigravity' routing carves a distinct niche with minimal overlap risk; only minor confusion with generic /ask skills keeps it below 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Yeachan-Heo/oh-my-claudecode
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.