Name: multi-ai-skill-builder
Rating: 64 (1 reviews)
Author: fernandezbaptiste

multi-ai-skill-builder

Meta-skill for building Claude Code skills using Multi-AI research, planning, and implementation. Coordinates Claude, Gemini, and Codex for comprehensive research, synthesizes findings, and generates production-ready skills. Use when creating new skills, enhancing existing skills, researching skill domains, or building skill families.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/multi-ai-skill-builder/SKILL.md

The canonical home for this skill is multi-ai-skill-builder in fernandezbaptiste/Skrillz

Quality

Content

70%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 delivers a strong, well-sequenced workflow with explicit validation and feedback loops plus concrete commands, but it is weakened by redundant duplicated sections and by referencing template files that do not exist while also inlining that template content.

Suggestions

Remove the standalone 'Multi-AI Coordination' section or the duplicated research commands, since Step 1 already covers agent assignment and the gemini/codex commands.

Create the referenced templates/SKILL_TEMPLATE.md, REFERENCE_TEMPLATE.md, and SYNTHESIS_TEMPLATE.md files (or drop the references) so the 'See templates/...' pointers resolve to real bundle files.

Move the inlined SKILL.md template from Step 3.2 into templates/SKILL_TEMPLATE.md and replace the inline block with a one-line pointer to reduce body length and duplication.

Dimension	Reasoning	Score
Conciseness	The ~510-line body is mostly efficient with concrete commands and prompts, but the 'Multi-AI Coordination' section repeats the agent-assignment table and research commands already covered in Step 1, and the 'Templates' and 'References' sections list the same three files — content that could be tightened.	3 / 5
Actionability	Provides concrete executable commands (gemini -p, codex, mkdir -p, head -20) and explicit file paths, but many code blocks are prompt templates with [TOPIC]/[SUMMARY]/[skill-name] placeholders that must be filled before use, leaving minor gaps from copy-paste readiness.	4 / 5
Workflow Clarity	A clearly sequenced 5-step workflow (Research → Synthesis → Build → Validation → Refinement) with time estimates, an explicit validation phase (structure check, multi-AI review, Gemini cross-check), feedback loops (Step 5 applies validation feedback), and checklists — matching the anchor-5 example.	5 / 5
Progressive Disclosure	There is section structure and signaled references (Templates/References sections), but the full SKILL.md template is inlined in Step 3.2 rather than kept in the referenced template file, and the referenced templates/SKILL_TEMPLATE.md, REFERENCE_TEMPLATE.md, and SYNTHESIS_TEMPLATE.md files do not actually exist in the bundle.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

A well-constructed description that explicitly pairs a concrete 'what' with an explicit 'Use when' trigger clause and names the coordinating models. It is held below a perfect score mainly by slightly abstract action objects and minor overlap risk with generic skill-builder skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Coordinates Claude, Gemini, and Codex', 'synthesizes findings', 'generates production-ready skills' — but the objects ('findings', 'research', 'skills') stay somewhat abstract compared to the fully tangible anchor-5 example, leaving minor gaps.	4 / 5
Completeness	It clearly answers both 'what' (meta-skill coordinating Multi-AI research/planning/implementation that synthesizes findings and generates production-ready skills) and 'when' (explicit 'Use when...' clause with concrete triggers), matching the anchor-5 example.	5 / 5
Trigger Term Quality	The 'Use when' clause covers four natural scenarios ('creating new skills, enhancing existing skills, researching skill domains, or building skill families') giving good keyword coverage, though it lacks the synonyms/variations that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The Multi-AI coordination niche (Claude + Gemini + Codex for skill building) is mostly distinct with skill-specific triggers, but 'creating new skills' could still overlap with a generic skill-builder skill, a minor overlap risk.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (517 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/multi-ai-skill-builder/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.