claude-md-generator

Gera CLAUDE.md inteligente para projetos consumidores. Consome output do Repo Auditor, faz entrevista guiada com o dev e produz um CLAUDE.md especifico, conciso e acionavel. Use apos o Repo Auditor (18) ter mapeado o repositorio. Trigger em: "gerar claude.md", "criar claude.md", "onboarding", "setup claude md", "contexto do projeto", "documentar projeto para agente".

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/28-claude-md-generator/SKILL.md

Quality

Content

62%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.

A thorough, well-sequenced multi-phase skill with strong actionability and clear governance hooks. It loses points on conciseness due to two large inline tables, and on progressive disclosure because referenced template/policy files are not part of the skill bundle.

Suggestions

Move the large 'Secoes do CLAUDE.md' and 'Padroes de Pergunta por Secao' tables into a references/ file and keep a concise summary inline.

Bundle templates/claude-md-output.md under references/ or assets/ so the 'usar como base' reference resolves within the skill, or inline a minimal template stub.

Add an explicit validate->fix->retry loop for the audit-mode patch application step since it is a batch operation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but the two large per-section classification tables (Fase 2 padroes de pergunta, secoes do CLAUDE.md) and repeated guidance add bulk that could be tightened or moved to a reference.	3 / 5
Actionability	Concrete and executable throughout — specific detection rules (idade < 30d, --mode flags), a real audit-report template, and explicit section/classification logic — with only minor gaps such as no copy-paste example of a generated CLAUDE.md section.	4 / 5
Workflow Clarity	Clear five-phase sequence with checkpoints (draft review/approval before write, diff-and-confirm before overwrite), and an audit checklist; the destructive overwrite is gated, though no explicit validate->fix->retry loop for batch audit fixes.	4 / 5
Progressive Disclosure	Good section organization, but the body references templates/claude-md-output.md and several policies/*.md files while no bundle directories (references/scripts/assets) exist in the skill folder, so those references are unsignaled/external and the large inline tables arguably belong in separate files.	3 / 5
	Total	14 / 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 strong description: third-person, concise, with explicit what/when and a list of concrete trigger phrases. The main gaps are minor — a few missing natural synonyms and slightly less than comprehensive action coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (CLAUDE.md generation) and several concrete actions — consumes Repo Auditor output, runs a guided dev interview, produces a specific/concise/actionable file — but coverage of actions is solid rather than exhaustive.	4 / 5
Completeness	Explicitly answers 'what' (generates a specific, concise, actionable CLAUDE.md from audit + interview) and 'when' (Use apos o Repo Auditor; Trigger em: ...), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists six explicit trigger phrases users would naturally say ('gerar claude.md', 'onboarding', 'contexto do projeto'), good coverage though a couple of natural synonyms and an English variant are missing.	4 / 5
Distinctiveness Conflict Risk	The Repo Auditor dependency and CLAUDE.md-generation niche make it mostly distinct, with only minor overlap risk against a generic onboarding/documentation skill.	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
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	14 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/28-claude-md-generator/SKILL.md
Commit: f3492ef

Reviewed: 5 days 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.