repo-auditor

Skill de auditoria inicial e continua do repositorio. Use quando precisar mapear stack real, convencoes, assets, testes, docs, riscos e pontos de integracao antes de executar outras skills. O resultado deve ser persistido em markdown reutilizavel para reduzir releitura e economizar tokens. Trigger em: "repo audit", "auditar repositorio", "mapear stack do projeto", "harnessability score", "repo-audit", "auditoria de repo", "fotografia do repo", "current.md", "mapear convencoes do projeto", "inventariar o codebase".

Quality

79%

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 ./skills/18-repo-auditor/SKILL.md

Quality

Content

66%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, dense, and actionable with strong progressive disclosure, but the audit workflow lacks explicit validation checkpoints and feedback loops for its batch split-generation and persistence steps, which the rubric caps at 3 for workflow clarity.

Suggestions

Add an explicit validation step to the audit workflow (e.g., 'After generating splits, verify each split against the source via git diff and re-run only on changed files') to lift workflow_clarity above 3.

Include a concrete execute-and-verify loop for split generation (validate → fix → re-generate) since it is a batch operation, satisfying the feedback-loop cap.

Provide the referenced templates/audit.md and docs/skill-guides/repo-auditor.md as bundle files so the signaled one-level-deep references actually resolve.

Dimension	Reasoning	Score
Conciseness	The body is dense and token-efficient — compact tables for harnessability signals, split catalog, and detection rules, assuming Claude's competence — but a few prose passages (the 'modelo conceitual' caveat and ambient-affordances narrative) could be trimmed, so it sits at 'efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	It gives concrete, mostly-executable guidance — explicit detection patterns ('tsconfig.json com strict:true', 'grep TODO/FIXME'), an output-format markdown template, and split-generation rules — with only minor gaps (no literal copy-paste commands for the audit itself), matching the 'mostly executable guidance' anchor.	4 / 5
Workflow Clarity	Sections are well sequenced (audit → harnessability → splits → handoff) but the core audit lacks an explicit validate/verification checkpoint before persisting output, and batch split generation has no feedback loop, so per the rubric's feedback-loop cap it cannot exceed 3.	3 / 5
Progressive Disclosure	Structure is good: overview in SKILL.md with one-level-deep, clearly signaled references ('Usar templates/audit.md como base', 'consultar docs/skill-guides/repo-auditor.md apenas quando necessario') and a split catalog; minor gaps because the referenced templates/guides are not present as bundle files and navigation relies on external paths.	4 / 5
	Total	15 / 20 Passed

Description

92%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 is strong: it states concrete capabilities, supplies an explicit multi-phrase trigger list, and carves a distinct niche with low conflict risk. The only soft spot is that the action list, while specific, could enumerate a few more concrete outputs to reach fully comprehensive specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (repo auditing) and lists several concrete actions — 'mapear stack real, convencoes, assets, testes, docs, riscos e pontos de integracao' plus 'harnessability score' — with only minor coverage gaps, matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	It clearly answers 'what' (initial and continuous repo audit persisted to reusable markdown) and 'when' via the explicit 'Trigger em:' list with concrete trigger phrases, matching the anchor that requires both what AND when.	5 / 5
Trigger Term Quality	The explicit 'Trigger em:' clause covers ten natural phrases a user would actually say — 'repo audit', 'auditar repositorio', 'mapear stack do projeto', 'fotografia do repo', 'current.md' — including synonyms and a concrete filename, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (operational repository audit / harnessability scoring) with distinct triggers unlikely to fire for adjacent skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	19 / 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/18-repo-auditor/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.