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.
71
Quality
66%
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/18-repo-auditor/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description effectively communicates its purpose as a repository auditing skill with clear 'when to use' guidance. The main weaknesses are moderate specificity in describing concrete actions and limited trigger term coverage due to Portuguese-only language. The description successfully establishes a distinct niche as a prerequisite skill for other operations.
Suggestions
Replace abstract 'mapear' with more concrete actions like 'identify frameworks', 'catalog dependencies', 'detect testing patterns', 'document API endpoints'
Add English trigger terms alongside Portuguese to improve discoverability: 'codebase audit', 'project analysis', 'tech stack discovery', 'repository mapping'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (repository auditing) and lists several areas to map (stack, conventions, assets, tests, docs, risks, integration points), but actions are somewhat abstract ('mapear') rather than concrete specific operations. | 2 / 3 |
Completeness | Clearly answers both what (audit repository for stack, conventions, assets, tests, docs, risks, integration points) and when ('Use quando precisar mapear... antes de executar outras skills'). Includes explicit 'Use when' clause with clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'auditoria', 'repositorio', 'stack', 'testes', 'docs', but uses Portuguese which limits discoverability. Missing common English variations users might say like 'codebase analysis', 'project structure', 'tech stack'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche as an initial/continuous repository audit skill that runs before other skills. The specific focus on mapping stack, conventions, and persisting results in markdown makes it distinct from general code analysis skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid conceptual framework for repository auditing with good progressive disclosure and clear persistence paths. However, it lacks concrete executable examples, explicit step-by-step workflows with validation checkpoints, and could be more concise by eliminating redundant sections.
Suggestions
Add a concrete example of the audit output format or show the key sections from templates/audit.md inline
Convert 'Responsabilidades' into a numbered workflow with explicit validation steps (e.g., '1. Check existing audit -> 2. If outdated, scan repo -> 3. Validate findings -> 4. Persist')
Consolidate 'Quando Usar/Nao Usar' and 'Quando Reauditar' into a single decision table or flowchart to reduce redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant sections (e.g., 'Quando Usar' and 'Quando Nao Usar' could be condensed, and some responsibilities overlap with outputs). The governance references add overhead without immediate actionable value. | 2 / 3 |
Actionability | Provides clear guidance on what to do and where to persist, but lacks concrete examples of the audit output format, specific commands to run, or executable code snippets. References a template but doesn't show its structure. | 2 / 3 |
Workflow Clarity | The workflow is implicit rather than explicit - responsibilities are listed but not sequenced as numbered steps with validation checkpoints. Missing explicit validation steps before persisting the audit or clear feedback loops for incomplete audits. | 2 / 3 |
Progressive Disclosure | Good structure with clear references to external files (GLOBAL.md, policies, templates, skill-guides) that are one level deep. Content is appropriately split between overview here and detailed guidance in referenced files. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
524725e
Table of Contents
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.