CtrlK
BlogDocsLog inGet started
Tessl Logo

documenter

Skill de Documentação por nível de decisão. Use quando precisar documentar features, APIs, arquitetura, setup, operação, ou manter documentação existente atualizada. Trigger em: "documentar", "documentação", "docs", "ADR", "architecture decision record", "README", "feature doc", "api doc", "setup doc", "runbook", "troubleshooting", "doc de operação", "registrar decisão", "atualizar docs".

76

Quality

69%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/10-documenter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

82%

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 is a solid skill description with excellent trigger term coverage and clear completeness (both what and when are addressed). Its main weaknesses are the breadth of scope which could cause overlap with more specialized skills, and the lack of concrete action verbs describing specific operations beyond general documentation. The phrase 'por nível de decisão' in the opening is intriguing but unexplained, which slightly reduces clarity.

Suggestions

Add more specific concrete actions like 'generate ADR templates', 'create API reference docs from code', 'produce runbooks with troubleshooting steps' to increase specificity beyond listing document types.

Clarify what 'por nível de decisão' means in practice — explain how documentation is organized by decision level to make the skill's unique approach more distinctive and reduce overlap risk with other documentation or architecture skills.

DimensionReasoningScore

Specificity

Names the domain (documentation) and lists several types of documentation (features, APIs, architecture, setup, operation, maintaining existing docs), but doesn't describe concrete actions beyond 'documentar' and 'manter atualizada'. It tells us what kinds of docs but not specific operations like 'generate ADR templates', 'create API reference from code', etc.

2 / 3

Completeness

Clearly answers both 'what' (document features, APIs, architecture, setup, operation, maintain existing documentation) and 'when' with an explicit 'Use quando precisar...' clause and a dedicated 'Trigger em:' list of activation keywords.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms in both Portuguese and English abbreviations: 'documentar', 'documentação', 'docs', 'ADR', 'architecture decision record', 'README', 'feature doc', 'api doc', 'setup doc', 'runbook', 'troubleshooting', 'registrar decisão', 'atualizar docs'. These are terms users would naturally use.

3 / 3

Distinctiveness Conflict Risk

While the documentation focus is clear, the scope is quite broad (features, APIs, architecture, setup, operation) which could overlap with skills focused on API design, architecture decisions, or project setup. The 'por nível de decisão' qualifier adds some distinctiveness but isn't well explained.

2 / 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 is a well-organized documentation skill that clearly defines four levels of documentation and when to use each. Its main weaknesses are verbosity (explaining concepts Claude already understands like clean code principles) and lack of concrete inline examples — it tells Claude what to document but defers all templates to external files without showing even a brief example. Adding a compact inline example and trimming philosophical content would significantly improve it.

Suggestions

Add at least one compact inline example (e.g., a minimal ADR or feature doc snippet) so Claude has a concrete reference without needing to load external template files.

Remove or drastically shorten the 'Código Limpo: Zero Comentários' section — Claude already knows clean code principles, and this adds ~15 lines of non-novel content.

Add a validation checkpoint to the workflow, such as a checklist to verify documentation completeness after writing (e.g., 'Verify: all cross-references resolve, all 'conteúdo obrigatório' items present').

Trim the introductory sentence and 'Quando Não Usar' section which state obvious things Claude already knows.

DimensionReasoningScore

Conciseness

The skill contains useful information but is verbose in places. The philosophical preamble ('Documentação existe para responder perguntas...'), the 'Quando Não Usar' section with obvious items, and the 'Código Limpo: Zero Comentários' section explain concepts Claude already knows. The 4 levels of documentation are well-structured but could be more concise.

2 / 3

Actionability

The skill provides structured checklists of what to document at each level and a clear directory structure, which is useful. However, it lacks concrete executable examples — no actual template content is shown inline, no example ADR, no example feature doc snippet. It describes what to produce rather than showing how to produce it, deferring to external template files.

2 / 3

Workflow Clarity

The 'Quando Documentar' section provides a temporal sequence (before coding, during design, during implementation, before deploy), and the 4 levels provide a clear taxonomy. However, there are no explicit validation checkpoints — no step to verify documentation completeness, no feedback loop for reviewing docs against code changes, and no verification that cross-references are intact.

2 / 3

Progressive Disclosure

The skill appropriately references external files for templates (docs/skill-guides/documenter-templates.md, templates/doc-update.md) and policies, keeping the main file as an overview. References are one level deep and clearly signaled. The directory structure section provides good navigation context.

3 / 3

Total

9

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
felvieira/claude-skills-fv
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.