code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill code-documenter72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
72%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 excels at trigger terms and distinctiveness, providing excellent coverage of documentation-related keywords that users would naturally use. However, it fails to describe what the skill actually does - it only lists when to invoke it and what types of documentation it handles, without specifying concrete actions like 'generates', 'writes', 'formats', or 'validates'.
Suggestions
Add concrete action verbs at the beginning describing what the skill does (e.g., 'Generates and formats technical documentation including docstrings, API docs, and user guides')
Restructure to lead with capabilities before the 'Use when' clause to clearly answer 'what does this do' before 'when to use it'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (documentation) and lists several types of documentation work (docstrings, API documentation, documentation sites, OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides), but doesn't describe concrete actions - it only lists what types of things it works with, not what it does with them. | 2 / 3 |
Completeness | Has strong 'when' guidance with 'Use when...' and 'Invoke for...' clauses, but the 'what' is weak - it never explicitly states what actions the skill performs (e.g., 'creates', 'generates', 'formats'). The description tells when to use it but not what it actually does. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'docstrings', 'API documentation', 'documentation sites', 'OpenAPI', 'Swagger', 'JSDoc', 'tutorials', 'user guides'. These are specific technical terms users would naturally mention when needing documentation help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear documentation-focused niche with distinct triggers like 'OpenAPI', 'Swagger', 'JSDoc', 'docstrings' that are unlikely to conflict with other skills. The specific technical documentation terms create a well-defined scope. | 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 demonstrates strong progressive disclosure with a well-organized reference table, but falls short on actionability by providing no concrete code examples or executable snippets. The workflow is present but lacks validation checkpoints, and the content includes some unnecessary role-playing framing that doesn't contribute to Claude's ability to document code effectively.
Suggestions
Add at least one concrete docstring example per major format (Google, NumPy, JSDoc) directly in the skill to make it immediately actionable
Remove the 'Role Definition' section - Claude doesn't need persona framing to execute documentation tasks
Integrate validation into the workflow: after step 4 (Document), add an explicit 'Validate - Test all code examples compile/run' checkpoint
Replace the verbose 'When to Use This Skill' list with a single sentence, as the reference table already covers when to load specific guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('senior technical writer with 8+ years of experience') and verbose sections like 'Role Definition' that don't add actionable value. The reference table and constraints are reasonably efficient, but the 'When to Use This Skill' section largely duplicates information Claude could infer. | 2 / 3 |
Actionability | The skill provides a workflow and constraints but lacks concrete, executable examples. No actual code snippets showing docstring formats, no sample OpenAPI specs, no copy-paste ready commands. The guidance is structural rather than executable. | 2 / 3 |
Workflow Clarity | The 5-step workflow (Discover, Detect, Analyze, Document, Report) provides a clear sequence, but lacks validation checkpoints or feedback loops. For documentation tasks that could introduce errors, there's no explicit 'test code examples' step integrated into the workflow despite being mentioned in constraints. | 2 / 3 |
Progressive Disclosure | Excellent use of a reference table with clear 'Load When' conditions. References are one level deep, well-organized by topic, and clearly signaled. The main skill serves as a proper overview pointing to detailed materials. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.