c4-code
Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure.
57
37%
Does it follow best practices?
Impact
94%
1.84xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/c4-code/SKILL.mdQuality
Discovery
67%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 in specificity and distinctiveness, clearly identifying the C4 code-level documentation niche with concrete deliverables. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill. The trigger terms could also be expanded to cover more natural user phrasings.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for C4 diagrams, code-level architecture documentation, or wants to map out code structure and dependencies.'
Include additional natural trigger terms users might say, such as 'architecture documentation', 'code map', 'component dependencies', 'codebase structure', or 'software architecture'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Analyzes code directories', 'create comprehensive C4 code-level documentation', 'function signatures, arguments, dependencies, and code structure'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (analyzes code directories to create C4 code-level documentation with specific outputs), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'C4', 'code-level documentation', 'function signatures', 'dependencies', 'code structure', but misses common user variations like 'architecture diagram', 'component diagram', 'code map', or file extensions. Users might not always say 'C4' specifically. | 2 / 3 |
Distinctiveness Conflict Risk | The 'C4 code-level documentation' niche is very specific and distinct. It's unlikely to conflict with general code documentation or other architecture skills because it explicitly targets the C4 model's code level with specific deliverables like function signatures and dependencies. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially an unfilled template with placeholder values throughout, providing no concrete guidance on how to actually perform C4 code-level documentation. The bulk of the content is generic Mermaid diagram examples for different paradigms that Claude already knows how to create, consuming significant tokens without adding actionable value. It lacks a clear workflow for analyzing code directories and producing documentation.
Suggestions
Replace placeholder brackets with a concrete, worked example showing actual code analysis of a real or realistic directory, demonstrating the expected output format
Add a clear step-by-step workflow: 1) List files in directory, 2) Read each file, 3) Extract function signatures, 4) Map dependencies, 5) Generate documentation, with validation checkpoints
Move the extensive Mermaid diagram examples and paradigm selection table to a separate reference file, keeping only a brief mention and link in the main skill
Remove the generic instructions section ('Clarify goals, constraints, and required inputs') and replace with specific, actionable commands for code analysis
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and mostly consists of template placeholders ([Directory Name], [What this function does], etc.) rather than actionable content. The extensive Mermaid diagram examples for every paradigm (OOP, FP, procedural, mixed) are largely teaching Claude things it already knows. The 'choosing the right diagram' table and multiple diagram options add significant token cost without proportional value. | 1 / 3 |
Actionability | The content is almost entirely a template with placeholder brackets rather than executable guidance. There are no concrete commands, no actual code to run for analysis, and no specific steps for how to analyze a directory. The Mermaid examples are generic templates, not actionable instructions for performing C4 code-level documentation. | 1 / 3 |
Workflow Clarity | There is no clear workflow for how to actually analyze code and produce C4 documentation. The instructions section has only four vague bullet points ('Clarify goals, constraints, and required inputs'). There's no sequenced process for reading code, extracting signatures, building dependency graphs, or validating the output documentation. | 1 / 3 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, and the content is organized with clear headers. However, the massive inline Mermaid diagram examples and the choosing-the-right-diagram table should be in a separate reference file rather than inline, making the main skill unnecessarily long. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
e18e63c
- 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.