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.

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/c4-code/SKILL.md

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a usable, structured C4 code-level documentation template with executable Mermaid examples and a diagram-selection table, but it is padded with verbose inline diagram demos and generic instruction filler, lacks an explicit generation workflow with validation checkpoints, and ships a broken reference to a non-existent playbook. Its weakest point is progressive disclosure: monolithic inline content plus a dangling file reference.

Suggestions

Fix or remove the dangling `resources/implementation-playbook.md` reference — either bundle the file or delete the line — and move the large Mermaid diagram catalog and Example Interactions into one-level-deep reference files (e.g., `references/diagram-templates.md`) with clearly signaled links from SKILL.md.

Replace the generic "Instructions" filler with a concrete numbered workflow: (1) scan the directory for entry points, (2) extract function/class signatures, (3) trace internal and external dependencies, (4) choose the diagram by paradigm using the table, (5) assemble the template, (6) verify every listed element against source.

Trim the inline Mermaid demos to one minimal example per diagram type and cut the conceptual C4-model Note and redundant Output Examples, trusting Claude's knowledge of Mermaid syntax and the C4 model.

Dimension	Reasoning	Score
Conciseness	The structured template payload (Code Elements, Dependencies, Relationships) is reasonably lean, but the body is padded with three full inline Mermaid diagram demos (largely syntax Claude already knows), a conceptual C4-model Note, generic filler Instructions ("Clarify goals...Apply relevant best practices and validate outcomes"), and redundant Example Interactions + Output Examples sections that could be tightened — fitting "Mostly efficient but includes some unnecessary explanation or could be tightened."	2 / 3
Actionability	It provides a concrete, copy-paste-ready template (signature format `functionName(param1: Type, param2: Type): ReturnType`, dependency fields) and executable Mermaid examples plus a decision table, but the lead "Instructions" section is vague boilerplate ("Clarify goals...provide actionable steps and verification") rather than concrete steps, and the template leans heavily on placeholders, so it is not uniformly actionable.	2 / 3
Workflow Clarity	The template implies an assembly order (Overview → Code Elements → Dependencies → Relationships) and includes a soft "Stop and ask for clarification if required inputs...are missing" checkpoint, but there is no explicit numbered step sequence for the multi-step generation process (extract signatures → trace dependencies → select diagram by paradigm → assemble → verify) and no validation loop confirming the doc against source — fitting "sequence present but checkpoints missing or implicit."	2 / 3
Progressive Disclosure	The skill is largely monolithic — a large inline Mermaid diagram catalog and example/output sections that belong in separate reference files — and its only external reference, `resources/implementation-playbook.md`, points to a file that does not exist (no resources/ directory is bundled), so the disclosure/navigation mechanism is broken rather than merely weakly signaled.	1 / 3
	Total	7 / 12 Passed

Description

50%

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 concrete and third-person, clearly stating what the skill produces, but it omits any "Use when..." trigger guidance and relies on a single analyze-to-document action with limited distinct triggers. It sits squarely at the midpoint: specific enough to avoid being generic, but missing the explicit when-to-use triggers and natural-term coverage that would lift it higher.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g., "Use when documenting a code directory's functions, classes, and dependencies at C4 code level, or when the user asks for a C4 code diagram / code-level documentation."

Broaden trigger-term coverage with common user phrasings such as "code diagram", "C4 diagram", "document functions/classes", and "code structure" so it matches how users actually request this.

Add a brief disambiguating phrase distinguishing code-level from the sibling C4 levels (e.g., "code-level detail, not container or component diagrams") to reduce conflict risk with other C4 skills.

Dimension	Reasoning	Score
Specificity	It names the domain and concrete actions ("Analyzes code directories to create comprehensive C4 code-level documentation") plus specific deliverable elements ("function signatures, arguments, dependencies, and code structure"), but the distinct action verbs are limited to a single analyze-then-document flow rather than the multiple distinct actions in the score-3 anchor.	2 / 3
Completeness	It clearly answers "what" (analyzes code directories to create C4 code-level documentation with signatures, arguments, dependencies, structure) but provides no "Use when..." clause or equivalent explicit trigger guidance, so "when" is entirely missing — matching the score-2 anchor ("Has what, but when is missing or only implied") exactly, and the rubric guideline caps completeness at 2 for a missing Use-when clause.	2 / 3
Trigger Term Quality	It includes relevant domain keywords a C4-aware user might say ("C4 code-level documentation", "code directories", "function signatures", "dependencies"), but it omits common variations (e.g., "code diagram", "C4 diagram", "document functions") and has no explicit "Use when..." trigger list, so coverage is partial rather than the broad natural-term set of the score-3 anchor.	2 / 3
Distinctiveness Conflict Risk	It identifies a specific niche ("C4 Code-level documentation specialist"), but C4 code-level overlaps with sibling C4 documentation skills (context, container, component), and the description provides no distinct trigger terms to disambiguate which C4 level applies — fitting "Somewhat specific but could still overlap with similar skills."	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/c4-code/SKILL.md
Commit: a3068b7

Reviewed: about 13 hours 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.