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. Use when documenting code at the lowest C4 level for individual directories and code modules.

Quality

71%

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

57%

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

The body delivers strong, copy-paste-ready Mermaid diagram templates and a clear documentation template, but surrounds them with generic boilerplate steps, lacks any concrete analysis workflow or validation checkpoints, and contains malformed stray code fences. Progressive disclosure is fine as a single well-sectioned file.

Suggestions

Replace the generic 'Instructions' one-liners with a concrete, ordered analysis workflow (e.g., enumerate files → extract signatures → map dependencies → draft sections → verify against source) with an explicit validation checkpoint.

Remove the malformed stray fences — the four-backtick ```` line after the first Mermaid block and the bare ``` fences near the end — so the markdown and code blocks are clean and copy-paste-safe.

Trim the redundant 'Example Interactions' and 'Output Examples' sections, which largely restate the template, to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly purposeful (Mermaid templates, a fill-in template), but the generic 'Use this skill when / Do not use / Instructions' boilerplate and the partly redundant 'Example Interactions' and 'Output Examples' sections add tokens Claude doesn't need; it is mostly efficient but could be tightened.	2 / 3
Actionability	Concrete, copy-paste-ready Mermaid templates and a structured fill-in template give real executable guidance, but the core 'how to analyze a directory' steps are vague ('Apply relevant best practices and validate outcomes') and malformed stray fences (the ```` line and bare ``` fences) reduce copy-paste fidelity, so guidance is incomplete.	2 / 3
Workflow Clarity	There is no real sequenced workflow for analyzing code — the 'Instructions' are generic unordered one-liners with no validation checkpoints that the generated documentation is accurate or complete, so the sequence is present only implicitly via template section order with checkpoints missing.	2 / 3
Progressive Disclosure	Single file with no bundle, well-sectioned under clear headers and no nested references; navigation is easy and the one-level structure is appropriate for a template skill, matching the score-3 anchor for well-organized single-file content.	3 / 3
	Total	9 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states both capabilities and an explicit use-trigger, with concrete actions and a distinct C4 code-level niche. Its main weakness is trigger phrasing that leans on C4 jargon rather than the natural terms a user would actually say.

Suggestions

Add natural-language trigger terms users would actually say (e.g., 'document the code in a directory', 'C4 code-level docs') alongside the jargon to broaden trigger coverage.

Consider naming concrete outputs the user will recognize (e.g., 'function signature reference', 'dependency map') to make the trigger even more matchable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure' — matching the score-3 anchor of several specific concrete actions, not just domain-plus-some.	3 / 3
Completeness	Explicitly answers both what ('Analyzes code directories to create... documentation including function signatures, arguments, dependencies, and code structure') and when ('Use when documenting code at the lowest C4 level for individual directories and code modules'), matching the score-3 anchor; the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	The trigger 'Use when documenting code at the lowest C4 level for individual directories and code modules' has relevant keywords but is jargon-anchored ('C4', 'lowest C4 level'); a user would more naturally say 'document this directory's code' or 'C4 code-level docs,' so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The 'C4 Code-level / lowest C4 level for individual directories and code modules' framing carves a clear niche distinct from general code-documentation and from sibling C4 component/container/context skills, with low conflict risk.	3 / 3
	Total	11 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/c4-code/SKILL.md
Commit: e63f7dd

Reviewed: about 4 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.