CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

1.84x
Quality

68%

Does it follow best practices?

Impact

94%

1.84x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/c4-code/SKILL.md

The canonical home for this skill is c4-code in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

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

The body delivers a concrete, well-structured documentation template with complete Mermaid examples and a useful diagram-selection table, but it reads as a template shell rather than a procedure: the workflow steps are implicit, the Instructions section is generic filler, one markdown fence is malformed, and the sole external reference points to a nonexistent file. Tightening the filler and adding a concrete analysis sequence with a verification step would raise the weakest dimensions.

Suggestions

Fix the malformed code fences: a stray ```` after the first classDiagram block and dangling ``` fences around the Notes and Output Examples sections break the markdown structure.

Replace the vague Instructions bullets with a concrete sequence, e.g., 1) list source files in the target directory, 2) extract signatures/classes from actual code, 3) verify each recorded signature and file:line location against the source, 4) fill the template sections, 5) add a diagram only for complex structures.

Create the referenced resources/implementation-playbook.md (or remove the reference) — the path currently points to a file that does not exist in the bundle, and consider moving the three full Mermaid examples there to slim the main file.

DimensionReasoningScore

Conciseness

The core template content (Code Elements, Dependencies, Relationships, diagram examples) is efficient, but it is padded with generic filler ("Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes.") and circular placeholder sections ("Working on c4 code level: [directory name] tasks or workflows"). It fits "mostly efficient with some unnecessary explanation" rather than the noticeably-verbose anchor 2, since the examples themselves earn their tokens.

3 / 5

Actionability

Concrete, usable guidance: exact field formats ("functionName(param1: Type, param2: Type): ReturnType" with Location and Dependencies), three complete valid Mermaid diagram examples, a paradigm-to-diagram decision table, and example interactions. Minor gaps keep it below 5 — the Instructions bullets are vague ("Apply relevant best practices and validate outcomes") and there is no concrete procedure for extracting the information from source code.

4 / 5

Workflow Clarity

There is no explicit analysis sequence; the template's section order (Overview → Code Elements → Dependencies → Relationships) is only an implicit sequence, and the Instructions section gives vague, unordered bullets with no verification checkpoints (e.g., confirming signatures against the actual source). It is above anchor 2 because the template structure does impose a coherent order, but below anchor 4 for lacking defined steps.

3 / 5

Progressive Disclosure

The body is well-sectioned with clear headers, but the single reference — "If detailed examples are required, open `resources/implementation-playbook.md`" — is a dead path: no resources/ directory or bundle file exists, and roughly 90 lines of diagram examples are inlined in the single file. Not 4 because the one reference present is broken; above 2 because the in-body structure is good.

3 / 5

Total

13

/

20

Passed

Description

66%Weight 40%Scale 1-5

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 clearly states what the skill does with several concrete deliverables, but it lacks any explicit "when to use" trigger clause, which both caps completeness and weakens trigger quality. Adding a "Use when..." sentence with natural trigger phrases would lift the two lowest-impact dimensions.

Suggestions

Append an explicit trigger clause, e.g., "Use when asked to document a code directory at C4 code level, or when the user mentions C4 code diagrams, function signatures, or code structure documentation."

Broaden natural keywords to include synonyms users would actually say, such as "document the code", "classes", "modules", and "code documentation".

State the C4 level distinction in the description (e.g., "the lowest C4 level, below container/component") to reduce overlap with sibling C4 skills.

DimensionReasoningScore

Specificity

"Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure" lists several concrete actions, matching the anchor for several specific actions with minor gaps. It falls short of 5 because coverage is incomplete — classes/modules and diagram creation, which the skill body actually covers, are absent.

4 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by the domain naming.

3 / 5

Trigger Term Quality

Terms like "C4 code-level documentation", "code directories", "function signatures", "dependencies", and "code structure" give good keyword coverage. Not 5 because common natural variations users would say (e.g., "document the code", "classes", "modules", "code docs") are missing.

4 / 5

Distinctiveness Conflict Risk

"C4 Code-level documentation" carves a mostly distinct niche with low conflict risk against unrelated skills. Not 5 because closely related sibling skills (C4 context/container/component per the body's Key Distinctions section) exist and the description offers no trigger phrases that distinguish code-level from those levels.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/c4-code/SKILL.md

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.