code-wiki

Generate wiki docs + Mermaid diagrams for any codebase.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/software-development/code-wiki/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable code, clear templates, and a well-sequenced workflow backed by a verification section. Its main weaknesses are a monolithic single-file structure with no progressive disclosure of the reusable templates, and a length that could be tightened in places.

Suggestions

Move the per-file markdown templates (README, architecture, module, class-diagram, sequence, getting-started) into a references/ file (e.g. templates.md) and link to them, reducing SKILL.md to an overview and improving progressive_disclosure.

Tighten the Pitfalls and Mermaid shape-semantics sections to the few highest-value items to lift conciseness.

Add an inline per-step validation note (e.g. 'verify links resolve before moving to the next module') so the feedback loop is per-checkpoint rather than only at the end.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and action-oriented (templates, code, heuristics earn their tokens), but at ~430 lines it includes sections that could be tightened (e.g. Mermaid shape semantics, several Pitfalls entries); matches anchor 2 ('mostly efficient but could be tightened').	2 / 3
Actionability	Provides executable bash (clone, scan, state-file heredoc), copy-paste Mermaid examples, and parameterized markdown templates per output file; matches anchor 3 ('fully executable code/commands; copy-paste ready').	3 / 3
Workflow Clarity	Clear 12-step sequence reinforced by a Quick Reference table, plus a Verification section with concrete checks (mermaid fence balance, file existence, module count, fabricated-path sanity) forming a feedback loop; matches anchor 3.	3 / 3
Progressive Disclosure	Sections are well-organized, but no bundle files exist (references/ scripts/ assets/ absent) and all content — including the sizable per-file markdown templates — is inline in a single ~430-line SKILL.md; content that could be split out is inline, matching anchor 2.	2 / 3
	Total	10 / 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 concise and names a clear niche, but it is a single terse sentence with no 'Use when...' trigger clause and limited trigger-term coverage, which caps both completeness and trigger-term quality at 2. It communicates what the skill does but not when a user should reach for it.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks to document a codebase, generate a wiki, or make architecture/Mermaid diagrams.'

Broaden natural trigger keywords to include phrasings users actually say ('document this repo', 'architecture diagrams', 'code walkthrough').

Add 1–2 more concrete actions (e.g. 'per-module deep-dives', 'sequence diagrams') to lift specificity toward the multiple-actions anchor.

Dimension	Reasoning	Score
Specificity	Quotes "Generate wiki docs" and "Mermaid diagrams" — two concrete actions, but not comprehensive enough for the multiple-specific-actions anchor 3; matches anchor 2 ('names domain and some actions').	2 / 3
Completeness	Answers 'what' clearly but has no 'Use when...' clause or equivalent explicit trigger guidance, which per judging guidelines caps completeness at 2; matches anchor 2 ('has what, but when is missing').	2 / 3
Trigger Term Quality	Contains relevant natural terms ('wiki docs', 'Mermaid diagrams', 'codebase') but is terse and missing common variations users might say (e.g. 'document this repo', 'architecture diagrams'); matches anchor 2.	2 / 3
Distinctiveness Conflict Risk	Niche ('wiki docs + Mermaid diagrams for any codebase') is fairly distinct, but the one-line description is terse and the metadata lists related_skills (codebase-inspection, github-repo-management) indicating overlap risk; matches anchor 2.	2 / 3
	Total	8 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 13 missing	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/software-development/code-wiki/SKILL.md
Commit: 5be99b6

Reviewed: about 14 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.