wiki-lint

Run a health check on the LLM Wiki vault — mechanical checks (orphans, broken links, stale pages, missing frontmatter, log gap, duplicates) plus semantic checks (contradictions, cross-reference gaps, concepts missing their own page). Outputs a markdown report with suggested actions. Usage /wiki-lint [--stale-days N] [--log-gap-days N]

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 ./.gemini/skills/wiki-lint/SKILL.md

Quality

Content

67%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 content is a well-structured, concise overview with a clear three-pass workflow and good external references, but it lacks concrete script-invocation examples and deduplicates its script listing. Adding runnable commands would most improve the weakest dimension.

Suggestions

Add an executable invocation for each script (e.g. 'python lint_wiki.py --vault <path> --stale-days N') so the mechanical pass is copy-paste ready.

Spell out a concrete procedure for the semantic Pass 2 (which pages to read, how to decide a contradiction) rather than only listing check categories.

Remove the duplicate script listing — keep paths in one place (the 'Scripts' section) and reference them from Pass 1.

Dimension	Reasoning	Score
Conciseness	The body is lean — mostly bullets, a report template, and a frequency table — and assumes Claude knows what orphans/broken links are, but the script paths are listed twice (Pass 1 and the 'Scripts' section), a minor redundancy that keeps it at 4 rather than 5.	4 / 5
Actionability	It names scripts by path (lint_wiki.py, graph_analyzer.py, append_log.py) but gives no executable invocation (no 'python lint_wiki.py ...' with arguments), and Pass 2 semantic checks are described abstractly without a concrete procedure, fitting the 3 anchor for incomplete guidance.	3 / 5
Workflow Clarity	The three-pass sequence (mechanical → semantic → report) is clearly laid out and the Frequency table maps triggers to passes; as a read-only lint it 'reports, doesn't fix' so the destructive-cap does not apply, though no explicit verify-the-report checkpoint exists, leaving it just below 5.	4 / 5
Progressive Disclosure	The body is an overview with clearly signaled one-level-deep references (sub-agent, SKILL.md, references/lint-workflow.md) using '→' and 'See', but no bundle files exist in this skill's references/scripts/assets and the referenced paths point outside the bundle, so it is well-structured but not fully verifiable, matching the 4 anchor.	4 / 5
	Total	15 / 20 Passed

Description

75%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 is specific and distinct with strong concrete action coverage, but it omits any explicit 'Use when...' trigger guidance, capping completeness. Adding a trigger clause would lift the weakest dimension.

Suggestions

Add an explicit 'Use when ...' trigger clause (e.g. 'Use when auditing the wiki, finding orphan pages or broken links, or before sharing the vault').

Include a natural synonym like 'audit' or 'lint' in the prose trigger terms, not just the command name.

Consider mentioning report severity grouping or the log.md append in the description to round out the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both mechanical ('orphans, broken links, stale pages, missing frontmatter, log gap, duplicates') and semantic ('contradictions, cross-reference gaps, concepts missing their own page') checks plus 'Outputs a markdown report with suggested actions' — comprehensive coverage matching the 5 anchor.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the trailing 'Usage /wiki-lint [...]' is invocation syntax, not a when-to-use trigger, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms like 'health check', 'wiki', 'broken links', 'orphans', and 'stale pages' are present, but common synonyms such as 'audit' or 'lint the wiki' (only implicit via the command name) are missing, fitting the 4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	The 'LLM Wiki vault' niche and '/wiki-lint' trigger are highly specific with minimal overlap risk against other skills, matching the 5 anchor for a clear distinct niche.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/wiki-lint/SKILL.md
Commit: 19392f7

Reviewed: ~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.