cs-wiki-linter

Dispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".

Quality

84%

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

Quality

Content

68%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 is well-structured and mostly actionable with a clear three-pass workflow, but it lacks validation checkpoints for a batch vault-wide operation and references bundle files that are not actually present.

Suggestions

Add explicit validation/verification checkpoints between passes (e.g., confirm scripts exited 0 and JSON parsed before Pass 2; confirm the report was written before appending the log) to satisfy the batch-operation feedback-loop requirement.

Resolve the '<plugin>' placeholder in the bash commands to a concrete path or document the substitution, so commands are copy-paste ready.

Either bundle the referenced lint-workflow.md and scripts locally or remove the dangling external reference, since no references/ or scripts/ directories exist in this skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with actionable lists and code blocks and does not over-explain concepts Claude knows, but the 'Rules' and 'Red flags' sections partially restate each other — a minor trim opportunity. Not a 5 because of that redundancy; clearly above the score-3 midpoint.	4 / 5
Actionability	Provides concrete bash commands and a copy-paste report template, but commands use unresolved placeholders like '<plugin>' and '<date>' that require substitution, leaving minor gaps from fully executable. Above midpoint, not yet fully copy-paste ready.	4 / 5
Workflow Clarity	Three passes (Mechanical, Semantic, Report) are clearly sequenced, but this is a batch operation over a whole vault with no validation/verification checkpoints (no 'verify scripts succeeded', no 'confirm report written', no feedback loop), so the batch-operation cap at 3 applies. Pass 2A also modifies pages (adds callouts) without verification.	3 / 5
Progressive Disclosure	Well-organized into clear sections with one clearly-signaled one-level-deep reference (lint-workflow.md), but no bundle files actually exist — referenced scripts and the reference file are external/unbundled, and the body inlines substantial workflow detail that the external reference would cover. Good but not exemplary.	4 / 5
	Total	15 / 20 Passed

Description

100%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 third-person, specific, and answers both 'what' and 'when' with concrete natural-language triggers. It is among the strongest examples in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both mechanical checks (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps) and semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), plus producing a markdown report — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers what (runs mechanical + semantic checks, produces a report with suggested actions) and when (weekly, after batch ingests, or on the named trigger phrases) with concrete trigger clauses.	5 / 5
Trigger Term Quality	Includes natural user phrases — "check the wiki" / "lint my wiki" / "audit the vault" — plus timing triggers ("weekly, after batch ingests"), giving comprehensive coverage of terms a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (LLM Wiki vault health checking) with distinct triggers unlikely to fire for unrelated skills, minimal conflict risk.	5 / 5
	Total	20 / 20 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: alirezarezvani/claude-skills
Path: .gemini/skills/cs-wiki-linter/SKILL.md
Commit: 19392f7

Reviewed: ~6 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.