check-links

Find broken wiki-links in the vault. Read-only analysis — scans for [[links]] and verifies target files exist. No writes, no dependencies.

Quality

83%

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

100%

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

A well-structured, lean, fully actionable read-only workflow with concrete tool invocations, edge-case handling, and report templates. It assumes Claude's competence and every section carries its weight.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — assumes Claude knows what wiki-links and vaults are; no concept padding, compact code blocks, every section earns its place.	3 / 3
Actionability	Provides executable Grep and Glob snippets with concrete regex, flags, and glob patterns, plus explicit strip rules, a report template, and a close-match suggestion pattern — copy-paste ready.	3 / 3
Workflow Clarity	A clear five-step sequence with an explicit verify step (Step 3: broken vs valid) and a reporting/suggestion follow-up; the read-only nature means no destructive-validation cap applies.	3 / 3
Progressive Disclosure	A single-purpose skill with no external bundle files and well-organized sections (Usage, How to Execute, Edge Cases, Tips); organization is clean with no nested references.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 concise, specific, third-person description with a clear niche, but it omits explicit 'Use when...' trigger guidance and lacks common trigger-term variations. Adding a trigger clause and synonyms like 'dead links' / 'link rot' would raise completeness and trigger_term_quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to check for broken/dead wiki-links, find link rot, or verify vault links resolve.'

Add natural trigger-term variations such as 'dead links', 'link rot', and 'broken links' so the description matches how users phrase the request.

Consider stating when NOT to use it (e.g. external/markdown links) to sharpen distinctiveness, though the read-only framing already helps.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Find broken wiki-links', 'scans for [[links]]', 'verifies target files exist', 'No writes' — matching the 'Lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger clause; per the guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms like 'broken wiki-links' and 'vault' but misses common variations (e.g. 'dead links', 'link rot', 'check links'); not full coverage of what users would say.	2 / 3
Distinctiveness Conflict Risk	The 'wiki-links in the vault' framing is a clear niche with distinct triggers, unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: ballred/obsidian-claude-pkm
Path: vault-template/.claude/skills/check-links/SKILL.md
Commit: ef1e4da

Reviewed: about 1 hour 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.