CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-lint

Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 dense, highly executable, and safety-conscious, with excellent validation gates around destructive consolidate actions. Its main flaws are inline content that belongs in reference files, and internal sequencing defects — out-of-order check numbering and a stale "12 lint checks" cross-reference that contradicts the 15 checks actually defined.

Suggestions

Fix the check ordering and stale cross-references: Synthesis Gaps is numbered 11 but appears after 14, and consolidate mode says "Run all 12 lint checks (Step 1–12 above)" while 15 checks (including 3a) exist — renumber sequentially and update the count.

Move the Rule 12 trust-ledger protocol and the Consolidate Mode details into a reference file (e.g., references/trust-ledger.md, references/consolidate.md), leaving SKILL.md as a concise overview with clearly signaled one-level-deep links.

Trim duplicated schema-override language between 'Before You Start' and the individual rules, and tighten the Rule 12e ledger-semantics prose to reduce token cost without losing the operational rules.

DimensionReasoningScore

Conciseness

The body is almost entirely operational guidance (exact greps, thresholds, CLI flags) with no explanation of concepts Claude already knows, matching anchor 4 ('efficient; minor instances of over-explanation'). It is not a 5 because passages like the Rule 12e ledger semantics and repeated schema-override language between 'Before You Start' and the rule bodies could be trimmed.

4 / 5

Actionability

Guidance is fully executable: exact grep patterns ("\[\[.*?\]\]"), a cohesion formula, copy-paste commands like "obsidian-wiki lint \"$OBSIDIAN_VAULT_PATH\" --json" and "obsidian-wiki trust-record ... --page ... --approved --json --pretty", plus concrete output templates. This matches anchor 5 ('copy-paste ready code or commands; specific examples cover the common cases') and exceeds anchor 4.

5 / 5

Workflow Clarity

The consolidate path has exemplary checkpoints ("Always run in dry-run first", "Apply these N changes? [yes / no / select]", snapshot abort on git failure), but the sequence itself is corrupted: sections run 10 → 12 → 13 → 14 → 11, and consolidate mode instructs "Run all 12 lint checks (Step 1–12 above)" when 15 checks (including 3a) are defined. That mismatch fits anchor 4 ('clear sequence with most checkpoints; minor gaps') rather than anchor 5.

4 / 5

Progressive Disclosure

No bundle files exist and everything is inline in a 685-line SKILL.md; references to llm-wiki/SKILL.md are clearly signaled and one level deep, but content that clearly belongs in separate files (the entire Rule 12 trust-ledger protocol, Consolidate Mode) is inlined. This matches anchor 3 ('content that should be separate is inline') and is above anchor 2 thanks to consistent section headers.

3 / 5

Total

16

/

20

Passed

Description

78%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.

A strong third-person description that states concrete audit targets, an explicit 'Use for' trigger, mode default, and a disambiguation pointer to wiki-dedup. Its only weakness is that the 'when' clause and keyword set could be richer with natural trigger phrases and synonyms.

DimensionReasoningScore

Specificity

"Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues" names the domain plus six concrete audit targets, matching anchor 4 ('several specific actions; minor gaps'). It stays below 5 because a single verb governs the list and several body checks (provenance, relationships, event-time) go unmentioned.

4 / 5

Completeness

Both questions are answered explicitly: what ("Audit wiki health: broken links, orphans, …") and when ("Use for maintenance or health checks"), which matches anchor 4. The 'when' clause lacks the concrete trigger phrases of the anchor-5 exemplar, keeping it at 4 rather than 5.

4 / 5

Trigger Term Quality

Natural phrases like "wiki health", "broken links", "orphans", and "maintenance or health checks" match what a user would actually say, fitting anchor 4 ('good keyword coverage; a few natural terms missing'). It is not a 5 because common variants such as "dead links", "wiki check", or "Obsidian vault" are absent.

4 / 5

Distinctiveness Conflict Risk

"use wiki-dedup for page-identity merges" plus a tightly-scoped wiki-health niche give it distinct triggers and minimal conflict risk, matching anchor 5. It does not risk overlapping generic audit or dedup skills because the boundary is stated explicitly.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (685 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository

Ar9av/obsidian-wiki

Path

.skills/wiki-lint/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.