obsidian-vault-lint-cowork

Cowork-native fork of obsidian-vault-lint. Weekly maintenance pipeline (broken-link cleanup, MOC coverage, alphabetical sort, xAI-assisted connection discovery, Topic-MOC proposals, plus a top-3 reading-recommendation phase that surfaces the newest Library notes matching your research interests) that runs without the Obsidian CLI dependency. Pure-Python over the vault's markdown filesystem — safe to invoke from a Cowork scheduled task in the Linux sandbox. Schedule weekly for a self-maintaining knowledge base.

Quality

68%

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 ./.github/skills/obsidian-vault-lint-cowork/SKILL.md

Quality

Content

61%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 actionable with real bundle references, but as a batch/destructive pipeline it lacks explicit validation feedback loops, capping workflow clarity, and carries some trimmable explanatory prose.

Suggestions

Add explicit validation/dry-run checkpoints between phases (e.g., run --dry-run, review the report, then --apply) to create a validate→fix→retry loop for the destructive Phase 2 and Phase 4 operations.

Trim the "Why a fork" and "Scheduling via Cowork" prose to the essentials so the body stays lean.

Document rename_tags.py in the file tree (or note it as an optional utility) so the listed bundle matches the actual scripts/ directory.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete sections, but the "Why a fork" rationale and scheduling walkthrough include explanatory padding that could be trimmed without losing actionability.	3 / 5
Actionability	Provides concrete, copy-paste-ready CLI commands, an env-var table, vault constants, and a file tree — mostly executable guidance with only minor gaps around per-script internals.	4 / 5
Workflow Clarity	The six phases are clearly sequenced, but this is a batch/destructive skill (autonomous fixes, pruning, git commit) without explicit validate→fix→retry checkpoints in the body, so per the rubric cap workflow clarity stays at 3.	3 / 5
Progressive Disclosure	Well-organized sections with a clear file tree and one-level-deep references to real bundle scripts (verified present in scripts/); minor gaps such as inline tunables and an unlisted rename_tags.py script.	4 / 5
	Total	14 / 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 clearly distinct, but lacks an explicit "Use when..." trigger clause, capping completeness. Trigger terms are good but slightly jargon-heavy for the target audience.

Suggestions

Add an explicit "Use when..." clause stating when Claude should invoke this skill (e.g., weekly vault maintenance, broken-link cleanup, or when the user asks for Obsidian vault upkeep).

Soften domain jargon in the description by pairing terms like "MOC" and "xAI" with plain-language synonyms a user would naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "broken-link cleanup, MOC coverage, alphabetical sort, xAI-assisted connection discovery, Topic-MOC proposals, plus a top-3 reading-recommendation phase" — giving comprehensive coverage of what the pipeline does.	5 / 5
Completeness	The "what" is clear and detailed, but there is no "Use when..." clause; "Schedule weekly for a self-maintaining knowledge base" is deployment guidance rather than explicit trigger guidance, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Natural terms like "Obsidian vault", "broken-link", "reading recommendations", "weekly maintenance", and "knowledge base" are present, but coverage leans on domain jargon (MOC, xAI, Cowork) and omits some common synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (Obsidian vault linting via a Cowork-native pure-Python fork) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: 0xRabbidfly/Eric-Cartman
Path: .github/skills/obsidian-vault-lint-cowork/SKILL.md
Commit: aa16c9e

Reviewed: 6 days 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.