obsidian

Composable Obsidian vault operations via CLI. Use when ANY task needs to read, write, search, tag, or query the Obsidian vault. This is the ONLY correct way to interact with the vault. Provides typed wrappers around the Obsidian CLI (v1.12+). Requires Obsidian to be running. Use when user says "save to vault", "obsidian", "research note", "daily note", "tag", "summarize and save", or any vault operation.

Quality

88%

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

Quality

Content

81%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.

Highly actionable body with strong workflow clarity and validation feedback loops, plus genuine bundle scripts clearly referenced. The main weakness is conciseness: a large re-explained Obsidian-Flavored-Markdown section and an inlined API reference that could live in a separate file inflate the token budget.

Suggestions

Move the 'Output Formatting Rules' (wikilinks, embeds, callouts, properties, highlights) into a separate references/ file and keep only vault-specific deviations inline — Claude already knows Obsidian Flavored Markdown.

Extract the full Python 'Quick Reference' API catalog into a reference file (e.g. references/api.md) and leave only the 3-4 most common calls in SKILL.md to cut context cost.

Trim the recurring 'Friction Rule' / self-healing restatements to a single canonical section to reduce repetition across the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content, but the 'Output Formatting Rules' section re-explains Obsidian Flavored Markdown (wikilinks, embeds, callouts, frontmatter, highlights) that Claude already knows, and the inline Quick Reference is long — earning a conciseness penalty.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: complete PowerShell heredoc examples, full CLI subcommand reference with flags, and a concrete Python Quick Reference covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints and feedback loops — verify-after-create via read, search empty-result retry guidance, dedup-before-create for memories, and the P0/P1/P2 self-healing loop for destructive/deviation cases.	5 / 5
Progressive Disclosure	Well-sectioned structure with real, one-level-deep script references (obsidian.py, cli_sync.py, .cli-manifest.json) clearly signaled by path, but the bulk API Quick Reference and OFM rules are inlined in SKILL.md rather than split into a separate reference file.	4 / 5
	Total	17 / 20 Passed

Description

95%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, specific description with explicit what/when structure and rich natural trigger phrases, plus clear exclusivity framing that lowers conflict risk. Minor specificity gaps (not every CLI capability is enumerated) keep it just short of perfect on that single dimension.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('read, write, search, tag, or query') and 'typed wrappers' with a version pin, but the action list is not exhaustive over the full CLI surface, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (composable Obsidian vault operations via CLI, typed wrappers) and 'when' twice with concrete trigger phrases, capped by clear prerequisite and exclusivity framing.	5 / 5
Trigger Term Quality	Includes natural user phrases with synonyms — 'save to vault', 'obsidian', 'research note', 'daily note', 'tag', 'summarize and save' — matching how a user would actually phrase the need.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear Obsidian-vault niche with distinct triggers and explicit 'ONLY correct way' / 'SOLE interface' framing that minimizes wrong-skill invocation; generic terms like 'tag' create only negligible overlap.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (653 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: 0xrabbidfly/eric-cartman
Path: .github/skills/obsidian/SKILL.md
Commit: 0b8453f

Reviewed: 5 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.