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.
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/obsidian/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope (Obsidian vault operations), lists concrete actions (read, write, search, tag, query), and provides explicit trigger guidance with natural user phrases. The description also includes helpful technical context (CLI v1.12+, requires Obsidian running) and assertively claims exclusivity for vault interactions, which aids in skill selection. Minor note: the use of 'ANY' and 'ONLY' in caps is slightly aggressive but functional for disambiguation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: read, write, search, tag, query. Also mentions typed wrappers around Obsidian CLI with version specificity (v1.12+), and notes the requirement that Obsidian must be running. | 3 / 3 |
Completeness | Clearly answers both 'what' (composable Obsidian vault operations via CLI — read, write, search, tag, query) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general rule about any vault operation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'save to vault', 'obsidian', 'research note', 'daily note', 'tag', 'summarize and save', plus the general 'vault operation'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets Obsidian vault operations specifically, with clear niche triggers like 'obsidian', 'vault', 'daily note'. The emphatic statement 'This is the ONLY correct way to interact with the vault' further reduces conflict risk by asserting exclusivity. Unlikely to overlap with non-Obsidian skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent executable examples and clear workflows, but it suffers severely from being a monolithic document that tries to cover too much in one file. The core vault operations content is strong, but the Agent Memory, Research Reports, and Friction Self-Healing sections bloat the skill enormously and should be split into separate referenced files. Token efficiency is poor — Claude doesn't need lengthy explanations of when to save memories or detailed self-healing workflow narratives.
Suggestions
Extract Agent Memory, Research Reports, Friction Self-Healing, and Composing with Other Skills into separate referenced files (e.g., AGENT-MEMORY.md, REPORTS.md, SELF-HEALING.md) and replace with one-line references in the main SKILL.md.
Move the Quick Reference API listing to a separate REFERENCE.md file, keeping only the most common 3-4 operations (create, read, append, search) inline.
Remove the Unicode/UTF-8 troubleshooting section and the detailed 'What NOT to do' list — condense to 1-2 lines of critical constraints.
Trim the self-healing example narrative (branch-wrapup ESLint scenario) which is ~20 lines explaining a concept Claude can infer from the workflow steps alone.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely long and verbose. It includes extensive sections on Agent Memory, Research Reports, Friction Self-Healing, and Composing with Other Skills that go well beyond the core vault operations. Many sections explain workflows and concepts Claude could infer. The 'What NOT to do' section, Unicode troubleshooting, and detailed self-healing examples add significant token overhead. | 1 / 3 |
Actionability | The skill provides fully executable PowerShell commands with heredoc syntax, a comprehensive Python API quick reference with concrete method signatures and examples, and copy-paste ready patterns for every operation (create, read, append, search, etc.). | 3 / 3 |
Workflow Clarity | Multi-step workflows include explicit validation checkpoints: the verification notes section instructs to verify creates with follow-up reads, the deduplication section requires searching before creating, the self-healing workflow has a clear numbered sequence with priority-based decision points, and the upgrade workflow has a clear 8-step process with explicit save/snapshot steps. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no references to separate files for the extensive Agent Memory, Research Reports, or Friction Self-Healing sections. These composable patterns could each be their own referenced documents. The Quick Reference alone is ~80 lines that could be in a separate API reference file. No bundle files are provided despite the content clearly warranting them. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (542 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
a5309ae
Table of Contents
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.