save

Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation, save this analysis, keep this insight, preserve this chat result.

Quality

88%

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

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.

A well-structured, actionable skill body that treats vault writes as a validated transaction with explicit checkpoints and error-recovery loops. Minor room to tighten policy prose and confirm the out-of-bundle referenced paths exist.

Suggestions

Tighten the governance paragraphs (untrusted-content, no-egress) into terser bullet rules to trim a few tokens without losing the safety constraints.

Confirm or inline-exist the ../wiki/references/*.md targets so the one-level-deep references are verifiable within the bundle.

Replace the templated /absolute/path/to/... and /path/to/vault placeholders with a one-line resolution example using the described PRODUCT_ROOT/vault discovery to make commands copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of Obsidian/vaults), with directive policy prose that earns its place; a few governance sentences could still be tightened.	4 / 5
Actionability	Concrete executable commands (transaction inspect/apply/checkpoint) with the APPROVAL_SHA256 flow and exit-75 handling are provided; paths are templated but their resolution is explained, leaving minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced Prepare -> Preserve -> Build -> Preview/apply workflow with SHA-256 preconditions, inspect-before-apply validation, an exit-75 re-read/rebuild feedback loop, and 'transaction recover' for interrupted applies.	5 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep markdown references (provenance.md, operation-transactions.md); no bundle directories are present to verify the referenced files, so structure is good but not fully confirmable.	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 tight, third-person description that clearly states what the skill does, when to use it, and how it differs from ingestion, with rich natural trigger phrases. Only minor: it leans on one core verb, leaving specificity just shy of fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names the Obsidian-vault domain and enumerates four concrete content types (answer, decision, insight, session summary) saved as a reviewed transaction, but centers on a single core verb so coverage is strong rather than fully comprehensive.	4 / 5
Completeness	It explicitly answers both 'what' (save selected content into an Obsidian vault as one reviewed transaction) and 'when' ('Use only when the user explicitly asks...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Triggers:' clause lists comprehensive natural phrases and synonyms a user would actually say (/save, save this, file this conversation, keep this insight, preserve this chat result).	5 / 5
Distinctiveness Conflict Risk	The Obsidian-vault save niche is clear, the explicit negative boundary ('not when they supply a file or URL to ingest') rules out ingest skills, and triggers are distinct.	5 / 5
	Total	19 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-obsidian
Path: skills/save/SKILL.md
Commit: ad67087

Reviewed: 10 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.