CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

68

Quality

86%

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

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 tight, operationally serious skill body: executable commands, explicit approval gates, conflict recovery, and honest-evidence rules, with security posture (untrusted source text, no egress) stated up front. The main gaps are the repeated scope-limit guidance and the missing inline example of the transaction bundle that the whole workflow revolves around.

Suggestions

Consolidate the three restatements of scope limitation (opening paragraph, "The current explicit save request defines authority and scope", and the closing "keep the operation no larger than the explicit save request") into one authoritative statement.

Include a minimal example save-bundle JSON (or an annotated field list) inline or in a references/ file within the skill directory, since bundle construction is the workflow's central step and currently only its shape is implied.

Move the dense catalog/MOC declaration and expected-hash rules into the already-referenced workflow acceptance guide, keeping SKILL.md to the rule that every canonical page must be linked from a declared active catalog.

DimensionReasoningScore

Conciseness

The body is dense with zero padding and assumes Claude's competence (no concept explanations), but the scope-limit theme is repeated three times ("Save only the scope the user selected", "The current explicit save request defines authority and scope", "keep the operation no larger than the explicit save request"), and the MOC/catalog hash paragraph is intricately worded. Efficient with minor trims possible — anchor 4, not lean enough for 5.

4 / 5

Actionability

Concrete executable commands with real argument shapes (workflow inspect/apply with --approved-plan-sha256, checkpoint, exit-75 conflict handling, transaction recover) plus specific budgets (500 words / 32 KiB hot cache, five-page read budget). Not a 5 because the central artifact — constructing the save-bundle JSON — is only sketched ("operation_type: save", workflow.catalogs shape) with no example, and commands contain unresolved placeholders ($CORE, /path/to/save-bundle.json).

4 / 5

Workflow Clarity

A clear sequence (Prepare → evidence check → draft transaction → inspect → review/approve → apply) with explicit validation gates: SHA-256 preconditions, the approval SHA binding, the storage_valid/workflow_complete double gate, exit-75 conflict recovery (re-read, rebuild, re-inspect), and transaction recover for interrupted applies. This matches the 5 anchor's explicit validation and error-recovery feedback loops, which is essential for a vault-mutating batch operation.

5 / 5

Progressive Disclosure

Sections are well organized and the three references (provenance contract, transaction contract, workflow acceptance guide) are clearly signaled, conditional, and one level deep. Not a 5 because the skill bundle itself ships no references/ or scripts/ files, all detail lives in external product-root paths that cannot be resolved from the skill directory as bundled, and intricate catalog/MOC hash policy is inlined rather than living in the already-referenced acceptance guide.

4 / 5

Total

17

/

20

Passed

Description

87%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 description: concrete capability statement, explicit use-when boundary with a negative exclusion clause, and a rich natural-language trigger list. Minor room to broaden trigger synonyms and hint at the transaction's coupled effects.

DimensionReasoningScore

Specificity

"Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction" names a concrete destination, transaction unit, and a four-type content taxonomy. It is more concrete than the 3 anchor's 1-2 actions, but not comprehensive (single core verb; the coupled index/log/hot updates are absent), so it falls just under the 5 anchor.

4 / 5

Completeness

Explicitly answers what ("Save ... into an Obsidian vault as one reviewed transaction") and when ("Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest") with concrete trigger phrases, in third person. This matches the 5 anchor; the missing-Use-when cap does not apply.

5 / 5

Trigger Term Quality

"Triggers: /save, save this, save that answer, file this conversation, save this analysis, keep this insight, preserve this chat result" gives good natural-phrase coverage plus the slash command. It falls short of the 5 anchor because common variants like "remember this", "note this down", or "archive this" are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (preserving selected conversation content into Obsidian as one reviewed transaction) with distinct trigger phrases, and the explicit exclusion "not when they supply a file or URL to ingest" minimizes overlap with ingest/research skills. Matches the 5 anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

AgriciDaniel/claude-obsidian

Path

skills/save/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.