CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-capture

Turn the current conversation or finding into a structured permanent wiki note. Use for save/capture/preserve requests; QUICK MODE writes a fast _raw/ note. Supports named-vault routing such as @research save this. This captures current discussion, not external source ingestion.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.skills/wiki-capture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a dense, highly actionable operational skill with clearly separated modes, explicit validation loops, and a well-used bundle reference. Its weaknesses are motivational padding, an internal contradiction between the quick-mode stop instruction and Step 5b's quick-mode exception, and bulk spec content (correction schema, body templates) inlined rather than disclosed progressively.

Suggestions

Resolve the quick-mode contradiction: either scope Step 5b into the quick-mode procedure explicitly or remove 'In quick mode, do this step but skip Step 6' from the full-mode section.

Trim motivational padding in Step 5b and elsewhere ('This is the step that keeps it alive...') to pure instruction.

Move the correction-mode YAML schema and the four full-mode body templates into references/ files, keeping only the essential template skeleton inline.

DimensionReasoningScore

Conciseness

Mostly efficient operational detail Claude cannot know (commands, frontmatter specs, gate criteria), but padded in places — e.g. 'The memory surface is only as good as what gets written into it. This is the step that keeps it alive — without it the profile stays empty and the session recap has nothing to inject' is motivational fluff, and several rationale passages could be tightened.

3 / 5

Actionability

Concrete copy-paste-ready commands with flags ('obsidian-wiki memory profile set <key> "<value>" --confidence 0.85', 'sync CAPTURE type=<type> page="<path>"', '${QMD_CLI:-qmd} update'), exact paths, slug examples, and confidence calibration. Minor gaps keep it from 5: correction mode's 'update an existing derived page when one owns the claim' lacks a concrete lookup procedure, and '<obsidian-wiki memory now>' is an unexplained placeholder.

4 / 5

Workflow Clarity

Three modes cleanly separated with sequenced steps, an explicit KEEP/SKIP gate, a mandatory sha256 pre/post verification loop in correction mode, and QMD failure recovery ('do not roll back the vault changes; report the QMD status separately'). Falls short of 5 because quick mode says 'Stop here; do not run the full-mode steps below' while Step 5b instructs 'In quick mode, do this step but skip Step 6' — an internal contradiction — and the unnumbered 'Before You Start' / 'Step 5b' disrupt the sequence.

4 / 5

Progressive Disclosure

The raw-file spec is properly offloaded to a real, one-level-deep, clearly signaled reference ('Read references/RAW-FORMAT.md for the full frontmatter spec'), which exists in the bundle. However, the body leans on three separate sections of an external llm-wiki/SKILL.md plus .skills/llm-wiki/references/MEMORY.md, and inlines the large correction-mode YAML schema and four full body templates that could live in reference files.

4 / 5

Total

15

/

20

Passed

Description

73%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 concise, in the right voice, and answers both what and when with concrete trigger terms and an explicit disambiguation boundary. Its main weaknesses are incomplete action coverage (correction mode and tracking updates are absent) and trigger coverage that misses common synonyms.

Suggestions

Add the correction mode and tracking-file updates to the action list so capability coverage is comprehensive (would lift specificity).

Broaden trigger terms with natural variations users would say, e.g. 'remember this', 'note this down', 'save this bug fix'.

Clarify when quick mode applies (e.g. 'Use --quick for fast mid-session saves') to make the 'when' clause fully explicit.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('Turn the current conversation or finding into a structured permanent wiki note', 'QUICK MODE writes a fast _raw/ note') but omits correction mode, classification, and index updating, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Turn the current conversation or finding into a structured permanent wiki note') and when ('Use for save/capture/preserve requests'), but the 'when' is terse and does not distinguish when quick mode vs. full mode applies, keeping it short of the level-5 anchor.

4 / 5

Trigger Term Quality

'Use for save/capture/preserve requests' plus a concrete invocation example ('@research save this') gives good natural keyword coverage, but misses common variations like 'remember this', 'note this down', or 'log this'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (conversation-to-wiki capture) with an explicit boundary — 'This captures current discussion, not external source ingestion' — that disambiguates it from the closely related ingestion skill, matching the clear-niche anchor with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Ar9av/obsidian-wiki

Path

.skills/wiki-capture/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.