CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-synthesize

Find recurring concept combinations across the wiki that lack an explicit synthesis page, then create cross-cutting synthesis pages. Use for knowledge synthesis after the vault has accumulated enough material.

Quality

81%

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

82%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 strong, highly operational skill body: every step is backed by concrete commands, a numeric scoring rubric, a complete page template, and exact CLI invocations with fallbacks. The only weaknesses are minor — some trimmable explanatory prose, a checklist that runs after the locked index update rather than before it, and template/QMD detail that could be split into reference files.

DimensionReasoningScore

Conciseness

The body is dense and operational throughout — every step carries commands, thresholds, or templates. Minor instances of over-explanation could be trimmed, e.g., "this signals to readers that it's a synthesis page, not a page about either concept alone" and template prose restating what each section is for ("This is the point of the page — the thing you couldn't see from either concept page alone"), so it fits 'efficient; minor instances of over-explanation' rather than the lean anchor 5.

4 / 5

Actionability

Fully executable guidance: a concrete rg command for backlink collection ("rg -l --glob '*.md' \"\\\\[[ConceptA\\]]\\" \"$OBSIDIAN_VAULT_PATH\""), an explicit numeric scoring table, a copy-paste synthesis page template with complete frontmatter, exact commands ("obsidian-wiki memory sync WIKI_SYNTHESIZE pages_scanned=<N> ... --takeaways", "${QMD_CLI:-qmd} update"), a report format, and worked examples ("[[Caching]] × [[Consistency]] — co-occurs in 4 pages, cross-domain"). Matches 'fully executable; copy-paste ready code or commands'.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with a Quality Checklist, an explicit error-recovery path ("If QMD refresh fails, do not roll back the vault changes; report the QMD status separately"), and conditional follow-up ("If the output says vectors are needed... run embed"). Not anchor 5 because the Quality Checklist appears after Step 7's locked sync, meaning index/log/hot are already updated before synthesis pages are validated against it — a minor validation-ordering gap.

4 / 5

Progressive Disclosure

Well-organized sections (Before You Start, Steps 1-7, Checklist, Tips, QMD) with external detail correctly deferred one level deep and clearly signaled ("follow the Config Resolution Protocol in llm-wiki/SKILL.md", "See .skills/llm-wiki/references/MEMORY.md for the full procedure"). Minor organization gaps: the ~50-line page template and the conditional QMD refresh section could live in bundle reference files, keeping the core workflow leaner.

4 / 5

Total

17

/

20

Passed

Description

70%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 clearly states what the skill does and includes an explicit use-for clause, written in third person without fluff. Its main weaknesses are limited action coverage (two actions) and a trigger condition that is a vague maturity precondition rather than concrete trigger phrases a user would say.

Suggestions

Broaden the action list beyond the core find/create pair, e.g., 'score and rank synthesis candidates, draft pages with provenance metadata, and back-link from source pages'.

Replace or supplement the vague precondition 'after the vault has accumulated enough material' with concrete user-side triggers, e.g., 'Use when the user asks to synthesize the wiki, connect related notes, or find cross-cutting themes between concepts'.

Add one or two natural synonyms users would say (e.g., 'connect ideas', 'cross-topic pages') to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Find recurring concept combinations across the wiki that lack an explicit synthesis page, then create cross-cutting synthesis pages" names the domain and exactly two concrete actions (discover gap pairs, create synthesis pages). This matches the anchor for 1-2 concrete actions but not comprehensive coverage; anchor 4 requires several listed specific actions, which this lacks.

3 / 5

Completeness

Both 'what' and 'when' are present: the what is concrete (find concept combinations lacking synthesis pages, create cross-cutting pages) and "Use for knowledge synthesis after the vault has accumulated enough material" is an explicit trigger clause. Not anchor 5 because the 'when' is a vague precondition ("enough material") rather than concrete user-said trigger phrases.

4 / 5

Trigger Term Quality

Good keyword coverage: "wiki", "synthesis", "synthesis page", "knowledge synthesis", "cross-cutting", "vault" are terms a user would plausibly say. A few natural variations are missing (e.g., "connect notes", "find themes", "cross-link"), keeping it below anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"recurring concept combinations", "synthesis page", "cross-cutting" carve out a clear niche distinct from generic wiki-writing skills, with only minor overlap risk against closely related wiki-maintenance skills (e.g., wiki-status/insights). Matches 'mostly distinct; minor overlap risk'.

4 / 5

Total

15

/

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-synthesize/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.