CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-dashboard

Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.

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

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 highly actionable, syntax-dense skill body that earns its length: every example is executable and the gotchas (filter expression strings, groupBy placement, rows. prefix, file.mtime date math) are exactly what Claude wouldn't know. Weaknesses are moderate: repeated boilerplate across the Bases examples, a step-numbering gap (Steps 1-2 never labeled), and a monolithic structure with no bundle files for the reference tables.

Suggestions

Consolidate the repeated properties:/order: boilerplate across the seven .base examples — show the full skeleton once, then only the differing filter/view block per pattern, trimming ~60 lines.

Fix the step numbering: label the tool-selection/query-drafting phases as Steps 1-2 so 'Step 3: Write the File' doesn't appear without predecessors, or drop numeric step labels entirely.

Move the filter-expression reference table and Dataview clause reference into a references/ file (e.g. references/bases-syntax.md, references/dataview-syntax.md) to shorten SKILL.md to an overview plus core recipes.

DimensionReasoningScore

Conciseness

The body is dense and factual with no filler explanations of concepts Claude already knows — Bases .base syntax and Dataview gotchas are genuinely novel information, and the property-conventions/filter-reference/recipes tables are token-efficient. It stops short of anchor 5 because the seven near-identical .base examples each repeat ~10 lines of properties/order boilerplate that could be consolidated. Not anchor 3, since the repetition serves distinct copy-paste recipes rather than unnecessary explanation.

4 / 5

Actionability

Fully executable, copy-paste-ready YAML and Dataview blocks covering the common cases (folder/tag/OR/multi-filters, cards, groupBy, formulas, stale pages, multi-folder), plus concrete target paths, slug examples, an exact log-line format, embed syntax, and qmd commands. Matches anchor 5's 'specific examples cover the common cases'.

5 / 5

Workflow Clarity

Clear overall sequence (resolve config → inspect index.md → choose tool → write file → optional embed → log → QMD refresh) with a quality checklist, an ask-before-modifying guard, and QMD failure handling ('do not roll back the vault changes; report the QMD status separately'). It misses anchor 5 because the numbered steps jump: headers read 'Step 3: Write the File' onward with no Steps 1-2 labeled, leaving the early sequence implicit.

4 / 5

Progressive Disclosure

Good section structure (Option A/B, canonical schema, per-pattern subsections, recipes table, checklist, QMD) and clearly signaled one-level external references to llm-wiki/SKILL.md; there are no nested or buried references. Not anchor 5: at ~470 lines with no bundle files, content like the full filter-expression and Dataview reference tables could live in a references/ file, and the simple-skill exception (under 50 lines) does not apply.

4 / 5

Total

17

/

20

Passed

Description

82%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 with an explicit 'Use for...' trigger clause, concrete trigger phrases, a useful negative boundary, and distinctive Obsidian-specific terminology. The main weakness is that it compresses capability into a single 'create views' action rather than enumerating the concrete outputs (auto-updating tables, card galleries, grouped indexes) as distinct actions.

Suggestions

Enumerate distinct concrete actions instead of one verb with output variants, e.g. 'Build auto-updating tables, card galleries, grouped indexes, and stale-content trackers' — this would lift specificity from anchor 3 to 4-5.

Add a few natural synonyms users would actually say, such as 'notes', 'wiki', 'query', or '.base files', to round out trigger-term coverage toward anchor 5.

DimensionReasoningScore

Specificity

Names the domain and tools ("Create dynamic, queryable Obsidian dashboard views using Bases or Dataview") but offers essentially one action verb with output variants ("tables, indexes, or structured views") rather than several distinct concrete actions, matching anchor 3. It does not reach anchor 4, which expects multiple distinct actions like extract/fill/convert.

3 / 5

Completeness

Explicitly answers both what ("Create dynamic, queryable Obsidian dashboard views using Bases or Dataview") and when ("Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering"), with concrete trigger phrases plus a negative boundary. This matches anchor 5 exactly; anchor 4 would require a weaker or less explicit 'when' clause.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("dashboard", "tables", "indexes", "vault", "Bases", "Dataview", "auto-updating") but misses common variations users would say such as "notes", "wiki", "query", or the ".base" file extension. Falls at anchor 4, short of anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Obsidian vault dashboards via the named Bases/Dataview tools) with highly distinctive trigger terms and an explicit anti-trigger ("not for ordinary question answering"), giving minimal conflict risk. Matches anchor 5; anchor 4 would imply residual overlap with closely related skills.

5 / 5

Total

17

/

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-dashboard/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.