CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

claude-dashboard

Use this for a local, data-backed dashboard, metrics page, KPI tracker, scorecard, data visualization or recurring report that opens in the bundled live editor: a page or scroll story of charts, numbers and tables over datasets (a CSV/TSV/JSON file the user has, or data you gather and attach), with a Sources panel that shows where every number comes from. Read it when creating, filling, refreshing or revising one. You write the datasets, then the page as plain HTML, into the dashboard's own store with this skill's script. Not for a static HTML mockup or a picture of a dashboard.

Quality

89%

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

85%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 an exceptionally dense, executable operational manual with best-in-class validation loops in the create/refresh workflows. Its one real structural defect is progressive disclosure: every `artifact-type/reference/*.md` pointer dangles in this bundle, and peripheral feature detail is inlined rather than split out.

Suggestions

Ship the referenced files: `artifact-type/reference/design-defaults.md`, `one-writer.md`, `features.md`, `exporting.md`, `remix.md`, `looks.md` and `design-system.md` are named throughout — the Design step depends on two of them — but none exist in the bundle, so every 'read X first' instruction dead-ends.

Move the Sharing, History and Comments sections (~120 lines) into reference files, as the body already does for features/exporting/remix, keeping SKILL.md focused on the create/fill/check/refresh loop.

Trim the History section's merge-semantics detail ('Compare, Bring back, Dismiss', line-merge rules, saved-over notices) to what the agent must act on; the rest is reader-facing UI behavior the page itself explains.

DimensionReasoningScore

Conciseness

Telegraphic, skill-specific prose that assumes competence ('d3 v7 is the global d3: helpers for common tasks. Where it lacks something, the page's own code does it') and explains nothing Claude already knows; the deduction is periphery length — the Sharing and History sections run ~45 lines each on guest-link and merge semantics detail that could be trimmed or moved out. Not a 3: there is no unnecessary explanation, only volume from genuine feature surface.

4 / 5

Actionability

Fully executable throughout: a complete command table (`node $A write-db <root> <batch.json | ->`, `check`, `open` with flags), a copy-paste JSON batch example for a source refresh, the `{"$file": "<path>"}` pattern, concrete `dash.data(id)`/`dash.calc(id, {inputs, fn, title, description})` signatures, and a complete pre-commit hook script — the common cases are covered with copy-paste-ready commands.

5 / 5

Workflow Clarity

The create workflow is numbered (Find the data → Design → Write) with explicit validation and bounded feedback loops: 'run `check <root>`… fix what it lists and run it again until `problems` is 0', then the page's own check with 'checking: run it again, 5 times at most' and 'failed:… write, check again, 2 fixes max; still failed: say so' — batch writes are validated, so no cap applies.

5 / 5

Progressive Disclosure

References are clearly signaled and one level deep, but the actual bundle contains no `artifact-type/reference/` directory — the Design step's load-bearing 'read `artifact-type/reference/design-defaults.md` and `one-writer.md` first' points at files that do not exist here, and ~120 lines of Sharing/History/Comments operational detail is inlined that belongs in separate files. Not a 2: headers, tables and per-document sections keep the structure far from 'minimal' or 'buried'; not a 4: the navigation the body depends on dead-ends.

3 / 5

Total

17

/

20

Passed

Description

91%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: explicit what and when with concrete trigger phrases, rich natural synonyms, and a helpful negative boundary that disambiguates it from static mockups. The only deductions are one second-person sentence ('You write the datasets…') and mild overlap risk via the broad term 'data visualization'.

DimensionReasoningScore

Specificity

Names multiple concrete actions across the lifecycle — 'creating, filling, refreshing or revising', 'You write the datasets, then the page as plain HTML, into the dashboard's own store with this skill's script' — which is comprehensive, but the second-person sentence ('You write the datasets…') takes one point off per the voice rule, landing it on 'several specific actions; minor gaps'.

4 / 5

Completeness

Explicitly answers both what ('a page or scroll story of charts, numbers and tables over datasets… with a Sources panel that shows where every number comes from') and when ('Use this for a local, data-backed dashboard…', 'Read it when creating, filling, refreshing or revising one'), with concrete trigger phrases and a negative boundary ('Not for a static HTML mockup or a picture of a dashboard').

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage with synonyms and formats users actually say: 'dashboard', 'metrics page', 'KPI tracker', 'scorecard', 'data visualization', 'recurring report', plus 'a CSV/TSV/JSON file the user has' — matching the synonyms-and-extensions anchor; it does not fit the 'a few natural terms missing' (4) anchor.

5 / 5

Distinctiveness Conflict Risk

Mostly distinct: 'local, data-backed… that opens in the bundled live editor' plus the 'Not for a static HTML mockup or a picture of a dashboard' exclusion carves a clear niche, but the broad trigger 'data visualization' keeps minor overlap risk with generic chart-rendering skills, so it sits above 'somewhat specific' but below 'minimal conflict risk'.

4 / 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

skill_md_line_count

SKILL.md is long (505 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

JimLiu/baoyu-design

Path

dsh-plugins/dsh-claude-dashboard/skills/claude-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.