CtrlK
BlogDocsLog inGet started
Tessl Logo

build-dashboard

Build a source-backed dashboard or monitoring view with clear metrics, filters, visual hierarchy, definitions, refresh context, and QA.

63

Quality

74%

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 ./packages/opencode/src/skill/builtin/.bundle/data-analytics/workflows/build-dashboard/SKILL.md
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 concise, well-structured, single-purpose skill body with an explicit workflow and solid validation/QA checkpoints, held just below top marks by absent referenced specification files and the lack of an explicit retry loop and external file split.

Suggestions

Add the referenced bundle files (specifications/streamlit-dashboard.md and specifications/html-dashboard.md) or remove the references so the skill is self-contained.

Spell out an explicit validate-then-fix-retry loop for the data-validation step (e.g., 'If joins, completeness, or duplicates fail validation, correct the query and re-validate before proceeding').

Tighten high-level directives such as 'Validate joins, completeness, duplicates...' with one concrete method or command per check to push actionability toward fully executable.

DimensionReasoningScore

Conciseness

The body is lean and non-padded, assuming Claude's competence throughout (e.g., 'Honor the user's destination. Otherwise choose the simplest surface supported by the harness') with no explanation of what a dashboard is or how libraries work, matching the level-5 'every token earns its place' anchor.

5 / 5

Actionability

As an instruction-only skill it gives concrete, specific guidance (named surfaces, a detailed metric-definition checklist covering formula through freshness, and 'Use ../visualize-data/SKILL.md for each chart'), but several steps are high-level directives and the referenced specification files do not exist in the bundle, leaving minor gaps below the fully-executable level-5 anchor.

4 / 5

Workflow Clarity

There is a clear eight-step sequence with explicit validation checkpoints (step 3 'Validate joins, completeness, duplicates...' and step 8 testing 'representative, empty, partial, and error states') plus a QA section, but no explicit validate-fix-retry loop is written out, leaving it just below the level-5 feedback-loop anchor.

4 / 5

Progressive Disclosure

The under-50-line body is well organized into 'Select a portable surface', 'Workflow', and 'QA and handoff' sections with clearly signaled one-level-deep references, but the referenced specification files are absent from the bundle and no content is actually split into separate files, keeping it below the level-5 anchor.

4 / 5

Total

17

/

20

Passed

Description

66%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 specific, well-scoped description with strong attribute coverage and natural trigger terms, held back from the top tier by the absence of an explicit 'Use when...' trigger clause and the reliance on a single action verb.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user needs a reusable dashboard, monitoring view, or live KPI report rather than a one-time analysis').

Lead with two or three distinct action verbs (e.g., 'Build, design, and validate a source-backed dashboard...') to match the multi-action pattern of the top-anchor examples.

Include natural synonyms users might say such as 'KPI view', 'analytics view', or 'monitor' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('Build a source-backed dashboard or monitoring view') and enumerates a comprehensive list of concrete deliverable attributes ('clear metrics, filters, visual hierarchy, definitions, refresh context, and QA'), but relies on a single action verb rather than the multiple distinct actions exemplified by the level-5 anchor.

4 / 5

Completeness

It provides a clear and specific 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric guideline a missing 'when' caps completeness at 3 rather than the strong-but-still-vague level 2 or the explicit-trigger level 4.

3 / 5

Trigger Term Quality

'dashboard' and 'monitoring view' are natural phrases a user would say, and 'metrics' and 'filters' add relevant coverage, but common synonyms such as 'report', 'KPI view', or 'analytics view' are missing, falling short of the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The 'source-backed' qualifier plus the QA/definitions/refresh-context framing carve a clear niche distinct from generic reporting or visualization skills, with only minor overlap risk against a closely related data-viz skill.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
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.