CtrlK
BlogDocsLog inGet started
Tessl Logo

build-dashboard

Build source-backed dashboards for monitoring performance, exploring drivers, or acting on product and business metrics. Use when the task needs a dashboard, scorecard, or monitoring view with clear metrics, filters, source definitions, and QA.

65

Quality

78%

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 ./plugins/data-analytics/skills/build-dashboard/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 well-sequenced, validation-rich workflow with clear handoff and quality bars, plus well-signaled one-level spec references. The main drag is conciseness: the runtime routing block duplicates Workflow Step 2, and some inlined mechanics belong in the referenced spec files.

Suggestions

Collapse the "Runtime Delivery Routing" configuration paragraph into Workflow Step 2 to remove the duplicated routing rules and tighten the body.

Move the detailed metric-family catalog (Reach/Volume/Value/...) into a referenced reference file, keeping only the role-mapping guidance inline in SKILL.md.

Surface the mechanics currently deferred to specifications/*.md with a brief inline pointer per surface so the skill is more self-contained without re-inlining full detail.

DimensionReasoningScore

Conciseness

Most content is substantive procedural guidance rather than padded concept explanation, but the "Runtime Delivery Routing" paragraph (line 24) substantially duplicates Workflow Step 2 and the routing prose could be tightened, so it sits at mostly-efficient-with-some-redundancy rather than 4.

3 / 5

Actionability

Concrete directives throughout: named spec files (specifications/bi-platform-dashboard.md, etc.), specific tool invocations ($gather-business-context, $analyze-data-quality, $visualize-data, $publish-artifact-to-sites, ~~structured_data), and explicit skip/render rules. As an instruction-only skill it is actionable, though the executable mechanics are deferred to external spec files rather than copy-paste ready here, keeping it below 5.

4 / 5

Workflow Clarity

An explicit 8-step sequence with validation checkpoints ("Validate trust", "Stop if source-backed data is unavailable"), a Dashboard Quality Bar checklist, and stop-gates for missing sources, matching the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

References to five spec files are clearly signaled and one level deep, but no bundle files are present and notable routing logic plus the metric-family catalog are inlined in SKILL.md rather than split into those references, leaving minor organization gaps versus the 5 anchor.

4 / 5

Total

16

/

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, well-structured description that clearly states both capability and trigger conditions with distinct, low-conflict triggers. Its only weakness is specificity: it leads with a single build action rather than enumerating several concrete dashboard-building actions.

DimensionReasoningScore

Specificity

"Build source-backed dashboards" names the domain plus one concrete action; the "monitoring performance, exploring drivers, or acting on...metrics" clause lists purposes rather than distinct build actions, so it does not reach the several-specific-actions bar of 4.

3 / 5

Completeness

It explicitly answers what ("Build source-backed dashboards for...") and when ("Use when the task needs a dashboard, scorecard, or monitoring view...") with concrete trigger phrases, matching the anchor.

5 / 5

Trigger Term Quality

Natural trigger terms appear ("dashboard, scorecard, or monitoring view" plus "metrics, filters, source definitions, and QA"), giving good coverage, but it omits common synonyms (BI, KPI) and has no extension-style triggers, falling short of comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The dashboard/scorecard/monitoring niche is clearly delimited with distinct triggers and minimal overlap with adjacent analysis or visualization 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
openai/plugins
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.