CtrlK
BlogDocsLog inGet started
Tessl Logo

building-a-dashboard

Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP. Use when a user asks to create a dashboard, put several metrics/charts together on one page, assemble a dashboard for a topic (product analytics, retention, revenue, activation, etc.), or add/remove/replace insights on a dashboard they already have. Covers deciding create vs update, reusing existing insights vs creating new ones, and using PostHog's vetted dashboard templates as reference for what a strong dashboard on a topic looks like.

72

Quality

87%

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 tightly written, actionable orchestration guide with a clear workflow and an explicit verification step. Its main gap is the absence of an explicit error-recovery feedback loop around the verify step for batch/destructive tile updates.

Suggestions

Add an explicit feedback loop after the 'dashboard-insights-run' verification step — e.g., 'If a tile returns no data, fix or remove the insight and re-run before summarizing.'

Tighten the opening by dropping or merging the definitional sentence ('A dashboard is a collection of insight tiles on one page'), which Claude can already infer.

Make the inline reference to query shapes concrete — name the specific product-analytics insight skill file rather than 'see the product-analytics insight skills for query shape'.

DimensionReasoningScore

Conciseness

Largely lean and action-oriented, assuming Claude's competence throughout; only minor instances of borderline over-explanation (e.g., 'A dashboard is a collection of insight tiles on one page') could be trimmed without loss.

4 / 5

Actionability

Provides concrete, executable guidance via named MCP tools with their key parameters and behaviors (e.g., 'dashboards-get-all' with a 'search' param, 'dashboard-update' where 'insights you omit are removed'), fully covering the common create/update cases for an instruction-only skill.

5 / 5

Workflow Clarity

A clear sequenced workflow (create-vs-update → templates → select insights → assemble → verify) with an explicit verification checkpoint ('Verify with dashboard-insights-run to confirm the tiles return data') and a destructive-operation warning, though it lacks an explicit validate-fix-retry feedback loop.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with one-level-deep, clearly signaled pointers to related skills ('managing-subscriptions', 'creating-ai-subscription'); the body is slightly over 50 lines and the inline 'see the product-analytics insight skills for query shape' reference is a touch hand-wavy.

4 / 5

Total

17

/

20

Passed

Description

92%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 precise, well-scoped description that clearly conveys both capability and trigger conditions with concrete, natural language. It borders on slightly long but earns its tokens with specific actions and explicit 'Use when' guidance.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build a new dashboard, or update an existing one', 'put several metrics/charts together on one page', 'add/remove/replace insights', 'reusing existing insights vs creating new ones', and consulting 'vetted dashboard templates' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (build/update a dashboard from insights, decide create-vs-update, reuse vs create, use templates) and when ('Use when a user asks to create a dashboard... or add/remove/replace insights on a dashboard they already have') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural phrasings users would say ('create a dashboard', 'put several metrics/charts together on one page', 'assemble a dashboard for a topic', 'add/remove/replace insights') with synonyms across build/create/assemble, though a few common variations are not enumerated.

4 / 5

Distinctiveness Conflict Risk

A clear PostHog/MCP dashboard niche with distinct collection-level triggers and explicit scope framing ('the same job the in-app assistant does with its upsert-dashboard tool, but over MCP'), keeping conflict with single-insight skills minimal.

5 / 5

Total

19

/

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
PostHog/posthog
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.