CtrlK
BlogDocsLog inGet started
Tessl Logo

dashboard-expert

Full CRUD and analysis for Mixpanel dashboards. Use when the user asks to build, create, analyze, read, understand, explain, modify, update, enhance, or manage dashboards, or asks about dashboard layout, text cards, or report arrangement. Covers dashboard analysis (read + understand existing), creation (new builds), modification (update existing), and explanation (data-driven annotation).

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-structured with appropriate progressive disclosure to four real reference files. Its main weaknesses are redundancy between the Quick Start and detailed sections and the absence of an explicit post-change validation step in the destructive Modify workflow.

Suggestions

De-duplicate the Quick Start snippets against the detailed mode phases, or collapse the Quick Start sections into pointers to the relevant phases, to reduce token redundancy.

Add an explicit post-change verify/feedback step to Mode: Modify (e.g. re-read the dashboard and confirm cells/rows match the plan after the PATCH), mirroring Build's Phase B5.

Prune Critical Gotchas entries that merely restate inline warnings (e.g. #1, #9), or move the inline warnings to the Gotchas list to keep each rule in one place.

DimensionReasoningScore

Conciseness

Content is dense and actionable without explaining basic concepts, but the Quick Start snippets duplicate code that reappears in the detailed mode phases and the Critical Gotchas restate inline warnings (e.g. combined content+layout PATCH, strip-\n), so it could be tightened; not 3 due to this redundancy, not 1 because it is not padded with concepts Claude already knows.

2 / 3

Actionability

Provides executable Python with real method calls, params, and data structures across all four modes (e.g. ws.create_dashboard(CreateDashboardParams(...)), update_dashboard with content/layout actions), copy-paste ready; not the level below because the examples are complete rather than pseudocode.

3 / 3

Workflow Clarity

Sequencing is strong (Build phases B1-B5, Modify operation order with an explicit "must follow this sequence") and Build includes validation (B1 investigate, B5 verify), but destructive Modify operations execute without an explicit post-change verify/feedback loop, which caps clarity at 2; not 1 because the sequences are explicit, not 3 because of the missing validation checkpoint on destructive edits.

2 / 3

Progressive Disclosure

The body is an operational overview that pushes exhaustive detail to four one-level-deep reference files (dashboard-reference.md, dashboard-templates.md, bookmark-pipeline.md, chart-types.md), all confirmed present and clearly signaled both inline and in See Also; not the level below because the split is clean and navigation is explicit rather than loosely organized.

3 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete with an explicit Use-when clause, all in third-person voice. It clearly delimits a distinct Mixpanel-dashboards niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists many concrete actions — "build, create, analyze, read, understand, explain, modify, update, enhance, or manage dashboards" — and enumerates the four capability areas, matching the anchor for multiple specific concrete actions; not the level below because it is comprehensive rather than naming only a few actions.

3 / 3

Completeness

Explicitly states what ("Full CRUD and analysis for Mixpanel dashboards") and when ("Use when the user asks to build, create, analyze...") with an explicit Use-when clause; not the level below because the trigger guidance is explicit, not merely implied.

3 / 3

Trigger Term Quality

Natural user-facing terms ("build", "analyze", "modify", "dashboard layout", "text cards", "report arrangement") give broad coverage of phrasings a user would actually say; not the level below because it includes common variations rather than only a few keywords.

3 / 3

Distinctiveness Conflict Risk

Scoped to "Mixpanel dashboards" with distinctive triggers unlikely to fire for unrelated skills; not the level below because the niche is clear rather than a broad domain that could overlap other skills.

3 / 3

Total

12

/

12

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
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.