create-dashboard
Builds comprehensive Amplitude dashboards from requirements or goals, organizing charts into logical sections with appropriate layouts. Use when creating a complete dashboard from scratch or assembling existing charts into a cohesive view.
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./analytics-skills/skills/create-dashboard/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with a clear 'Use when' clause and a well-defined niche around Amplitude dashboards. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., chart types, metric configuration), and the trigger terms could include more natural user language variations.
Suggestions
Add more specific concrete actions such as 'configures chart types, sets metrics and filters, defines time ranges' to improve specificity.
Include additional natural trigger terms users might say, such as 'analytics dashboard', 'metrics view', 'reporting', or 'data visualization in Amplitude'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Amplitude dashboards) and some actions (organizing charts into sections, appropriate layouts), but doesn't list multiple concrete specific actions like configuring metrics, setting filters, or defining chart types. | 2 / 3 |
Completeness | Clearly answers both what ('Builds comprehensive Amplitude dashboards from requirements or goals, organizing charts into logical sections with appropriate layouts') and when ('Use when creating a complete dashboard from scratch or assembling existing charts into a cohesive view'). | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'Amplitude', 'dashboards', 'charts', and 'sections', but misses common user variations like 'analytics dashboard', 'metrics view', 'reporting dashboard', or 'data visualization'. | 2 / 3 |
Distinctiveness Conflict Risk | The specificity to 'Amplitude dashboards' creates a clear niche that is unlikely to conflict with other skills. The distinction between building from scratch vs assembling existing charts further narrows the scope. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured skill for building Amplitude dashboards with clear step-by-step workflow and useful reference tables. Its main weaknesses are the lack of concrete tool call examples (showing exact payloads for create_dashboard) and missing validation/verification steps after dashboard creation. Some generic product-thinking guidance could be trimmed to improve conciseness.
Suggestions
Add a concrete example of a complete `Amplitude:create_dashboard` tool call with actual JSON payload showing rows, chartMetas, and rich text blocks configured together.
Add an explicit validation step after Step 4 (e.g., 'Verify the dashboard by retrieving it and confirming all charts render with data') to create a feedback loop.
Remove generic product-thinking prompts like 'Who is the audience?' and 'What decisions will it inform?' — Claude can infer these contextually without explicit reminders.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary guidance that Claude would naturally know (e.g., 'Ask user for clarification on primary goals' and 'Who is the audience?' are generic product thinking prompts). The layout guidelines table and best practices are useful but some items like 'Put most important metrics above the fold' are common sense for Claude. | 2 / 3 |
Actionability | The skill references specific tool names (Amplitude:search, Amplitude:create_dashboard, etc.) and provides concrete parameters like column widths and height values, which is good. However, there are no executable code examples or complete tool call examples showing exact JSON payloads. The chartMetas display configurations are listed but not shown in a concrete create_dashboard call. | 2 / 3 |
Workflow Clarity | The steps are clearly sequenced (0-5) with logical progression from discovery to adding context. However, there are no explicit validation checkpoints — no step to verify the dashboard rendered correctly, no feedback loop for checking chart data before assembling the dashboard, and the troubleshooting section at the end is disconnected from the workflow rather than integrated as validation steps. | 2 / 3 |
Progressive Disclosure | For a skill with no bundle files, the content is well-organized with clear sections (Instructions with numbered steps, Layout Guidelines table, Best Practices, Common Issues). The structure is flat and easy to navigate, and the content length is appropriate for a single file without needing external references. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.