create-chart
Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%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 strong description that clearly identifies a specific tool (Amplitude), lists concrete capabilities (event selection, filters, groupings, visualization), and includes an explicit 'Use when' clause. The main weakness is that trigger term coverage could be broader — users might search for 'analytics', 'metrics', 'dashboard', or 'funnel' and not match this skill. The 'Use when' clause uses second person ('you know', 'you want') which is slightly off from the preferred third-person voice but is within the 'Use when' guidance clause so is less problematic.
Suggestions
Expand trigger terms to include common user phrases like 'analytics', 'metrics', 'dashboard', 'funnel', 'retention chart', or 'graph' to improve discoverability.
Rephrase the 'Use when' clause to avoid second person: e.g., 'Use when the user wants to measure something in Amplitude without building the chart manually.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates Amplitude charts', 'event selection', 'filters', 'groupings', and 'visualization choices'. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices') and when ('Use when you know what you want to measure but prefer not to build the chart manually'). | 3 / 3 |
Trigger Term Quality | Includes good terms like 'Amplitude', 'charts', 'natural language', 'event', 'filters', 'groupings', and 'visualization', but misses common user variations like 'analytics', 'metrics', 'dashboard', 'funnel', 'retention', or 'graph'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — 'Amplitude charts' is a specific product/domain that is unlikely to conflict with other skills. The combination of Amplitude + chart creation + natural language is highly distinctive. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill that provides concrete tool calls, JSON structures, and a well-sequenced workflow with verification steps. Its main weakness is length — the chart type reference section is extensive and could benefit from being split into a separate file. The event discovery guidance with good/bad examples is particularly well done.
Suggestions
Extract the detailed chart type descriptions and JSON structure examples into a separate CHART_TYPES_REFERENCE.md file, keeping only the summary table in the main SKILL.md
Consolidate the chart type table and the 'Quick Reference' section to eliminate redundancy — they cover the same information twice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., chart type selection table followed by detailed descriptions that repeat much of the same info). Some sections like the 'Quick Reference' repeat what's in the table. However, it mostly avoids explaining concepts Claude already knows and stays focused on Amplitude-specific guidance. | 2 / 3 |
Actionability | Provides concrete tool calls (Amplitude:search, Amplitude:get_event_properties, etc.), specific JSON structures for chart definitions, filters, segments, and cohorts. The examples are copy-paste ready with real parameter names and values. Decision criteria and good/bad examples for event discovery are highly actionable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (get context → discover events → evaluate → find similar charts → get properties → build definition → create chart → verify → save). Includes explicit verification steps (step 8), error handling with retry guidance, and a feedback loop for zero results. The 'Planning First' section adds a pre-workflow decomposition step. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's a long monolithic file (~200+ lines) with no references to external files. The chart type selection details, JSON structure examples, and error handling could be split into separate reference files. For a skill of this complexity, some progressive disclosure to supporting files would improve navigability. | 2 / 3 |
Total | 10 / 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.