analyze-chart
Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 well-crafted description that clearly communicates both purpose and trigger conditions. It excels at distinctiveness by anchoring to Amplitude specifically and includes natural language users would employ when investigating metric anomalies. The only minor weakness is that the specific capabilities could be slightly more detailed regarding what concrete outputs or analyses are performed.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Amplitude chart analysis) and some actions (explain trends, anomalies, drivers), but doesn't list multiple concrete actions like identifying specific chart types, comparing segments, or generating hypotheses with data breakdowns. | 2 / 3 |
Completeness | Clearly answers both what ('Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers') and when ('Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'spike', 'drop', 'metric looks unusual', 'why behind numbers', 'trends', 'anomalies', and 'Amplitude chart' — these cover common variations of how users describe investigating data changes. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Amplitude chart analysis with a clear niche around investigating anomalies and explaining drivers. The combination of 'Amplitude' + 'chart' + 'spike/drop' investigation makes it unlikely to conflict with general analytics or other data skills. | 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 well-structured, actionable skill with clear step sequencing, explicit validation gates, and specific tool references that make it highly executable. Its main weakness is moderate verbosity—some sections could be tightened—and the lack of any external file references for supplementary detail, though the latter is a minor issue given the skill's scope. Overall it's a strong skill that effectively guides Claude through a complex analytical workflow.
Suggestions
Consider extracting the Step 5 synthesis template into a separate TEMPLATE.md file and referencing it, to reduce the main skill's length and improve progressive disclosure.
Tighten the 'When to Use' section—Claude can infer most of these use cases from the skill title and instructions; 1-2 bullets would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but some sections are slightly verbose—e.g., the 'When to Use' bullets and the detailed synthesis template could be tightened. The enumeration of all five synthesis sub-sections is borderline necessary vs. over-specified for Claude. | 2 / 3 |
Actionability | Each step references specific tool calls (e.g., `Amplitude:getting_data_from_url`, `Amplitude:query_charts`, `Amplitude:get_feedback_insights`) with clear instructions on when and how to use them. Constraints like 'up to 9 properties' and 'up to 3 charts at a time' are concrete and actionable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0–5) with explicit validation checkpoints—Step 1 has a hard stop if data is missing, Step 3 bounds exploration, and Step 4 is marked as required for anomalies. The feedback loop of 'if chart data cannot be retrieved, do not proceed' prevents cascading errors. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's entirely self-contained with no references to external files for detailed guidance (e.g., tool reference docs, example outputs, or advanced segmentation strategies). For a skill of this length (~100 lines), some content like the full synthesis template or best practices could be split out. | 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.