amplitude-automation
Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.
70
60%
Does it follow best practices?
Impact
83%
1.23xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/amplitude-automation/SKILL.mdQuality
Discovery
57%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 identifies a clear and distinct niche (Amplitude automation via Rube MCP/Composio) which minimizes conflict risk, but it lacks specificity in what concrete actions are performed and is missing an explicit 'Use when...' clause. The listed capabilities read more like category headers than actionable descriptions.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Amplitude analytics, tracking events, querying cohorts, or identifying users.'
Replace the category-style list with concrete actions, e.g., 'Query event data, look up user activity, create and manage cohorts, identify users by properties' instead of just 'events, user activity, cohorts, user identification'.
Include natural trigger terms users might say, such as 'analytics', 'track', 'funnel', 'retention', or 'Amplitude dashboard'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Amplitude via Rube MCP/Composio) and lists some actions (events, user activity, cohorts, user identification), but these are more like category labels than concrete actions. It doesn't specify what it does with events or cohorts (create, query, delete?). | 2 / 3 |
Completeness | The 'what' is partially addressed (automate Amplitude tasks) but the 'when' is missing — there is no explicit 'Use when...' clause or equivalent trigger guidance. The instruction to 'always search tools first' is operational guidance, not a trigger condition. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Amplitude', 'events', 'user activity', 'cohorts', and 'user identification', but these are somewhat generic analytics terms. Missing natural user phrases like 'track events', 'analytics', 'funnel', 'retention', or file/format references users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Amplitude', 'Rube MCP', and 'Composio' creates a very specific niche that is unlikely to conflict with other skills. This is clearly about a particular integration with a particular analytics platform. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-organized skill that clearly documents Amplitude workflows with good sequencing and validation patterns. Its main weaknesses are moderate redundancy (pitfalls repeated in multiple places) and lack of fully executable examples—most guidance is pseudocode-level tool sequences rather than complete call payloads. The document would benefit from deduplication and splitting detailed reference material into separate files.
Suggestions
Deduplicate pitfalls: consolidate the per-workflow pitfalls and the 'Known Pitfalls' section into a single reference, either inline or in a separate PITFALLS.md file.
Add at least one fully complete tool call example per core workflow showing exact parameter payloads (not just pseudocode sequences), e.g., a complete AMPLITUDE_SEND_EVENTS call with all required fields populated.
Consider splitting the detailed per-workflow documentation and common patterns into a separate WORKFLOWS.md, keeping SKILL.md as a concise overview with the quick reference table and links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy—pitfalls are repeated across individual workflows and then again in the 'Known Pitfalls' section (e.g., user ID resolution, timestamps). The 'Common Patterns' section partially duplicates workflow steps already described. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Tool names and parameter lists are concrete and specific, and the JSON example for user properties is helpful. However, most 'code' blocks are pseudocode sequences rather than actual executable tool calls with complete parameter examples. More complete call examples (showing full parameter payloads) would push this to a 3. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, prerequisite/required/optional labels, and explicit validation patterns (e.g., the async cohort operation pattern with retry loop, the ID resolution prerequisite before GET_USER_ACTIVITY). The feedback loop for cohort status checking is explicit. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's a long monolithic document (~180 lines of substantive content). The common patterns, detailed pitfalls, and per-workflow details could be split into referenced files. The only external reference is the Composio toolkit docs link. | 2 / 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
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.