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 niche (Amplitude automation via Composio/Rube MCP) which makes it distinctive, but it lacks specificity in the actions it performs and omits an explicit 'Use when...' clause. The listed capabilities read more like category headers than concrete actions, and the trigger terms could better cover natural user language around analytics and tracking.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Amplitude analytics, tracking events, querying user behavior, or managing cohorts.'
Make actions more concrete by specifying verbs, e.g., 'Query event data, look up user activity, create and manage cohorts, identify users' instead of just listing nouns.
Include natural trigger terms users might say, such as 'analytics', 'tracking', 'product analytics', 'funnel', or 'retention'.
| 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 these (e.g., 'create events', 'query user activity', 'build cohorts'). | 2 / 3 |
Completeness | The 'what' is partially addressed (automate Amplitude tasks), and there's a procedural instruction ('Always search tools first'), but there is no explicit 'Use when...' clause telling Claude when to select this skill. The 'when' is only implied by the domain mention. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Amplitude', 'events', 'user activity', 'cohorts', and 'Composio/Rube MCP', but misses common user phrasings like 'analytics', 'tracking', 'funnel', 'retention', or 'product analytics'. The terms are somewhat technical and may not match how users naturally phrase requests. | 2 / 3 |
Distinctiveness Conflict Risk | The description is quite specific to Amplitude via Rube MCP (Composio), which is a narrow enough niche that it's unlikely to conflict with other skills. The combination of the specific platform and tooling makes it clearly distinguishable. | 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 competent integration skill that clearly documents tool sequences, parameters, and common pitfalls for Amplitude automation via Rube MCP. Its main weaknesses are significant content repetition (especially around user ID resolution and async patterns) and a lack of executable examples showing actual tool invocations with realistic inputs and expected outputs. The workflow clarity is strong with good sequencing and async feedback loops.
Suggestions
Consolidate repeated pitfalls (user ID resolution, timestamps, async patterns) into single authoritative sections rather than repeating them in each workflow AND in Known Pitfalls
Add at least one fully concrete tool invocation example showing actual parameters and expected response structure, rather than only pseudocode numbered steps
Consider extracting the detailed workflow sections into a separate WORKFLOWS.md reference file, keeping SKILL.md as a concise overview with the quick reference table and setup instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but contains significant repetition—pitfalls about user IDs, timestamps, and async operations are stated multiple times across workflow sections and then again in 'Known Pitfalls' and 'Common Patterns'. The quick reference table is useful but the overall document could be tightened by ~30% without losing information. | 2 / 3 |
Actionability | Tool sequences and parameter lists are clearly specified, but there are no executable code examples—only pseudocode-style numbered steps and one JSON snippet for user properties. The setup instructions are concrete, but the actual workflow guidance stays at the 'call this tool with these params' level without showing real invocation examples or expected response structures. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit prerequisite steps (e.g., FIND_USER before GET_USER_ACTIVITY), async operation patterns include polling loops for status checking, and the cohort membership workflow includes a proper feedback loop (repeat until complete or error). Validation checkpoints are present where needed. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's a monolithic ~180-line document with no bundle files. The repeated pitfalls across sections and the 'Known Pitfalls' summary section suggest content that could benefit from being split into separate reference files. However, there are no external files to reference, and the single external link is to Composio docs. | 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
d065ead
- 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.