mixpanel-automation
Automate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries. Always search tools first for current schemas.
77
66%
Does it follow best practices?
Impact
97%
1.29xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/mixpanel-automation/SKILL.mdQuality
Discovery
82%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 the tool (Mixpanel via Rube MCP/Composio) and lists specific capabilities. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness. The trigger terms are excellent and highly distinctive for the analytics domain.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Mixpanel analytics, tracking events, building funnels, or querying user behavior data.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: events, segmentation, funnels, cohorts, user profiles, JQL queries. Also specifies the integration method (Rube MCP via Composio) and includes a procedural instruction (search tools first for current schemas). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Mixpanel tasks with specific capabilities listed), but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the domain terms. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Mixpanel', 'events', 'segmentation', 'funnels', 'cohorts', 'user profiles', 'JQL queries'. These are terms analytics users would naturally use when requesting Mixpanel-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Mixpanel', 'Rube MCP', 'Composio', 'JQL queries' are very specific terms that carve out a clear niche. Unlikely to conflict with other skills unless there are multiple Mixpanel-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive catalog of Mixpanel workflows with clear tool sequences and parameter documentation, but suffers from repetition (date formats and expression syntax mentioned 3+ times), lack of executable examples, and missing validation/error-handling steps. The content would benefit from consolidation of repeated information, addition of concrete tool call examples with sample inputs/outputs, and explicit verification steps especially for destructive operations like batch profile updates.
Suggestions
Add at least one fully concrete tool call example per major workflow showing realistic parameters and a sample response structure, rather than pseudocode-style numbered lists.
Consolidate repeated pitfalls (date formats, expression syntax, rate limits) into a single reference section and remove duplicates from individual workflow sections to reduce token count by ~30%.
Add explicit validation/verification steps for destructive operations like MIXPANEL_PROFILE_BATCH_UPDATE (e.g., query profiles before and after update to confirm changes).
Remove 'When to use' descriptions that simply restate the obvious (e.g., 'User wants to count events' for 'Aggregate Event Data') — Claude can infer intent from context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but verbose for what it conveys. There's significant repetition across workflows (e.g., date format pitfalls repeated multiple times, expression syntax explained in individual sections AND in a dedicated Common Patterns section AND again in Known Pitfalls). The pitfalls sections per workflow could be consolidated. Claude doesn't need explanations like 'When to use: User wants to count events' for each workflow. | 2 / 3 |
Actionability | Tool names and parameter lists are concrete and specific, which is good. However, there are no executable code examples — the 'ID Resolution' patterns use pseudocode-style numbered lists rather than actual tool call examples with realistic parameters. A concrete example showing a full tool invocation with sample parameters and expected response structure would significantly improve actionability. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with prerequisite/required/optional labels, which is helpful. However, there are no validation checkpoints — no steps to verify that results are correct, no error handling guidance (what happens if a tool call fails?), and no feedback loops. For batch profile updates (a destructive operation), there's no validation step before or after the update. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with no bundle files or references to separate detailed guides. At ~200 lines, the repeated pitfalls and expression syntax documentation could be split into reference files. The quick reference table at the end is a good structural element, but the overall organization puts everything inline rather than layering appropriately. | 2 / 3 |
Total | 8 / 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.