mixpanel-automation

Automate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries. Always search tools first for current schemas.

1.29x

Quality

—

Does it follow best practices?

Impact

97%

1.29x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-sequenced MCP guidance, but it is over-long for a single SKILL.md with redundant pitfall/table sections and no progressive disclosure to reference files, and the batch-update workflow lacks a verification feedback loop.

Suggestions

Move the Quick Reference table and Mixpanel expression-syntax reference into a separate REFERENCE.md and link to it from the body, trimming the main file to a lean overview.

Consolidate the per-workflow 'Pitfalls' with the 'Known Pitfalls' section to remove duplication and recover token budget.

Add a verification step after MIXPANEL_PROFILE_BATCH_UPDATE (e.g., re-query affected profiles to confirm the operation applied) to satisfy the batch-operation feedback-loop requirement.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic-concept padding), but it is redundant — per-workflow 'Pitfalls' sections are restated in a 'Known Pitfalls' section and again as a 'Quick Reference' table, so not every token earns its place.	2 / 3
Actionability	Concrete tool slugs, exact parameter names, required formats ('YYYY-MM-DD'), and worked Mixpanel expression-syntax examples make the guidance copy-paste ready; the instruction-only nature is not penalized because guidance is actionable.	3 / 3
Workflow Clarity	Sequences are numbered and the Setup flow has an explicit validation checkpoint ('Confirm connection status shows ACTIVE'), but the batch-update workflow (MIXPANEL_PROFILE_BATCH_UPDATE) has no verify/retry feedback loop, so per the rubric batch-operation workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The single file is well-organized with clear headers, but at ~220 lines it keeps reference-style material (Quick Reference table, expression-syntax reference) inline rather than splitting to reference files, so it is not a lean overview pointing one level deep.	2 / 3
	Total	9 / 12 Passed

Description

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.

A specific, third-person description with good trigger coverage and a clear niche, but it lacks an explicit 'Use when...' clause, capping completeness at 2. Adding a trigger clause would raise the score.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to query or automate Mixpanel analytics, funnels, cohorts, or user profiles') to satisfy the completeness 'when' requirement.

Include common user phrasings like 'Mixpanel reports', 'event trends', or 'conversion funnels' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'events, segmentation, funnels, cohorts, user profiles, JQL queries' — matching the anchor for enumerating several specific capabilities rather than vague domain mention.	3 / 3
Completeness	Clearly states what it does ('Automate Mixpanel tasks via Rube MCP...') but the second sentence ('Always search tools first for current schemas') is procedural guidance, not an explicit 'Use when...' trigger, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Covers natural Mixpanel-domain terms a user would actually say (events, segmentation, funnels, cohorts, JQL) plus the integration surface (Rube MCP, Composio), giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The Mixpanel niche via Rube MCP/Composio is specific and distinct, with triggers unlikely to collide with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 2b23b55

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.