mixpanelyst

This skill should be used when the user asks about Mixpanel product analytics, event data, funnel analysis, retention curves, cohort analysis, segmentation queries, user behavior, conversion rates, churn, DAU/MAU, ARPU, revenue metrics, feature adoption, A/B test results, user paths, flow analysis, or any request to query, explore, visualize, or analyze Mixpanel data using Python. Also use when the user asks to read, write, or manage Mixpanel "business context" — the markdown documentation that grounds AI assistants in an organization's structure and goals.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

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

A highly actionable, well-structured API reference that leverages help.py and WebFetch for progressive disclosure and provides strong discovery/validation workflows. Its main weakness is verbosity — general analytical-philosophy prose and inlined reference bulk inflate the body beyond a lean overview.

Suggestions

Trim the general analytical-philosophy prose (e.g. 'Distrust averages', social-vs-B2B cadence analogies) to the Mixpanel-specific quirks and silent defaults; Claude already knows to distrust averages.

Move the bulkier reference material (full per-method parameter lists, the custom-property formula reference, entity CRUD method inventories) into a separate REFERENCE.md and keep SKILL.md as an overview with links, relying more heavily on the help.py delegation pattern already in use.

Add an explicit validate-before-act feedback loop for destructive operations (e.g. preview_deletion_filters → confirm → create_deletion_request → verify) so the data-deletion workflow matches the validation rigor of the discovery workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and Mixpanel-specific, but the ~1000-line body carries substantial prose on general analytical philosophy ("Distrust averages", "Counting methodology is a modeling choice", social-vs-B2B cadence analogies) that could be tightened without losing the valuable Mixpanel-specific quirks.	3 / 5
Actionability	Fully executable, copy-paste-ready Python examples and concrete commands ("python3 $SKILL_DIR/scripts/help.py Workspace.query") cover the common query/flow/retention/user cases, matching the top anchor.	5 / 5
Workflow Clarity	The Discovery (two-step, verify-with-help.py) and Exploratory Analysis (Steps 1-5) workflows are clearly sequenced with validation checkpoints; minor gap is that destructive operations (data deletion, delete_* entity methods) are listed without an explicit validate-before-act feedback loop.	4 / 5
Progressive Disclosure	Excellent one-level-deep delegation to scripts/help.py for full signatures and WebFetch for full external references, with clear section headers; however a large volume of API reference (inlined query signatures, formula reference, entity CRUD method lists) still lives in the body rather than in separate reference files.	4 / 5
	Total	16 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 strong, third-person description with explicit trigger guidance and comprehensive natural keyword coverage. The only mild weakness is that the named actions are fairly generic verbs paired with the domain rather than a long list of distinct concrete operations.

Dimension	Reasoning	Score
Specificity	Names the Mixpanel domain and lists several concrete actions ("query, explore, visualize, or analyze Mixpanel data using Python"; "read, write, or manage Mixpanel business context"), with only minor gaps in coverage rather than the comprehensive multi-action list of a 5.	4 / 5
Completeness	Explicitly answers both what (query/explore/visualize/analyze Mixpanel data; read/write/manage business context) and when ("This skill should be used when the user asks about...") with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and acronyms users actually say — "funnel analysis, retention curves, cohort analysis, segmentation queries, conversion rates, churn, DAU/MAU, ARPU, revenue metrics, feature adoption, A/B test results, user paths, flow analysis" — matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to Mixpanel with Mixpanel-specific trigger terms and a secondary "business context" niche, giving a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	19 / 20 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
skill_md_line_count	SKILL.md is long (1060 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/mixpanel-headless/skills/mixpanelyst/SKILL.md
Commit: 1dc1958

Reviewed: 16 hours 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.