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

82%

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

65%Weight 40%Scale 1-3

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 with strong executable examples and clear discovery workflows, weakened by its length: too much detailed reference and general analytical prose is inlined in SKILL.md instead of deferred to separate files, and destructive/batch operations lack validation guidance.

Suggestions

Move the large inlined reference blocks (full typed query signatures, the Entity CRUD method-name listing, the custom-property formula language reference, and Legacy Queries) into separate markdown files under references/ and link to them, leaving SKILL.md as an overview — this directly raises both conciseness and progressive_disclosure.

Add an explicit validation workflow for destructive and batch operations (e.g., preview with preview_deletion_filters, confirm scope, then create_deletion_request / bulk_delete_*), rather than only listing the methods, to lift the workflow_clarity cap.

Trim general analytical-principle prose ('Distrust averages', 'Counting methodology is a modeling choice') down to the Mixpanel-specific silent-default behaviors, since the underlying principles are knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — the API signatures, enum tables, and silent-default callouts are genuinely non-obvious library knowledge — but the ~1050-line body also carries general analytical-principle prose ('Distrust averages', 'Counting methodology is a modeling choice') Claude largely already knows. Not a 3 because of that explanatory padding; not a 1 because the reference content is substantive rather than padded filler.	2 / 3
Actionability	Extensive executable, copy-paste-ready code (Workspace/query examples, discovery snippets, parameter sweeps, custom-property creation, matplotlib Agg charting) plus concrete `python3 $SKILL_DIR/scripts/help.py ...` commands and real signatures. Not a 2 because guidance is concrete and complete rather than pseudocode or abstract.	3 / 3
Workflow Clarity	The discovery ('ALWAYS Do Both Steps Before Querying') and 5-step exploratory workflows are clearly sequenced with verification checkpoints, but destructive/batch operations surfaced in Entity CRUD (create_deletion_request, bulk_delete_*) are listed with no validation/preview workflow. Per the rubric's destructive-operations guideline this caps the score at 2 rather than 3.	2 / 3
Progressive Disclosure	Good one-level signaling via `help.py` ('Run help.py for the full signature') and WebFetch guide URLs, with real bundle files (scripts/help.py, scripts/auth_manager.py), but a large volume of API reference — full typed query signatures, the Entity CRUD method mega-listing, the custom-property formula language, and Legacy Queries — is inlined in SKILL.md rather than split into reference files (no references/ dir exists). Matches the anchor-2 'content that should be separate is inline' pattern; not a 1 because references are clearly signaled and not deeply nested.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, well-targeted description that pairs a clear Mixpanel-specific niche with explicit 'use when' triggers and a comprehensive set of natural analyst keywords. Its only mild weakness is verbosity — the trigger-term list is long — but every term earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'query, explore, visualize, or analyze Mixpanel data using Python' and 'read, write, or manage Mixpanel business context' — in third-person voice with no vague filler. Not a 2 because it goes beyond naming a domain to enumerate specific operations; no level above exists.	3 / 3
Completeness	Explicitly answers both what (query/analyze Mixpanel data, manage business context) and when, via the 'This skill should be used when the user asks about...' and 'Also use when...' trigger clauses. Not a 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Covers natural analyst phrasings users would actually say: 'funnel analysis', 'retention curves', 'cohort analysis', 'conversion rates', 'churn', 'DAU/MAU', 'A/B test results', 'flow analysis'. Not a 2 because the coverage is broad and variation-rich rather than a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Mixpanel product analytics and Mixpanel 'business context', a clear niche with distinct triggers unlikely to fire for other skills. Not a 2 because the Mixpanel specificity removes meaningful overlap risk.	3 / 3
	Total	12 / 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
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: 11c74d6

Reviewed: 17 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.