CtrlK
BlogDocsLog inGet started
Tessl Logo

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

1.29x
Quality

67%

Does it follow best practices?

Impact

97%

1.29x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/mixpanel-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The content is a well-organized, action-oriented Mixpanel reference with clear tool sequences and a useful quick-reference table, but it is monolithic (no progressive file split) and lacks explicit validation feedback loops for batch/destructive profile updates. Adding a validation checkpoint and moving bulk reference material into separate files would lift the capped dimensions.

Suggestions

Add an explicit validate/confirm checkpoint before and after the destructive PROFILE_BATCH_UPDATE step (e.g., re-query profiles to verify applied changes) to satisfy the batch-operation feedback-loop cap.

Move the bulk reference material (expression syntax, known pitfalls, quick reference table) into one-level-deep files like REFERENCE.md or EXPRESSIONS.md, linked from a concise overview, to improve progressive_disclosure.

Tighten duplicated content — the 'Known Pitfalls' section restates date format and expression syntax already covered in workflow Pitfalls — to push conciseness from 4 toward 5.

DimensionReasoningScore

Conciseness

The body is mostly lean action-oriented reference material (tool sequences, key params, pitfalls) with little padding of concepts Claude already knows, though some Pitfalls items and the duplicate Known Pitfalls section slightly restate earlier points.

4 / 5

Actionability

Concrete tool slugs, named parameters with formats, and a Quick Reference table give mostly executable guidance, but it is tool/parameter reference rather than copy-paste code and a few flows lack full invocation examples.

4 / 5

Workflow Clarity

Workflows are sequenced with prerequisite/required markers, but the batch PROFILE_BATCH_UPDATE operation has no validate-then-confirm checkpoint and destructive/batch steps lack explicit validation feedback loops, which per the rubric caps workflow_clarity at 3.

3 / 5

Progressive Disclosure

Content is well-sectioned but entirely monolithic within SKILL.md — no bundle files exist and detailed reference material (full expression syntax, pitfalls, quick reference) is inlined rather than split into one-level-deep referenced files.

3 / 5

Total

14

/

20

Passed

Description

70%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.

The description is specific and distinct, clearly scoping a Mixpanel analytics automation niche, but it omits an explicit 'when to use' trigger clause, capping completeness at 3. Adding a 'Use when...' sentence would push completeness and overall quality higher.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to query or automate Mixpanel analytics — events, funnels, cohorts, or user profiles.' to satisfy the 'when' half of completeness.

Include a couple of natural synonyms/variations (e.g., 'product analytics', 'event tracking', 'retention') to broaden trigger_term_quality beyond the repeated 'Mixpanel' phrasing.

Voice is already third person and concrete; keep it, but consider mentioning the key deliverable (e.g., 'returns counts, segments, and conversion data') to sharpen specificity.

DimensionReasoningScore

Specificity

Lists several concrete capabilities (events, segmentation, funnels, cohorts, user profiles, JQL queries) and the operational mechanism (Rube MCP/Composio), but each action is named rather than elaborated, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clearly answered, but there is no explicit 'Use when...' or equivalent trigger clause telling Claude when to invoke the skill, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural terms (events, segmentation, funnels, cohorts, user profiles, queries) that users would say, but lacks synonyms/file extensions and the trigger clause repeats 'Mixpanel' rather than offering varied phrasings.

4 / 5

Distinctiveness Conflict Risk

The Mixpanel/analytics niche plus the Rube MCP mechanism is highly specific with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.