posthog-automation

Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools first for current schemas.

1.44x

Quality

66%

Does it follow best practices?

Impact

100%

1.44x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/posthog-automation/SKILL.md

Quality

Content

67%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 well-structured, highly actionable MCP-navigation skill with exact tool slugs, parameters, pitfalls, and a validated setup sequence. Its main weakness is redundancy — pitfalls and tool listings are stated two to three times across sections — which inflates token cost without adding guidance.

Suggestions

Consolidate 'Known Pitfalls' with the per-workflow 'Pitfalls' blocks (or vice versa) so each caution is stated once, cutting roughly 30 lines of duplication.

Drop the 'Quick Reference' table or reduce it to task-to-tool mapping only, since the key parameters are already listed per workflow.

Add brief validation steps after impactful actions — e.g., 'after creating a flag, call POSTHOG_RETRIEVE_FEATURE_FLAG_DETAILS to confirm its configuration' — to close the workflow-clarity gap.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tool sequences, parameter lists, pitfalls), but 'Known Pitfalls' repeats workflow pitfalls nearly verbatim — '$pageview' prefix rules, kebab-case flag keys, unique flag keys, pagination guidance — and the 'Quick Reference' table re-lists the same tools and parameters a third time. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the 'minor instances' anchor above.	3 / 5
Actionability	Exact tool slugs (POSTHOG_CAPTURE_EVENT, POSTHOG_LIST_AND_MANAGE_PROJECT_FEATURE_FLAGS), required/optional markers, key parameters, concrete ID-resolution sequences, and an executable feature-flag targeting JSON make the guidance mostly executable. It sits below 'fully copy-paste ready' only because no example shows the actual MCP call invocation syntax or a response to parse.	4 / 5
Workflow Clarity	The Setup section has a numbered sequence with explicit checkpoints ('Verify Rube MCP is available...', 'Confirm connection status shows ACTIVE before running any workflows'), and each workflow is sequenced with [Required]/[Optional] markers plus ID-resolution patterns. Minor validation gaps remain — e.g., no verify-step after creating a flag with 'active: true' or after batching events — placing it just below the explicit-feedback-loop anchor.	4 / 5
Progressive Disclosure	No bundle files exist, and the single-file body is well-sectioned (Prerequisites, Setup, Core Workflows, Common Patterns, Quick Reference) with a clearly signaled external docs link and no nested references. It is not a 5 because roughly 100 lines of per-tool parameter tables and targeting detail could plausibly live in one-level-deep reference files, leaving SKILL.md as a leaner overview.	4 / 5
	Total	15 / 20 Passed

Description

65%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 focused, reasonably specific description that clearly identifies the PostHog automation niche and its concrete object areas, held back by a generic action verb and the complete absence of a 'when to use' trigger clause. Adding explicit usage triggers and natural synonyms would raise both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user mentions PostHog, product analytics, feature flags, or sending tracking events.'

Replace the generic verb 'Automate PostHog tasks' with concrete actions such as 'Capture and query events, create and manage feature flags, and inspect projects and user profiles'.

Include natural synonyms users would say — 'product analytics', 'rollout', 'flag rollout percentage', 'experiments' — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('PostHog tasks via Rube MCP (Composio)') and lists five concrete object areas ('events, feature flags, projects, user profiles, annotations'), but the only action verb is the generic 'Automate... tasks'. This matches the anchor of naming the domain with concrete coverage but not comprehensive specific actions, sitting below the 'several specific actions' anchor.	3 / 5
Completeness	The 'what' is clearly stated (automate PostHog events, flags, projects, profiles, annotations), but there is no 'Use when...' clause or equivalent explicit trigger guidance — only an operational instruction ('Always search tools first'). Per the judging guidelines, a missing explicit trigger clause caps completeness at 3; it does not fall to 2 because the 'what' is concrete.	3 / 5
Trigger Term Quality	Natural user terms like 'PostHog', 'feature flags', 'events', and 'user profiles' are present and would be said by users needing this skill. A few natural synonyms are missing ('product analytics', 'experiments', 'cohorts', 'dashboards'), which fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive one.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche — PostHog product analytics and feature flag automation through a specific MCP route ('Rube MCP (Composio)') — with distinct trigger terms unlikely to fire for other skills. Minor overlap with other Composio/Rube toolkit skills exists but does not lower it below the minimal-conflict anchor.	5 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/posthog-automation/SKILL.md
Commit: b90e2de

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.