Name: posthog
Rating: 60.8 (1 reviews)
Author: membranedev

posthog

PostHog integration. Manage Persons, Groups, Events, Experiments, Dashboards, Annotations. Use when the user wants to interact with PostHog data.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/posthog/SKILL.md

Quality

Content

68%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 body is highly actionable with executable commands and a well-structured connection workflow, but it loses points for an unnecessary introductory explanation of PostHog and for lacking verification steps around its destructive create/update actions.

Suggestions

Delete or drastically shorten the opening paragraph explaining what PostHog is — Claude already knows this.

Add a verification/check step after mutating actions (e.g. re-fetch the created flag/dashboard with 'membrane action run get-... ' and confirm the returned state) so destructive workflows have a feedback loop.

Consider moving the popular-actions table and proxy-options flags into a reference file referenced from SKILL.md to improve progressive disclosure for this 170+ line skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the opening paragraph ('PostHog is an open-source platform... Essentially, it's a comprehensive tool...') explains what PostHog is — a concept Claude already knows — and could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready, executable commands for every stage ('npm install -g @membranehq/cli@latest', 'membrane connection ensure ... --json', 'membrane action run ... --input ...', plus a full proxy-flags table), covering the common cases.	5 / 5
Workflow Clarity	The connection workflow has explicit state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-again feedback loop, but the skill exposes destructive/mutating actions (Create/Update Feature Flag, Dashboard, Cohort) with no verification step, capping this dimension at 3 per the destructive-operations guideline.	3 / 5
Progressive Disclosure	Sections are clearly headed and well-organized with no nested references, and no bundle files exist; the ~178-line body is navigable, though the large popular-actions table and proxy-options reference could plausibly live in separate files.	4 / 5
	Total	15 / 20 Passed

Description

75%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 solid: it names a specific product, enumerates concrete managed entities, and includes an explicit 'Use when' trigger. It falls just short of top marks because 'Manage' is a generic verb and the 'when' clause is broad rather than rich with natural trigger synonyms.

Suggestions

Replace the generic verb 'Manage' with specific actions, e.g. 'Create, list, update, and inspect Persons, Groups, Events, Experiments, Dashboards, Annotations'.

Expand the 'when' clause with concrete natural triggers, e.g. 'Use when the user wants to list or analyze PostHog events, persons, feature flags, experiments, or dashboards'.

Add the natural synonyms already used in the body (feature flags, A/B tests, cohorts, insights) so trigger matching covers more user phrasings.

Dimension	Reasoning	Score
Specificity	Lists concrete entities ('Manage Persons, Groups, Events, Experiments, Dashboards, Annotations') covering multiple capabilities, but the single catch-all verb 'Manage' is less granular than distinct action verbs, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Both 'what' ('Manage Persons, Groups, Events, Experiments, Dashboards, Annotations') and 'when' ('Use when the user wants to interact with PostHog data') are present, but the 'when' clause is generic rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	'PostHog' plus the entity names are natural terms users would say, but common synonyms surfaced in the body (feature flags, A/B testing, cohorts, insights) are missing, so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	'PostHog integration' names a specific product giving it a clear niche with minimal conflict risk, though 'interact with PostHog data' is broad enough to allow minor overlap with adjacent analytics skills.	4 / 5
	Total	16 / 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: membranedev/application-skills
Path: skills/posthog/SKILL.md
Commit: f484c82

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.