posthog-analytics

PostHog analytics, event tracking, feature flags, dashboards

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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 concrete code and naming conventions, but it is a monolithic ~950-line document with padded inline reference material and workflows that lack explicit validation checkpoints. Splitting templates and catalogs into reference files and tightening explanations would meaningfully improve it.

Suggestions

Move the four dashboard templates and the full event catalog into separate reference files (e.g. DASHBOARDS.md, EVENTS.md) and link to them one level deep, leaving SKILL.md as an overview.

Add explicit validation/feedback checkpoints to the MCP dashboard-creation workflow (e.g. verify the query result before insight-create, confirm the insight was added before moving on).

Trim framework install sections to the essentials and remove explanatory commentary Claude already knows, to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The ~950-line body is actionable per section but overall padded: full install snippets for four frameworks, four fully inlined dashboard templates, and broad event/debugging catalogs that assume little of Claude's knowledge and could be trimmed or moved to reference files.	2 / 3
Actionability	Concrete executable code across Next.js, React, Python, Node, copy-paste-ready event naming conventions with good/bad examples, and explicit PostHog MCP tool calls make the guidance fully actionable.	3 / 3
Workflow Clarity	Sequences are present (numbered dashboard-creation workflow, install steps) but validation checkpoints and error-recovery feedback loops are largely implicit or absent, e.g. the MCP dashboard flow lists steps without verifying results before proceeding.	2 / 3
Progressive Disclosure	No bundle files exist and the entire skill is one monolithic ~950-line SKILL.md with dashboard templates and reference catalogs inlined; organization into clear sections helps, but large blocks that should be separate are kept inline.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 distinctive and uses natural trigger terms, but reads as a category list rather than concrete actions and omits any explicit 'when to use' trigger within the description field itself (it relies on a separate when-to-use field). Tightening it into specific verbs and folding in the trigger would lift it.

Suggestions

Rewrite the description as concrete actions, e.g. 'Track events, identify users, and toggle feature flags in PostHog, and build project-specific dashboards.'

Append an explicit trigger clause to the description, e.g. 'Use when adding PostHog analytics, feature flags, or event tracking.'

Dimension	Reasoning	Score
Specificity	The phrase 'PostHog analytics, event tracking, feature flags, dashboards' names the domain and several capability areas, but these are noun-like categories rather than concrete verbs (e.g., 'track events', 'toggle flags', 'build dashboards'), so it does not reach the 'multiple specific concrete actions' anchor.	2 / 3
Completeness	The description field states what the skill does but contains no 'Use when...' clause; the trigger guidance lives in a separate 'when-to-use' field, so per the rubric a missing explicit trigger in the description caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms a user would say — 'PostHog', 'analytics', 'event tracking', 'feature flags', 'dashboards' — are present with good coverage and no jargon, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Tying capabilities explicitly to PostHog gives it a clear niche unlikely to trigger for other analytics tools, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (957 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Commit: 9dacc46

Reviewed: about 6 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.