Name: auditing-experiments-flags
Rating: 76.8 (1 reviews)
Author: PostHog

auditing-experiments-flags

Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.

Quality

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean, actionable skill body with clear sequenced workflows and explicit failure handling. The main defect is a broken reference: flag-checks.md is linked but only the .j2 template is present in the bundle.

Suggestions

Render references/flag-checks.md.j2 to references/flag-checks.md (or update the body link to point at the .j2 file) so the referenced path actually resolves.

Add a one-line note in the Reference files section clarifying which checks live in flag-checks vs experiment-checks, so Claude can navigate without a broken hop.

Confirm all five linked reference paths resolve at load time, since a single missing file undermines the otherwise clean progressive-disclosure structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-focused — specific tool names and output formats with no padding or explanation of concepts Claude already knows; every section earns its tokens.	3 / 3
Actionability	Concrete executable guidance throughout: exact tool calls (experiment-get, feature-flag-get-all, notebooks-create), literal severity badges, link templates, and a worked example finding — copy-paste ready despite being instruction-only.	3 / 3
Workflow Clarity	Three usage modes each have numbered, sequenced steps, and explicit error-recovery loops cover partial fetch failures and unavailable activity-log data; the task is read-only so no destructive-validation checkpoint is required.	3 / 3
Progressive Disclosure	Structure is clean with a Reference files section and one-level-deep links, but the body links to ./references/flag-checks.md while only flag-checks.md.j2 exists in the bundle — that referenced path does not resolve, breaking navigation.	2 / 3
	Total	11 / 12 Passed

Description

100%

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, concise description that names a specific domain, lists concrete audit targets, and provides explicit natural-language triggers covering both what and when. Voice and trigger coverage both meet the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (PostHog experiments and feature flags) and multiple concrete audit targets — "configuration issues, staleness, and best-practice violations" — matching the multiple-specific-actions anchor; uses third-person voice ("Audit...").	3 / 3
Completeness	Explicitly answers what ("Audit PostHog experiments and feature flags for...") and when ("Read when the user asks to audit, health-check, or review...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	"audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup" gives good coverage of natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The PostHog experiments/feature-flags niche with distinct triggers (audit, health-check, flag hygiene) is unlikely to fire for unrelated skills.	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
relative_links	Relative link issues: 2 missing, 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/posthog_ai/skills/auditing-experiments-flags/SKILL.md
Commit: bb04e92

Reviewed: about 14 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.