CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./products/posthog_ai/skills/auditing-experiments-flags/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured, lean, and covers edge cases (partial failures, unavailable activity logs) thoughtfully, but it is non-functional as bundled: all substantive check, taxonomy, and remediation content lives in ./references/ files that are not present in the bundle.

Suggestions

Ship the missing ./references/ files (experiment-checks.md, flag-checks.md, finding-taxonomy.md, synthesis-patterns.md, remediation-actions.md) — without them the audit steps they are referenced from cannot be executed.

Inline at least the most critical check list or a compact summary table in SKILL.md so the skill is partially usable even before references are loaded.

Remove or define 'Phase 1' (no Phase 2+ exists), and drop the restated opener sentence to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude knows what PostHog/experiments are, and avoids padding; minor trims possible such as the restated opener ('This skill teaches you how to run configuration audits') and the undefined 'Phase 1' reference.

4 / 5

Actionability

Concrete tool names (experiment-get, experiment-list, feature-flag-get-definition), output format, and link format are given, but the core executable detail — the actual checks — is delegated to ./references/*.md files that do not exist, leaving the guidance incomplete with key details missing.

3 / 5

Workflow Clarity

Three usage modes each have clear numbered sequences, and partial-failure and unavailable-data sections provide error-recovery checkpoints; it is a read-only batch audit, so the missing-findings verification is a minor rather than critical gap.

4 / 5

Progressive Disclosure

Sectioning and one-level-deep reference signaling are well done, but every referenced file (experiment-checks.md, flag-checks.md, synthesis-patterns.md, remediation-actions.md, finding-taxonomy.md) points to a ./references/ directory that is absent, so the overview has no backing detail content to navigate to.

3 / 5

Total

14

/

20

Passed

Description

87%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 strong: it states a clear purpose, an explicit 'Read when...' trigger clause with concrete user phrasings, and a distinct PostHog-specific niche. Minor room to widen trigger synonyms and break 'audit' into more distinct concrete actions.

DimensionReasoningScore

Specificity

Names the domain ('PostHog experiments and feature flags') and several concrete audit targets ('configuration issues, staleness, and best-practice violations'), but it is a single audit action with three targets rather than multiple distinct actions, so it falls just below the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' ('Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations') and 'when' via a concrete 'Read when the user asks to...' clause with specific trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Includes natural trigger verbs a user would say — 'audit', 'health-check', 'review', 'check flag hygiene', 'verify experiment setup' — with good synonym coverage, though a few natural phrasings (e.g. 'diagnose', 'troubleshoot', 'test') are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (PostHog experiment/flag auditing) with domain-specific triggers, making conflict with other skills minimal.

5 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 9 missing, 3 suspicious

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.