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.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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-organized, actionable audit skill with strong workflow sequencing and explicit error handling. The main weakness is a reference path mismatch (flag-checks.md vs. the bundled flag-checks.md.j2 template) that slightly undermines navigation.

Suggestions

Resolve the flag-checks reference mismatch: the body links to ./references/flag-checks.md, but the bundled file is flag-checks.md.j2 — either render the template to flag-checks.md or update the links to point at the template.

Trim the opening sentence ("This skill teaches you how to run configuration audits") since the H1 already conveys the purpose, freeing tokens for substance.

Consider inlining a one-line definition of at least one representative check so the orchestrating body is self-contained without requiring a reference hop.

DimensionReasoningScore

Conciseness

Lean, structured body with specific tool names and an example finding; only minor throat-clearing ("This skill teaches you how to run configuration audits") keeps it from a 5.

4 / 5

Actionability

Provides concrete, executable guidance — exact tool names, link formats, severity badges, and skip rules; not a 5 because the actual check logic is delegated to reference files rather than inline.

4 / 5

Workflow Clarity

Three clearly sequenced usage modes with numbered steps, severity ordering, an output-format threshold, and explicit error-recovery sections (partial failures, unavailable data) that function as validation checkpoints and feedback loops for a batch read operation.

5 / 5

Progressive Disclosure

Good one-level-deep reference structure with a clearly labeled "Reference files" index; capped at 4 because the body links to ./references/flag-checks.md but the actual bundle file is flag-checks.md.j2, a mismatched/broken reference path.

4 / 5

Total

17

/

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.

A strong description that explicitly covers both capability and trigger conditions with concrete, natural language. Minor room to broaden trigger synonyms and enumerate more discrete actions, but it is clearly distinguishable and well-targeted.

DimensionReasoningScore

Specificity

Names the domain (PostHog experiments/flags) and several concrete audit categories (configuration issues, staleness, best-practice violations), matching the score-4 anchor; not a 5 because the actions are framed as categories rather than a comprehensive list of discrete operations.

4 / 5

Completeness

Explicitly answers both "what" (audit experiments/flags for config issues, staleness, best-practice violations) and "when" ("Read when the user asks to audit, health-check, or review..."), with concrete trigger phrases — matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("audit, health-check, or review", "check flag hygiene", "verify experiment setup") — good keyword coverage; not a 5 because it lacks further synonyms/variants (e.g., lint, diagnose).

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (PostHog experiments and feature flags) with distinct triggers and minimal overlap risk with unrelated skills, matching the score-5 anchor.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 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.