Name: cleaning-up-stale-feature-flags
Rating: 73.6 (1 reviews)
Author: PostHog

cleaning-up-stale-feature-flags

Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review them for safety, and then disable or delete them. Covers staleness detection, dependency checking, and safe removal workflows.

Quality

90%

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

88%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-structured, highly actionable skill body with a clear sequenced workflow and strong safety guardrails for destructive flag operations. Conciseness and progressive disclosure are good but not maximal due to light redundancy and a lengthy inline example.

Suggestions

Consolidate the safety rules duplicated between 'Step 4. Disable flags' and 'Important notes' into one location to trim tokens.

Consider moving the full 'Example interaction' transcript to a separate EXAMPLE.md file and linking to it, keeping the workflow overview leaner.

Add a one-line note in 'Related tools' clarifying that feature-flag-disable takes only a flag id (already noted in step 4) to avoid restating the caveat twice.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence; the PostHog-specific staleness criteria and rollout classifications earn their tokens. Minor redundancy between step 4's safety rules and the 'Important notes' section keeps it just short of fully lean.	4 / 5
Actionability	Provides concrete tool calls (posthog:feature-flag-get-all with active: "STALE", feature-flag-disable, delete-feature-flag), precise rollout-state classifications, and copy-paste-ready cleanup prompt templates covering the common boolean, multivariate, not-rolled-out, and partial cases.	5 / 5
Workflow Clarity	Four-step workflow is clearly sequenced with explicit validation checkpoints for destructive/batch operations — deploy code before disabling, require explicit user approval, confirm each action one at a time, and use the cleanup list as an approval checklist.	5 / 5
Progressive Disclosure	Self-contained and well-sectioned with no nested references and no bundle files needed. The inline example interaction is fairly long and could optionally live in a separate file, leaving the overview slightly less cluttered.	4 / 5
	Total	18 / 20 Passed

Description

92%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, well-scoped description that clearly states capabilities and trigger conditions in third person. It is comprehensive on what/when and highly distinct, with only minor room to broaden trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Identify and clean up stale feature flags', 'review them for safety', 'disable or delete them', plus 'staleness detection, dependency checking, and safe removal workflows' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers what the skill does and provides a concrete 'Use when the user wants to find unused, fully rolled out, or abandoned feature flags…' trigger clause covering multiple scenarios.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('clean up', 'find unused, fully rolled out, or abandoned feature flags', 'disable or delete') but misses some common synonyms like 'audit' or 'tech debt' as triggers; good but not exhaustive.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche — stale feature flags in a PostHog project — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PostHog/posthog
Path: products/feature_flags/skills/cleaning-up-stale-feature-flags/SKILL.md
Commit: b0fece0

Reviewed: ~19 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.