CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

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

85%

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

The skill body is highly actionable and well-sequenced with strong validation safeguards for a destructive batch operation. Its main weakness is redundancy between the workflow steps and the closing 'Important notes' section.

Suggestions

Trim the 'Important notes' section to only net-new caveats (e.g. seasonal flags, experiment flags) and remove points already stated in the workflow like 'Code first, then disable' to reduce token redundancy.

Shorten the example interaction or reference it as a representative subset rather than re-rendering the full cleanup prompt already shown in step 3.

DimensionReasoningScore

Conciseness

The body is largely lean and domain-specific, but the 'Important notes' section reiterates points already made in the workflow (e.g. 'Code first, then disable' repeats step 4's 'Never disable flags before the code changes are deployed') and the example interaction is lengthy, so it could be tightened.

2 / 3

Actionability

Copy-paste-ready cleanup blocks with specific search terms (isFeatureEnabled, useFeatureFlag, etc.), exact tool names and parameters (posthog:feature-flag-get-all with active: "STALE"), and per-rollout-state instructions make the guidance fully executable.

3 / 3

Workflow Clarity

A clear four-step sequence (list, assess, generate cleanup, disable) with explicit checkpoints and feedback loops — 'Never disable flags before the code changes are deployed', 'confirm each action', and the cleanup instructions doubling as an approval checklist — gives the destructive batch operation proper validation.

3 / 3

Progressive Disclosure

No bundle files exist, and the self-contained content is organized into well-labeled sections (When to use, What makes a flag stale, Workflow, Example, Important notes, Related tools) with easy header-based navigation, so a single well-structured file is appropriate here.

3 / 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.

The description is strong across the board: concrete capabilities, natural trigger terms, explicit what-and-when guidance, and a clear PostHog feature-flag niche with low conflict risk. It uses third-person voice throughout.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — 'Identify and clean up stale feature flags', 'find unused, fully rolled out, or abandoned feature flags', 'review them for safety', and 'disable or delete them' — plus sub-capabilities like staleness detection and dependency checking.

3 / 3

Completeness

It clearly answers 'what' (identify, review, disable/delete stale flags) and 'when' with an explicit 'Use when the user wants to find unused, fully rolled out, or abandoned feature flags...' trigger clause.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered with terms like 'clean up stale feature flags', 'find unused... flags', 'fully rolled out', and 'disable or delete', which a user would realistically say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

The PostHog-scoped, feature-flag-specific niche with distinct triggers (stale/unused/rolled-out flags, disable vs delete) makes it unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.