CtrlK
BlogDocsLog inGet started
Tessl Logo

launchdarkly-flag-cleanup

Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or create a PR that hardcodes the winning variation after a rollout is complete.

75

Quality

92%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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.

This is a strong, well-structured skill that provides a clear multi-step workflow for a complex, potentially destructive operation. Its greatest strengths are the explicit safety gates (readiness check, user confirmation, verification), concrete decision tables, and good progressive disclosure to reference files. The main weakness is mild verbosity in the introduction and core principles sections, which could be tightened without losing clarity.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but has some unnecessary verbosity. The opening paragraph explaining what the skill does is redundant given the context. Phrases like 'Your job is to explore the codebase...' and some of the Core Principles restate things Claude already knows. However, the tables and edge cases are well-structured and earn their tokens.

2 / 3

Actionability

The skill provides concrete, executable guidance throughout: specific MCP tool names, exact decision tables for determining forward values, a clear code transformation example with before/after TypeScript, specific search patterns to look for, and explicit criteria for safe/caution/blocked verdicts. The guidance is specific enough to act on immediately.

3 / 3

Workflow Clarity

The 7-step workflow is clearly sequenced with explicit validation checkpoints: Step 2 is a dedicated safety/readiness check, Step 4 requires user confirmation before proceeding, Step 7 includes verification (build, lint, tests, re-search for references). The blocked/caution/safe verdicts create clear decision gates, and the forward value determination table provides explicit stop conditions when environments differ.

3 / 3

Progressive Disclosure

The skill provides a clear overview with well-signaled one-level-deep references: SDK Patterns, PR Template, Flag Discovery, and Flag Targeting are all linked at appropriate points in the workflow and collected in a References section. The main content stays focused on the workflow while deferring language-specific patterns and PR formatting to separate files.

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.

This is a strong skill description that clearly communicates what the skill does (remove feature flags while preserving production behavior) and when to use it (flag removal, deleting references, post-rollout cleanup). It uses third person voice, includes natural trigger terms developers would use, and occupies a distinct niche that is unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'remove a feature flag from code', 'preserving production behavior', 'delete flag references', 'create a PR that hardcodes the winning variation'. These are clear, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (safely remove a feature flag while preserving production behavior) and 'when' (explicit 'Use when' clause covering removing flags, deleting references, or creating PRs after rollout completion).

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'remove a flag', 'feature flag', 'delete flag references', 'create a PR', 'hardcodes the winning variation', 'rollout is complete'. These cover the natural language a developer would use when requesting this task.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche: feature flag removal is a specific workflow distinct from general code refactoring or PR creation skills. The terms 'feature flag', 'winning variation', and 'rollout' clearly delineate this skill's domain.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
launchdarkly/ai-tooling
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.