Name: launchdarkly-flag-create
Rating: 68.8 (1 reviews)
Author: launchdarkly

launchdarkly-flag-create

Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag, add a feature toggle, or set up an experiment. Guides exploration of existing patterns before creating.

Quality

83%

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

75%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 skill body with a clear multi-step workflow and concrete MCP tooling guidance. It uses progressive disclosure effectively, with minor room to tighten prose and add an explicit error-recovery loop in verification.

Suggestions

Add an explicit fix-and-retry feedback loop in Step 5 (e.g., 'if lint or get-flag checks fail, diagnose and re-run before proceeding') to raise workflow clarity.

Tighten the 'Important Context' prose by converting explanatory sentences into terse bullets, reducing minor over-explanation.

Make the cross-skill reference to ../launchdarkly-flag-targeting/references/context-availability.md gracefully degrade (note it requires the targeting skill bundle) so navigation does not break when that sibling skill is absent.

Dimension	Reasoning	Score
Conciseness	Efficient overview that assumes Claude's competence and avoids explaining what feature flags are; minor instances of over-explanation such as 'The default value in code is your safety net' could be trimmed slightly.	4 / 5
Actionability	Concrete guidance throughout—specific search terms, file names, a flag-type decision table, and copy-paste-ready MCP instruction objects like '{kind: "updateName", value: "New Name"}'; the code-evaluation step defers executable examples to a reference file.	4 / 5
Workflow Clarity	Clear 5-step sequence (Explore → Determine type → Create → Add eval → Verify) with an explicit Step 5 verification checklist including build/lint and get-flag confirmation; lacks an explicit fix-and-retry error-recovery loop.	4 / 5
Progressive Disclosure	Well-structured overview with one-level-deep, clearly signaled references to flag-types.md and sdk-evaluation-patterns.md (both present) plus a summary References section; the cross-skill external reference (../launchdarkly-flag-targeting/references/context-availability.md) is not resolvable within this bundle, a minor organization gap.	4 / 5
	Total	16 / 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, third-person description that clearly states the skill's purpose and provides explicit, natural trigger phrases for when to use it. It covers multiple concrete actions and occupies a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Create and configure LaunchDarkly feature flags', 'wrap code in a flag, add a feature toggle, or set up an experiment') with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both what ('Create and configure LaunchDarkly feature flags in a way that fits the existing codebase') and when ('Use when the user wants to create a new flag, wrap code in a flag, add a feature toggle, or set up an experiment') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong coverage of natural user phrases ('create a new flag', 'wrap code in a flag', 'add a feature toggle', 'set up an experiment') with good synonyms, though file-extension-style terms are not applicable to this domain.	4 / 5
Distinctiveness Conflict Risk	Clear LaunchDarkly flag-creation niche with distinct creation-focused triggers; minimal conflict risk even alongside the sibling targeting skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/feature-flags/launchdarkly-flag-create/SKILL.md
Commit: 82ce1ba

Reviewed: 9 days 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.