Name: launchdarkly-flag-targeting
Rating: 72 (1 reviews)
Author: launchdarkly

launchdarkly-flag-targeting

Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Use when the user wants to change who sees a flag, roll out to a percentage, add targeting rules, or promote config between environments.

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

85%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.

The body delivers an excellent workflow with strong validation checkpoints, concrete MCP tool guidance, and clean one-level-deep reference structure. Its main weakness is redundancy: the approval process and several key facts are repeated multiple times, and a mid-table paragraph breaks the scenarios table rendering.

Suggestions

Consolidate the approval-workflow explanation: keep a brief pointer in the Safety Checklist and the full five-step process only in the 'Handling Approval-Required Environments' section (or vice versa), cutting the duplicated detail.

Move the 'Before writing a rule, individual target, or percentage rollout...' paragraph out from between the table rows so the 'Common scenarios' markdown table renders as one block.

De-duplicate 'Important Context' items that already appear in the Core Concept section or the scenarios table (weights sum to 100, rule ordering, individual-target priority), keeping each fact in one place.

Dimension	Reasoning	Score
Conciseness	The body is mostly purposeful, but the approval workflow is fully explained twice (Safety Checklist item 2 and the 'Handling Approval-Required Environments' section), and facts like 'weights must sum to 100', rule ordering, and individual-target priority each repeat two to three times. This fits the 'mostly efficient but could be tightened' anchor rather than the level-4 'minor instances' anchor, and the level-2 anchor's pervasive padding is not present.	3 / 5
Actionability	Guidance is fully executable for an MCP-driven skill: specific tools, parameters ('on: true', 'rolloutType: "percentage"'), instruction operations ('addRule', 'removeRule', 'addContextTargets'), and a scenarios table mapping user intent to exact tool calls. Per the rubric's code-vs-instruction note, the absence of code is not penalized since the guidance is concrete, and detailed payloads are properly deferred to targeting-patterns.md.	5 / 5
Workflow Clarity	The five-step workflow (understand state, choose approach, safety checklist, apply, verify) has explicit validation: re-fetch with get-flag, describe the result in plain language, and check side effects. It also includes a named checklist and a feedback loop for approval-blocked mutations (create approval request, apply once approved, verify), matching the top anchor for risky production-change workflows.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview and all four referenced files (targeting-patterns.md, context-availability.md, safety-checklist.md, approval-workflows.md) exist, are one level deep, and are clearly signaled both inline and in a References section with descriptions. Bulk detail is appropriately split out, matching the clear-overview top anchor.	5 / 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 description that clearly and concretely states both what the skill does and when to use it, with natural trigger phrasing tied to real user requests. The only weakness is that a few common synonyms for the trigger terms are missing.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete actions — 'toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments' — giving comprehensive coverage of the skill's capabilities. This matches the top anchor (multiple specific concrete actions) and exceeds the level-4 anchor, which expects minor coverage gaps.	5 / 5
Completeness	It explicitly answers both questions: 'Control LaunchDarkly feature flag targeting including...' states what it does, and 'Use when the user wants to change who sees a flag, roll out to a percentage...' states when to use it with concrete trigger phrases. This matches the top anchor exactly.	5 / 5
Trigger Term Quality	Phrases like 'change who sees a flag', 'roll out to a percentage', and 'promote config between environments' are natural user utterances with good coverage. It falls short of the 5 anchor because common synonyms such as 'enable/disable a flag', 'turn on for beta users', or 'kill switch' are absent.	4 / 5
Distinctiveness Conflict Risk	The LaunchDarkly feature-flag-targeting niche is clearly defined with domain-specific triggers ('feature flag targeting', 'percentage rollouts'), so it is unlikely to fire for unrelated skills. It only marginally overlaps sibling LaunchDarkly skills, matching the clear-niche top anchor.	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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/feature-flags/launchdarkly-flag-targeting/SKILL.md
Commit: ef54971

Reviewed: 6 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.