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

launchdarkly-flag-discovery

Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory.

Quality

86%

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

78%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 instruction skill: goal-branched workflow, concrete MCP tool guidance with defaults and tradeoffs, important domain gotchas ("launched" vs "recently deployed", weight scaling, dormant permanent flags), and clean one-level progressive disclosure into two real reference files. Main improvement room is adding example tool invocations and trimming a few narrative asides.

Suggestions

Add one or two example MCP tool invocations with actual arguments (e.g., a representative `list-flags` or `find-stale-flags` call) so the call shape is unambiguous.

Trim the meta opening sentence and narrative asides (e.g., "tells a different story than one inactive everywhere") to save tokens without losing guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense with tables, tool names, and parameter defaults, and never explains concepts Claude already knows (no "what is a feature flag" padding). A few tokens could still be trimmed — the meta opener "You're using a skill that will guide you through auditing..." and the narrative aside "tells a different story than one inactive everywhere" — which places it at 4 rather than 5.	4 / 5
Actionability	Gives concrete executable guidance: `list-flags` with `state`/`type` filters, `find-stale-flags` with `inactiveDays` (default 30, with 60/90 vs 7/14 tradeoff guidance), `includeOnly` values, and the weight-scaling gotcha ("A weight of `60000` means 60%"). Falls short of 5 because no example MCP tool invocations with actual arguments are shown, leaving minor ambiguity in call shape.	4 / 5
Workflow Clarity	Six clearly sequenced steps branch by user goal with explicit checkpoints (confirm `projectKey`, "Don't recommend action without more context", safe/caution/blocked verdicts, and a categorization scheme ordered by confidence). Not 5 because error-recovery/feedback loops are not made explicit; comfortably above 3 since checkpoints are present and concrete.	4 / 5
Progressive Disclosure	SKILL.md is a true overview (~110 lines) and both referenced files (`references/flag-health-signals.md`, `references/removal-readiness-checklist.md`) exist with substantive content, are one level deep, clearly signaled in the body ("See [Flag Health Signals](references/flag-health-signals.md) for the full interpretation guide") and indexed in a References section. Exact match for the 5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

88%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: concrete actions with a clear domain anchor, an explicit "Use when..." trigger clause with natural user phrases, and good distinctiveness. The only weakness is slightly incomplete keyword coverage (missing synonyms like "flag cleanup" or "rollout"), and mild trigger-territory overlap with the sibling flag-cleanup skill.

Dimension	Reasoning	Score
Specificity	Quotes "Audit your LaunchDarkly feature flags", "find stale or launched flags", and "assess removal readiness" — multiple concrete, domain-anchored actions covering the full discovery workflow (inventory, health, readiness). Matches the 5 anchor's comprehensive coverage; the 4 anchor's "minor gaps" doesn't apply since no meaningful capability of the discovery scope is missing.	5 / 5
Completeness	Explicitly answers "what" (audit flags, find stale/launched flags, assess removal readiness) and "when" via a literal "Use when..." clause with concrete trigger phrases. Exact match for the 5 anchor's example pattern.	5 / 5
Trigger Term Quality	"Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory" contains natural phrases users would say, plus "feature flags" in the first sentence. Not a 5 because common synonyms like "flag cleanup", "remove flags", or "rollout" are absent.	4 / 5
Distinctiveness Conflict Risk	"LaunchDarkly" pins a clear niche with distinct triggers, but the skill sits in a family of sibling skills (flag-cleanup, flag-targeting per the body) and phrases like "cleanup candidates" and "removal readiness" brush against the cleanup skill's territory. Fits 4 ("minor overlap risk with closely related skills") better than 5.	4 / 5
	Total	18 / 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: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/feature-flags/launchdarkly-flag-discovery/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.