CtrlK
BlogDocsLog inGet started
Tessl Logo

launchdarkly-guarded-rollout

Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety thresholds.

72

Quality

90%

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

88%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 content is highly actionable: complete JSON payloads, exact unit conversions, explicit tool sequences, and thorough edge-case and rollback handling. Minor trimming of the conceptual introduction and principles sections, or moving reference tables into bundle files, would push it to the top level.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious specifics Claude cannot know (weight units like "1000 = 1%", monitoring windows in milliseconds, MCP tool names), which justifies its length. Minor over-explanation remains — the "What Are Guarded Rollouts?" prose and the "Core Principles" list restate what the workflow sections already demonstrate — so it fits anchor 4 (minor instances that could be trimmed) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

It provides a complete, copy-paste-ready JSON payload for start-guarded-rollout with realistic stage and metric configurations, concrete tool calls for each step (get-flag, list-metrics, toggle-flag), and exact actions for each edge case. This matches the top anchor: fully executable guidance covering the common case.

5 / 5

Workflow Clarity

The five-step workflow (Prepare → Design Stages → Configure Metrics → Start → Verify) includes explicit pre-flight checks (flag on, no existing rollout), a verification step ("Use get-flag to confirm the guarded rollout is active"), and a documented recovery path ("Stopping a Rollout" plus the Edge Cases table). Validation checkpoints are explicit, not implicit, matching the top anchor.

5 / 5

Progressive Disclosure

The body is a well-organized flat set of sections with no nested references and a coherent single workflow, but it is ~160 lines all inline with no offloading of reference-style material (Key Components, Edge Cases tables) to bundle files. It sits between anchor 4 (good structure, minor organization gaps) and anchor 5 (clear overview with well-signaled references), since no references exist to signal.

4 / 5

Total

18

/

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: third-person, concise, and explicit about both capabilities and trigger conditions. Its only weaknesses are a missing domain marker (LaunchDarkly/feature flags) and a few missing synonyms that would sharpen trigger matching and distinctiveness.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "progressive traffic increases, metric monitoring, and automatic rollback" — comprehensively covering the skill's scope of staging, monitoring, and recovery. It matches the top anchor for listing several specific concrete actions with no vague filler.

5 / 5

Completeness

It explicitly answers both what ("Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback") and when ("Use when releasing features gradually with safety thresholds"). The trigger clause is explicit and concrete, matching the top anchor rather than anchor 4's "when could be more explicit".

5 / 5

Trigger Term Quality

Natural phrases like "releasing features gradually", "safety thresholds", and "progressive traffic" are present, but common synonyms such as "canary", "phased rollout", or "feature flag" are missing. This fits anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Guarded rollouts" carves a fairly distinct niche, but the description never names LaunchDarkly or feature flags, so it could be selected for generic canary/deployment tasks — minor overlap risk with closely related skills (anchor 4) rather than anchor 5's clear niche with distinct triggers.

4 / 5

Total

18

/

20

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.

Validation — 16 / 16 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.