CtrlK
BlogDocsLog inGet started
Tessl Logo

flag-release

Record an automated rollout for an existing LaunchDarkly flag that guards a pull request's change, so the change releases safely when the PR merges. Honors a stated release intent (release now / hold / notBefore / segment / prerequisite) and defers per-environment to the project's release policies. Use as the release step once the guarding flag exists and its code is wired. Keywords: record release, automated rollout, release policy, guarded rollout, staged rollout, simple vs policy, release intent, hold release, dark launch.

76

Quality

96%

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

92%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, highly actionable skill body: concrete tools, a copy-paste call, explicit buckets, and validation checkpoints across a Plan/Implement split with one-level-deep references. The only weakness is repetition of the hold/policy safety warning across four locations.

Suggestions

Consolidate the hold/policy warning: state the 'omit from environments to hold; policy ships on merge' rule once in the Implement bucket section and reference it from the blockquote and Edge Cases instead of re-deriving it each time.

Move the precedence ordering (intent → override → policy → default) fully into references/auto-release.md since it is already linked, keeping the body's Plan step focused on capturing intent.

DimensionReasoningScore

Conciseness

Dense and substantive with no padding of concepts Claude already knows, but the critical hold/policy warning ('policy is NOT a manual gate', 'omit it from the environments array') is restated in four places (blockquote, bucket table, step 2, edge cases), which could be consolidated. Not a 5 due to that repetition; not a 3 because every token is on-task.

4 / 5

Actionability

Names the exact MCP tools (create-automated-rollout-config, match-release-policies, get-flag), provides a copy-paste JSON call, an explicit RELEASE/HOLD bucket table, and concrete read-the-keys-back verification — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Two clearly sequenced phases with a confirmation gate ('Record nothing in this phase' → 'Only after confirmation'), explicit validation checkpoints (confirm flag exists and is OFF, scan environmentKeys back before sending, Verify step recording config_id), and a fail-closed rule plus an Edge Cases table for recovery. Batch operation validation is present, so no cap applies.

5 / 5

Progressive Disclosure

The body is an overview with well-signaled, one-level-deep references to the verified references/auto-release.md (linked from Prerequisites, Plan, Implement, and References), and the core model is appropriately split out rather than inlined; section structure (Prerequisites, Plan, Implement, Edge Cases, What NOT to Do, References) makes navigation easy.

5 / 5

Total

19

/

20

Passed

Description

100%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 tight, third-person description that states concrete capabilities, an explicit use-when clause, and a keyword tail for triggering. It carves a clear niche within the LaunchDarkly flag workflow and avoids over-claiming.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Record an automated rollout for an existing LaunchDarkly flag', 'Honors a stated release intent (release now / hold / notBefore / segment / prerequisite)', 'defers per-environment to the project's release policies' — giving comprehensive, specific coverage rather than generic verbs.

5 / 5

Completeness

Clearly answers 'what' (records an automated rollout for an existing guarding flag) and 'when' ('Use as the release step once the guarding flag exists and its code is wired'), both explicit and concrete.

5 / 5

Trigger Term Quality

An explicit Keywords tail gives natural phrases users would say — 'record release, automated rollout, release policy, guarded rollout, staged rollout, ... hold release, dark launch' — covering synonyms and common variations for this domain.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to the release step of a PR-flag workflow on an existing flag ('does not create flags or edit code'), which clearly separates it from sibling flag-create and guarded-rollout skills with minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

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.