CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flag-and-release-change

Drive a pull request's change end to end: decide it's flag-worthy, create the guarding flag, wire the new code path behind it on the PR branch, and record an automated release so the change ships safely when the PR merges. A portable orchestrator that composes should-flag-change, launchdarkly-flag-create, and flag-release. Keywords: flag a PR, wrap change in a flag, dark launch, kill switch, auto-release, automated rollout, end-to-end flag workflow.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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.

An excellent orchestrator skill body: concrete executable git commands, a rigorously sequenced plan→implement workflow with real validation gates (approval checkpoint, fail-closed flag creation, test-green requirement, honest reporting), and clean progressive disclosure that delegates mechanics to composed skills and a single verified reference. The only weakness is mild repetition of the don't-re-teach principle and a duplicated command block shared with the reference file.

Suggestions

State the "don't re-teach the composed skills' mechanics" principle once (e.g., in the composition table or What NOT to Do) and drop the repetitions in plan step 4, implement step 4, and the References section.

Show only a one-line pointer to references/pr-wiring.md for the clone/fetch/diff commands, or keep the commands only in the reference, to eliminate the verbatim duplication between body and bundle file.

DimensionReasoningScore

Conciseness

The body is largely efficient and assumes competence, but the "don't re-teach/don't re-derive the composed skills' mechanics" point is repeated roughly five times (intro table, plan step 4, implement step 4, What NOT to Do, References), and the clone/fetch/diff command block is duplicated verbatim in references/pr-wiring.md — minor over-explanation that could be trimmed, fitting the efficient-with-minor-trimmable-instances anchor rather than every-token-earns-its-place.

4 / 5

Actionability

Guidance is fully executable: copy-paste-ready git commands for the PR workflow, exact handoff points to each composed skill per step, a concrete fail-closed rule ("only an 'already exists' result is success-via-reuse"; any other create-flag failure is a hard stop), and a test gate ("Run them and continue only once green") — matching the copy-paste-ready anchor with common cases covered.

5 / 5

Workflow Clarity

The two-phase plan→implement flow is clearly sequenced with explicit validation checkpoints: a hard approval gate ("Present the combined plan and stop... proceed only on clear approval"), fail-closed error handling with a stated rationale, test-green continuation, and "Report only what you verified"; the Edge Cases table acts as a checklist, matching the explicit-validation-and-feedback-loops anchor.

5 / 5

Progressive Disclosure

Verified against the actual bundle (SKILL.md + references/pr-wiring.md): the skill keeps only orchestration content inline and delegates PR mechanics to its single local reference, which exists, is one level deep, and is clearly signaled both inline ("Full PR mechanics...: references/pr-wiring.md") and in a dedicated References section that labels it "This skill's only unique reference" — matching the clear-overview, well-signaled one-level-deep anchor.

5 / 5

Total

19

/

20

Passed

Description

87%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 end-to-end actions, third-person voice, and a rich set of natural trigger keywords with synonyms. Its main gap is the absence of an explicit 'Use when...' usage-conditions clause, leaving the 'when' implicit in the keyword list.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when a PR introduces a user-facing or risky change that should ship behind a feature flag') so the trigger conditions are stated as guidance, not just keywords.

Narrow the shared trigger terms (e.g., 'kill switch', 'auto-release') toward PR-scoped phrasings like 'flag a PR change' to reduce overlap with the composed single-purpose skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions covering the full workflow — "decide it's flag-worthy, create the guarding flag, wire the new code path behind it on the PR branch, and record an automated release" — which is comprehensive for this skill's scope, matching the multiple-specific-actions anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

The 'what' is clearly and explicitly answered, and the Keywords list constitutes explicit trigger guidance, but there is no 'Use when...' clause or equivalent sentence stating usage conditions, so 'when' is present yet could be more explicit — matching the both-present-but-could-be-more-explicit anchor rather than the fully-explicit one.

4 / 5

Trigger Term Quality

The keyword list — "flag a PR, wrap change in a flag, dark launch, kill switch, auto-release, automated rollout, end-to-end flag workflow" — provides comprehensive natural phrasings with genuine synonyms a user would say, fitting the comprehensive-synonyms anchor; no significant natural term is missing.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (end-to-end PR flag orchestration) and names the skills it composes, but triggers like "kill switch" and "auto-release" overlap with the composed launchdarkly-flag-create and flag-release skills themselves, giving minor overlap risk with closely related skills rather than minimal conflict.

4 / 5

Total

18

/

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: 20 suspicious

Warning

Total

15

/

16

Passed

Repository

launchdarkly/ai-tooling

Path

skills/feature-flags/flag-and-release-change/SKILL.md

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.