Name: testland/release-runbook-author
Rating: 70.39999999999999 (1 reviews)
Author: testland

testland/release-runbook-author

Turns one service's release into a written six-phase runbook: pre-flight checks, a smoke gate, a canary observation window, a named human promote gate, progressive rollout, and post-release verification. Fixes each phase's pass criteria as a delta against a recorded baseline rather than a bare absolute number, gives canary and rollout separate windows and separate thresholds, and emits a per-phase evidence table that becomes the release record. The multi-team cutover-sequence procedure - dependency-ordered gates with one named owner each, hard timeboxes, written rollback triggers, and the reverse-order rollback path - is worked in references for windows where several teams cut over interdependent services. Use when a single service is about to ship and its release steps exist only as tribal knowledge or a chat thread, or when a shared release window needs its cutover order, gate owners, and rollback path written down.

Quality

88%

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

77%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-only skill with clear phase sequencing, strong validation checkpoints, and clean progressive disclosure into verified reference files. Its weakness is a verbose, citation-heavy prose style that could be tightened for token efficiency.

Suggestions

Trim the repeated inline citations to Azure/Google SRE sources; consolidate them once or state the convention without the quoted justification to reduce token load.

Convert narrative rationale paragraphs ('The failure mode it addresses is...', 'The common runbook error is the opposite...') into concise imperative statements so the skill instructs rather than explains.

Move the multi-paragraph baseline-comparison rationale into the body's most essential two-condition rule and link the rest to a reference, keeping the overview lean.

Dimension	Reasoning	Score
Conciseness	The body is substantive and largely about specialized conventions Claude would not already know, but the prose style is narrative-heavy with repeated inline source citations and rationale explanation that could be tightened to instruct more directly.	3 / 5
Actionability	Provides a concrete canary observation table with real values, a per-phase comparison table, and an 11-row 'Before the runbook is usable' defect checklist, with minor gaps where guidance stays abstract.	4 / 5
Workflow Clarity	The six phases are explicitly sequenced with validation checkpoints ('A failed pre-flight row ends the release at phase 1', the defect checklist, gate integrity) and a feedback loop where a threshold trip returns to the phase 4 decision table.	5 / 5
Progressive Disclosure	The SKILL.md body is an overview that points to one-level-deep references (worked-example, output-template, anti-patterns, cutover-*), all of which exist as real files and are clearly signaled, with content appropriately split.	5 / 5
	Total	17 / 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, concrete description in third person that names specific capabilities and provides explicit, natural trigger guidance. The only minor gap is a lack of common synonyms in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Turns one service's release into a written six-phase runbook', 'Fixes each phase's pass criteria as a delta against a recorded baseline', 'emits a per-phase evidence table that becomes the release record' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (six-phase runbook with baseline-delta thresholds and evidence tables) and when via a concrete 'Use when' clause with multiple trigger scenarios.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'a single service is about to ship', 'release steps exist only as tribal knowledge or a chat thread', and 'shared release window needs its cutover order' are present, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (single-service release runbook) and explicitly carves the cross-team cutover procedure out as a separate skill, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

19 days ago

Table of Contents

Discovery Implementation Validation