cut-release

Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR (drop internal-only churn, consolidate duplicates), bump pyproject.toml + uv.lock, run the CI-mirror lint chain, and open the release PR. Activate on "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", or any phrasing that ends in opening a release PR -- even when the user does not say "skill". Stops BEFORE tagging; tagging stays a human gate that triggers the release workflow. Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 release workflow with explicit checkpoints, validation gates, and clean one-level-deep references to real bundle files. Its only minor flaw is some repetition of the 'stops before tagging' boundary across multiple sections.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence ('Do not duplicate their content; reference them'), with no padded concept explanations; a few points are restated across sections (the 'stops before tagging' boundary appears in the intro, anti-patterns, and boundary), which is minor over-explanation worth trimming.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout -- 'git describe --tags --abbrev=0', 'scripts/bump-version.sh <new-version>', 'gh pr create --base main --head <branch>...' -- covering the common cases concretely.	5 / 5
Workflow Clarity	Eight numbered phases (0-7) are clearly sequenced with explicit checkpoints ('B10 CHECKPOINT 1/2/3') and feedback loops for lint-failure recovery ('If it fails... common cures... re-run'), plus a destructive/batch validation gate (Phase 5 lint must be green before push).	5 / 5
Progressive Disclosure	The body is an overview that points one level deep to real bundle files (assets/semver-rubric.md, assets/entry-sanitizer.md, assets/pr-body-template.md, and the three scripts/*), each clearly signaled with 'Load'/'Run'/'Reference; do not re-derive', keeping detail offloaded and navigation easy.	5 / 5
	Total	19 / 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, third-person description that concretely enumerates the release workflow steps and gives explicit natural-language trigger phrasing. Its only mild weakness is blending in project-specific jargon among the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full release-cut flow: 'assess whether the cycle...warrants a patch or minor bump', 'sanitize the [Unreleased] CHANGELOG block', 'bump pyproject.toml + uv.lock', 'run the CI-mirror lint chain', and 'open the release PR' -- comprehensive coverage matching the 5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (assess, sanitize, bump, lint, open PR) and 'when' via 'Activate on...' followed by concrete trigger phrases, satisfying the clear-and-explicit 5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrasings users would say ('ship a release', 'cut v0.x', 'release prep', 'bump and PR', 'open release PR') with synonym coverage, but intersperses some project jargon (CI-mirror lint chain, semver discipline) that keeps it just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (APM release-cut) with explicit boundary signals ('Stops BEFORE tagging', refuses major bump without confirmation) and distinguishes itself from tagging/rollback/blog skills, giving minimal conflict risk.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/cut-release/SKILL.md
Commit: 71a877c

Reviewed: ~5 hours 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.