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

100%

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

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly sequenced, executable release-cutting procedure that relies on referenced bundle files and external primitives instead of restating them, with explicit checkpoints, validation gates, and a lint-fail recovery loop. It avoids pedagogy and keeps each phase copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence -- it never explains what semver, a changelog, or a lint chain is, and it deliberately points to companion primitives ("Do not duplicate their content; reference them") instead of inlining them. The recurring 'stops before tagging' emphasis is deliberate safety-gate reinforcement, not concept padding, fitting the score-3 'every token earns its place' anchor over the score-2 'some unnecessary explanation' bar.	3 / 3
Actionability	Every phase is copy-paste ready with executable commands -- `git rev-parse --abbrev-ref HEAD`, `git describe --tags --abbrev=0`, `scripts/list-changes-since-tag.sh`, `scripts/bump-version.sh <new-version>`, `scripts/verify-lint-mirror.sh`, `gh pr create --base main --head <branch> ...` -- matching the score-3 'fully executable code/commands' anchor rather than the score-2 pseudocode bar.	3 / 3
Workflow Clarity	Phases 0 through 7 are explicitly sequenced with named checkpoints (B10 CHECKPOINT 1/2/3), operator confirm gates, and a lint-fail feedback loop with concrete cures (ruff fix steps, merge-main for R0801), satisfying the score-3 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to real bundle files -- `assets/semver-rubric.md`, `assets/entry-sanitizer.md`, `assets/pr-body-template.md`, and `scripts/*.sh` (all present on disk) -- and external primitives it explicitly declines to duplicate, matching the score-3 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, naming concrete release-cutting actions and listing natural activation phrases while flagging explicit scope boundaries (no tagging, no unprompted major bump). It uses the standard imperative 'Use this skill to ... Activate on ...' form rather than first/second person, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions -- "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" -- matching the score-3 anchor of several specific concrete actions rather than the partial score-2 list.	3 / 3
Completeness	Explicitly answers both what ("Use this skill to cut an APM release ... open the release PR") and when ("Activate on ... or any phrasing that ends in opening a release PR"), hitting the score-3 'clearly answers both what AND when with explicit triggers' anchor rather than the score-2 'when only implied'.	3 / 3
Trigger Term Quality	Provides good coverage of natural phrasings users would say -- "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need" -- and even notes triggering when the user does not say "skill", exceeding the score-2 'some relevant keywords' bar.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche -- cutting an APM release from the worktree -- with distinct triggers and explicit boundaries ("Stops BEFORE tagging", "Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation"), making wrong-skill triggering unlikely per the score-3 anchor.	3 / 3
	Total	12 / 12 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: 634f7b6

Reviewed: 8 days 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.