CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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

Low

Low-risk findings worth noting

The canonical home for this skill is cut-release in microsoft/apm

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 strongly structured operational skill: every phase has executable commands, three explicit operator checkpoints with STOP gates, and a lint feedback loop that blocks pushing on failure. Detail is correctly pushed to real one-level bundle files. The only deduction is minor redundancy in repeated boundary statements and the duplicated trigger list.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes competence (exact git/gh/script commands, no concept explanations), but a few spots could be trimmed: the tagging boundary is restated in the intro, Phase 2, anti-patterns, Phase 7, and the Boundary section, and the 'When to use' trigger list duplicates the frontmatter description. This sits above 'minor instances of over-explanation' being absent but below 'every token earns its place'.

4 / 5

Actionability

Fully executable throughout: `git rev-parse --abbrev-ref HEAD`, `git describe --tags --abbrev=0`, `scripts/list-changes-since-tag.sh` with its documented JSON output fields, `scripts/bump-version.sh <new-version>`, `scripts/verify-lint-mirror.sh` with concrete failure cures (`uv run --extra dev ruff check src/ tests/ --fix`), and the full `git commit` / `git push` / `gh pr create --body-file` sequence with a PR-body template. Copy-paste ready and covers the common cases including failure paths.

5 / 5

Workflow Clarity

A clear 7-phase sequence with explicit validation checkpoints: STOP if on main, wait for operator confirm after the bump decision and changelog diff, halt on non-zero from bump-version.sh, and a lint gate with a feedback loop (fail -> cure -> re-run, 'Do NOT push or open the PR until lint is green'). Error recovery guidance is specific per failure mode, matching the top anchor.

5 / 5

Progressive Disclosure

The SKILL.md body is an orchestration overview that defers detail to real, one-level-deep bundle files (assets/semver-rubric.md, assets/entry-sanitizer.md, assets/pr-body-template.md, scripts/*.sh — all verified present, none nesting further) and explicitly references external primitives instead of duplicating them ('Do not duplicate their content; reference them'). Well-signaled and easy to navigate.

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.

An exemplary description: it enumerates concrete, file-level actions for the whole pipeline, provides an explicit and natural trigger list including a catch-all phrasing rule, and draws sharp boundaries (no tagging, no unprompted major bumps). Both 'what' and 'when' are explicit, and the niche is unmistakable.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with comprehensive coverage: "assess whether the cycle since the last tag warrants a patch or minor bump", "sanitize the [Unreleased] CHANGELOG block into a dated version block", "bump pyproject.toml + uv.lock", "run the CI-mirror lint chain", and "open the release PR". It names exact files and even details entry-level policy ("drop internal-only churn, consolidate duplicates"), matching the comprehensive anchor rather than the 'several actions with minor gaps' anchor below.

5 / 5

Completeness

Explicitly answers both questions: 'what' via the concrete action list and 'when' via "Activate on 'ship a release', 'cut v0.x', ...". It also adds explicit scope boundaries ("Stops BEFORE tagging", "Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation"), fully matching the clear what-and-when anchor.

5 / 5

Trigger Term Quality

Six natural trigger phrases plus a catch-all: "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", and "any phrasing that ends in opening a release PR -- even when the user does not say 'skill'". Coverage includes synonyms and colloquial variants a user would actually say, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

A clear niche (cut an APM release from the current worktree) with hard boundaries that prevent mis-triggering on adjacent tasks: it explicitly stops before tagging, excludes release-notes/blog drafting by scoping to the changelog block, and the refusal to major-bump without confirmation separates it from positioning decisions. Minimal overlap risk with neighboring skills.

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
microsoft/apm
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.