release

Cut an OpenWork release, release the app, publish a new version, rerun or recover a release tag, verify release assets. Tag-driven GitHub Actions release that makes zero commits to the repo.

Quality

85%

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

96%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.

The body is an excellent operational runbook: lean, fully executable, and clearly sequenced with explicit validation and recovery loops. The only gap is progressive disclosure, where substantial detail is inlined rather than delegated to the referenced external files.

Suggestions

For progressive disclosure, consider moving the detailed warden-token/AUR-publish mechanics into docs/RELEASING.md and keeping SKILL.md as a tighter overview that links out.

Make the external references more clearly navigational (e.g. a "Full runbook: docs/RELEASING.md" callout near the top) rather than burying them mid-sentence.

No changes needed for conciseness, actionability, or workflow clarity.

Dimension	Reasoning	Score
Conciseness	Dense, information-rich body with no padding over basic concepts; every line carries non-obvious operational detail (commands, blocking vs non-blocking channels, self-healing behavior, version-stamping mechanics) that earns its place, matching the lean score-5 anchor.	5 / 5
Actionability	Copy-paste-ready commands throughout (pnpm release:cut, gh workflow run, gh run watch, gh release view, curl -sI) covering the common cases of cut, expedited, watch, recovery, and verify, matching the fully-executable score-5 anchor.	5 / 5
Workflow Clarity	Clearly sequenced release process with explicit checkpoints ("done when the run is green and the GitHub release is published (not a draft)") and feedback loops for the destructive tag-deletion case ("Only delete/recreate a tag after verifying the GitHub release is still draft-only"), satisfying the score-5 anchor without hitting the destructive-operation cap.	5 / 5
Progressive Disclosure	Well-organized single file with clear section headers and real inline pointers to external paths (docs/RELEASING.md, scripts/release/*.mjs), but the bulk operational detail lives inline rather than split into one-level-deep reference files, leaving minor organization gaps versus the clean overview-split score-5 anchor.	4 / 5
	Total	19 / 20 Passed

Description

75%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.

The description is specific, distinctive, and lists concrete actions covering the full release lifecycle, but it lacks an explicit "Use when..." trigger clause, capping completeness at 3. Adding a natural trigger sentence would lift the overall score.

Suggestions

Append an explicit trigger clause such as "Use when cutting, publishing, recovering, or verifying an OpenWork release" to satisfy the 'when' half of completeness.

Add natural synonyms a user might say (e.g. "ship a release", "cut a tag") to broaden trigger-term coverage toward 5.

Consider mentioning the version format (e.g. "vX.Y.Z tags") so users searching by tag syntax can match this skill.

Dimension	Reasoning	Score
Specificity	Lists five concrete release actions ("Cut an OpenWork release, release the app, publish a new version, rerun or recover a release tag, verify release assets") with comprehensive coverage of the release lifecycle, matching the score-5 anchor.	5 / 5
Completeness	Clearly answers "what" via the concrete action list, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural verb-phrases ("release the app", "publish a new version", "verify release assets") that users would actually say, but missing common synonyms (e.g. "ship") and explicit version/format terms, so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche (OpenWork tag-driven GitHub Actions release making zero commits) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: 2 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: different-ai/openwork
Path: .opencode/skills/release/SKILL.md
Commit: 9f0e880

Reviewed: 3 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.