CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

validate-a-release

Validate the release, check the released binaries, is 0.18.x safe to roll out, prove a published desktop release. Checks the RELEASED mac-arm64 enterprise and cloud binaries' signing and notarization and the updater manifests, and publishes evidence.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a tight, fully executable verification runbook: every step is copy-paste bash with expected outputs, explicit pass/fail determination, and a clear stop-and-report failure path, plus an honest 'proves / does not prove' boundary section. Its only flaws are minor — slight duplication of the CI-coverage explanation and no explicit failure instruction for the signing step.

DimensionReasoningScore

Conciseness

The body is lean and command-first with no padding, but the intro paragraph and the 'Does not prove' section both explain that app-smoke and packaged-update-install cover boot testing, a minor repetition that could be trimmed. Not 5 because of that duplicated explanation; not 3 because nothing explained is common knowledge — all project-specific details Claude could not know.

4 / 5

Actionability

Fully executable, copy-paste-ready bash for every step (gh release download, ditto unpack, codesign/spctl verification, manifest and sha512 checks) with expected outputs stated ('accepted', 'source=Notarized Developer ID'). Not below 5 because the commands are complete and cover the common case end to end.

5 / 5

Workflow Clarity

Clear four-step sequence (download → verify signing → check manifests → publish evidence) with explicit checkpoints and a stop-and-report condition for manifest failures ('Any MISSING, MISMATCH, or wrong version... stop and report'). Not 5 because the signing step states expected output but gives no explicit failure instruction, a minor validation gap versus the full feedback-loop anchor.

4 / 5

Progressive Disclosure

A short single-purpose SKILL.md with no bundle files, no external references needed, and well-organized numbered sections — per the simple-skill guideline this scores 5 on section organization alone. There are no buried references or inlined content that belongs in separate files.

5 / 5

Total

18

/

20

Passed

Description

70%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 communicates a specific, distinctive capability with natural trigger phrasing, but it front-loads four redundant trigger fragments before the actual capability statement and omits an explicit 'Use when...' clause, leaving the invocation context implied rather than stated. Tightening the opening and adding explicit usage triggers would raise completeness and specificity.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when a GitHub release has just been published and you need to verify it is safe to roll out') to satisfy the 'when' half of completeness.

Replace the four repetitive opening fragments ('Validate the release, check the released binaries, is 0.18.x safe to roll out, prove a published desktop release') with one or two distinct natural trigger phrases.

Include common user synonyms such as 'notarized', 'code signing', or 'updater' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'binaries' signing and notarization', 'the updater manifests', 'publishes evidence' — but the opening sentence ('Validate the release, check the released binaries... prove a published desktop release') is repetitive filler rather than capability coverage, so it falls short of the comprehensive 5 anchor.

4 / 5

Completeness

The 'what' is clear and specific, but there is no explicit 'Use when...' clause or equivalent; the 'when' is only weakly implied by the opening trigger phrases, which caps completeness at 3 per the judging guideline. Not 4 because the usage context must be inferred rather than stated.

3 / 5

Trigger Term Quality

Contains natural phrases users would actually say ('is 0.18.x safe to roll out', 'check the released binaries', 'prove a published desktop release') with good keyword coverage, but misses common synonyms like 'notarized', 'code signing', or 'updater', matching the 4 anchor rather than comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche — validating the RELEASED mac-arm64 enterprise and cloud binaries' signing, notarization, and updater manifests of a specific product — with distinct triggers and minimal overlap risk with any generic skill.

5 / 5

Total

16

/

20

Passed

Validation

100%

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.

Repository

different-ai/openwork

Path

.opencode/skills/validate-a-release/SKILL.md

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.