publish-evidence

Publish test evidence, publish all test runs, update PR verification, audit red evidence, prove a PR, or declare a PR verdict. Use after @openwork/testkit runs.

Quality

81%

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

78%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 concise, actionable, well-structured skill body with concrete commands and verification guidance. Its main gap is the absence of a rendered example of the published evidence comment and marker.

Suggestions

Add a short rendered example of a  sticky-comment section so Claude knows the exact expected output format.

Consolidate the 'never reruns tests' statements into one place to remove the small redundancy.

Consider a brief numbered publish sequence (run checks on PR head -> publish matching gitSha -> confirm comment -> handle exit code) to make the workflow order explicit.

Dimension	Reasoning	Score
Conciseness	Lean, action-oriented content that assumes Claude's competence and avoids explaining known concepts; not 5 because 'never reruns tests' is restated and a few framing sentences could be trimmed.	4 / 5
Actionability	Provides copy-paste commands (pnpm evals:e2e --publish, gh pr view, gh pr comment --attach) with exit codes; not 5 because no rendered example of the published sticky comment or <!-- test-evidence --> marker is shown, leaving a gap for a publishing skill.	4 / 5
Workflow Clarity	Topical sections include a verification checkpoint ('Confirm the final comment shows the test and verdict') and exit-code feedback loops; not 5 because there is no single numbered sequence with explicit validation gates, and not below 4 since verification and error-recovery are present.	4 / 5
Progressive Disclosure	A ~50-line single-file skill with no external bundle files and well-organized section headers; per the simple-skill exception this earns a 5 with clear organization and no nested references.	5 / 5
	Total	17 / 20 Passed

Description

83%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, specific description with concrete actions and an explicit trigger clause. The main weakness is the single narrow 'when' condition and some domain jargon that limits trigger-term breadth.

Suggestions

Broaden the 'when' clause with multiple concrete trigger phrases (e.g. 'Use after @openwork/testkit runs, when finalizing a PR verdict, or when auditing failed/red test evidence').

Add a natural-language synonym for 'red evidence' (e.g. 'failed test evidence') so users who don't know the jargon still trigger the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('Publish test evidence, publish all test runs, update PR verification, audit red evidence, prove a PR, or declare a PR verdict') with comprehensive coverage, matching the level-5 anchor; not 4 because there are no meaningful gaps.	5 / 5
Completeness	Both 'what' and 'when' are present with an explicit 'Use after @openwork/testkit runs' trigger, but the trigger is a single narrow condition rather than multiple concrete trigger phrases, so it falls short of level 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('publish test evidence', 'prove a PR', 'declare a PR verdict') a user would say, but jargon ('red evidence', '@openwork/testkit') and missing synonyms keep it below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche tied to @openwork/testkit PR verdicts with distinct triggers and minimal conflict risk; not 4 because the @openwork/testkit binding makes it highly distinguishable from related skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: different-ai/openwork
Path: .opencode/skills/publish-evidence/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.