QA Release — Testing skill for Claude Code
Run the release QA gate before calling feature or project work done.
How to install QA Release
Installs to ~/.claude/skills/artjack-verdict-qa-release/SKILL.md
mkdir -p ~/.claude/skills/artjack-verdict-qa-release && curl -fsSL https://raw.githubusercontent.com/ArtJack/verdict/HEAD/commands/qa-release.md -o ~/.claude/skills/artjack-verdict-qa-release/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Release does
description: "Run the release QA gate before calling feature or project work done." argument-hint: "[release, feature, or merge candidate]"
Use the `verdict` agent to run the release QA gate for:
`$ARGUMENTS`
Verdict must use the bundled release gate standard:
`${CLAUDE_PLUGIN_ROOT}/standards/release-gate.md`
Required output:
VERDICT:pass / pass with risks / blocked / fail — an open Blocker forces fail- Scope reviewed (and SHA range if state exists)
- Release blockers
- Known
Alternatives in Testing
- Gstack — 15,000+ Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manag 33.9k ★
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Myflow Controller
A controller for AI coding agents that takes 'done' away from the model: a Claude Code skill plus a stdlib-onl
Purity
Test the product. Tests passing ≠ done right. Does the work match the formula? 99.1% or nothing.
Code Max
Agent skill that makes a coding agent verify before it claims done — no stubs, no fabricated test results, evi
Flywheel Nudge
Apply the agent-flywheel first-turn maturity nudge (spec-first, delegate, verify-before-done) plus active guar
Amby.Revise
Continue an existing feature's spec (or design) — add and refine in place, with a done-guard.
Cross Spec Review
Run the release-scope cross-spec review gate — do this release's specs agree with each other? — and record the
Related Agents
Red Team Reviewer
Fresh-eyes adversarial review of the skill itself (not its outputs). Use before calling an iteration done, and
Coding Guidelines Reviewer
Use after finishing a change in this repo to check it against CODING_GUIDELINES.md's rigor tiers, the testing
Corpus Prover
Proves a change on the maintainer's real local corpus — what number moved, by how much, and that nothing else