Skip to content
Back to skills

Project Os Qa

ASecurity

Run independent Project OS acceptance verification after a developer releases the repository lane.

  • 63 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsgit

Works with

  • cli

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add ferhatcore/claude-codex-project-os --skill project-os-qa --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project Os Qa?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Project Os Qa
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ferhatcore-project-os-qa/badge)](https://www.skillsdirectory.com/skills/ferhatcore-project-os-qa)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: project-os-qa
description: Run independent Project OS acceptance verification after a developer releases the repository lane.
---

# project-os-qa

Read AGENTS.md, the assigned task, planning/qa/README.md and the repository's test instructions.
Check the lane is free, approval references remain valid, and the criteria include the latest changes.
Use project_os_qa if the client exposes that agent. If native delegation has no named role selector, read .codex/agents/qa.toml and pass its complete developer_instructions in the delegated brief. Otherwise use a fresh manual session.
Run isolated checks and inspect outputs. Preserve per-criterion verdicts, evidence and unverified items.
Do not fix production code or weaken tests. Blocking findings return to the developer within the shared retry budget.
PM checks completeness after QA. Git actions and deployment remain separate approved operations.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.