Skip to content
Back to skills

Project Os Task

ASecurity

Prepare a scoped Project OS task with testable acceptance criteria and approval references.

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

Security analysis

A100/100

Scanned November 13, 2026

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

Installs into .claude/skills of the current project.

Are you the author of Project Os Task?

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

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

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-task
description: Prepare a scoped Project OS task with testable acceptance criteria and approval references.
---

# project-os-task

Read AGENTS.md, .project-os.json, planning/decisions.md, planning/flow.md and planning/tasks/_template.md.
Draft one task for one repository in the shapes from planning/formats.md, with scope, branch, dependencies, risk flags, stable criterion IDs and a verification plan.
Use observable outcomes and real project evidence. Never invent a build command, approval, model result or completed task.
Drafting within authorised planning scope is allowed; product code waits for applicable scope/code approval.
Run node .project-os/check.mjs --workspace . after editing records and fix every finding. Record dated CHANGED criteria before redispatching altered work. Update the board and route essential decisions through PM.
Delegate implementation to project_os_developer only after permission and dispatch checks pass.

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.