3skill

Create and manage Product Requirements Documents (PRDs) by defining user stories with verifiable acceptance criteria and tracking progress by priority order.

This skill is essentially a PRD template + agent-run instructions. That is coherent, but be careful before using it autonomously: 1) Do not run infinite unattended loops against your main repo; use isolated worktrees or throwaway test repos. 2) Never use flags like `--dangerously-skip-permissions` or other options that bypass agent safety — they defeat platform protections. 3) Require human review of any agent-made commits (use pull requests, branch protection, CI). 4) Backup your repo and run agents in a sandboxed environment first. 5) If you intend to allow an agent to commit code, restrict its scope (single worktree, limited filesystem access) and audit progress.txt and prd.json updates. These steps will reduce the risk of unintended or damaging automated changes.

Type: OpenClaw Skill Name: prd-skill202603 Version: 1.0.0 The skill bundle is a legitimate tool for managing Product Requirements Documents (PRDs) and coordinating autonomous AI coding workflows. It provides structured JSON templates (prd.json), Markdown instructions (SKILL.md), and workflow patterns (references/workflows.md) that guide an agent through implementing features story-by-story. While the documentation in references/agent-usage.md mentions high-risk CLI flags for external tools (e.g., --dangerously-skip-permissions for Claude Code), these are presented as optional usage patterns for human users to enable unattended loops, rather than instructions for the agent to perform unauthorized or harmful actions. No evidence of data exfiltration, backdoors, or malicious prompt injection was found.