← Back to Skills Marketplace
4skill
by
zhao202404
· GitHub ↗
· v1.0.0
· MIT-0
116
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install prd-skill20260303
Description
Create and manage Product Requirements Documents by defining user stories with acceptance criteria, ordering tasks by dependencies, and tracking progress.
Usage Guidance
This skill's templates and JSON schema are coherent for creating and tracking PRDs, but its runtime docs instruct running autonomous agent loops and a CLI flag that bypasses permissions. Before using: (1) Do NOT run the example infinite loop or any command containing --dangerously-skip-permissions unless you fully trust the agent binary and environment. (2) Expect to provide git credentials and agent/API keys locally — the skill does not declare or manage them. (3) If you want automation, run the agent in a tightly sandboxed environment or CI with least privilege and audit logs, and require manual approval before commits. (4) Inspect any agent prompts and progress.txt entries before allowing automated commits. If you cannot or do not want to run an autonomous agent with repository access, use the PRD templates manually instead.
Capability Analysis
Type: OpenClaw Skill
Name: prd-skill20260303
Version: 1.0.0
The skill bundle provides a structured framework for managing Product Requirements Documents (PRDs) via JSON templates and markdown documentation. It is designed to facilitate autonomous development workflows for AI agents. While the documentation in 'references/agent-usage.md' suggests high-risk practices for external tools, such as using the '--dangerously-skip-permissions' flag with Claude Code, these are presented as part of a documented workflow for unattended operation rather than an attempt to exploit the host system. No evidence of malicious code, data exfiltration, or unauthorized execution was found; the skill primarily focuses on file manipulation and task tracking (e.g., using 'jq' to query 'prd.json').
Capability Assessment
Purpose & Capability
The name/description (PRD authoring and tracking) align with the included JSON schema, templates, and workflows. However the references and runtime instructions assume the skill will invoke external agent CLIs (e.g., claude, opencode), perform git worktree operations, and commit code — capabilities consistent with 'implementing stories' but not explicitly declared (no required binaries, no required env vars, no config paths). The omission of expected requirements (agent CLI availability, git access) is noteworthy.
Instruction Scope
SKILL.md and references instruct agents to read and update prd.json and progress.txt (expected) but also recommend running persistent agent loops (example: while :; do claude --print --dangerously-skip-permissions ...) and to auto-checkout/create git branches and commit code. The explicit use of a --dangerously-skip-permissions flag and an infinite unattended loop grants wide autonomous power outside the skill metadata and is out-of-scope for a simple PRD authoring skill.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk by the skill itself. This lowers installation risk.
Credentials
The skill declares no required environment variables, yet the instructions assume presence of external CLIs (claude, opencode) which typically require API keys or credentials, and also assume git credentials for creating branches and committing. The skill does not declare or justify these credentials or any config paths, creating a mismatch between declared requirements and actual instructions.
Persistence & Privilege
The skill is not force-enabled (always:false), but its documentation explicitly encourages running indefinite unattended agent loops that bypass permissions and autonomously modify a repository. That pattern increases blast radius if the user follows the instructions; combined with the instruction to skip permission checks, it is a meaningful operational risk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install prd-skill20260303 - After installation, invoke the skill by name or use
/prd-skill20260303 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the prd skill (v1.0.0).
- Enables creation and management of Product Requirements Documents (PRDs) for feature planning.
- Supports structured user stories with acceptance criteria, prioritized task order, and schema for tracking completion.
- Provides detailed documentation and quick reference commands for working with `prd.json` files.
- Includes guidance for story sizing, ordering, and best practices for acceptance criteria and progress tracking.
Metadata
Frequently Asked Questions
What is 4skill?
Create and manage Product Requirements Documents by defining user stories with acceptance criteria, ordering tasks by dependencies, and tracking progress. It is an AI Agent Skill for Claude Code / OpenClaw, with 116 downloads so far.
How do I install 4skill?
Run "/install prd-skill20260303" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 4skill free?
Yes, 4skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 4skill support?
4skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 4skill?
It is built and maintained by zhao202404 (@zhao202404); the current version is v1.0.0.
More Skills