← Back to Skills Marketplace
517
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install product-owner
Description
Manage backlogs, write user stories, define acceptance criteria, and maximize product value.
Usage Guidance
This skill appears coherent and minimal-risk: it only writes local files under ~/product-owner/ and has no external network calls or secret requirements. Before installing, confirm you are comfortable with the agent creating and maintaining the ~/product-owner/ directory and that you will not store secrets or credentials in the backlog/memory files. Note the skill is designed to 'learn over time' and may ask follow-up questions across sessions; if you prefer one-off interactions, clarify that preference during setup. Finally, the skill can suggest installing related skills via clawhub but will do so only if you confirm.
Capability Analysis
Type: OpenClaw Skill
Name: product-owner
Version: 1.0.1
The skill bundle is benign. It provides comprehensive instructions for an AI agent to act as a product owner, focusing on backlog management, user story writing, and prioritization. Crucially, `setup.md` explicitly states, "All data is stored locally in `~/product-owner/`... No data is sent externally," which directly negates data exfiltration concerns. There are no instructions for malicious execution, persistence, obfuscation, or prompt injection attempts designed to subvert the agent's core function or access sensitive data beyond its stated purpose. All commands mentioned (`clawhub install/star/sync`) are standard platform interactions.
Capability Assessment
Purpose & Capability
Name/description align with the instructions: writing stories, prioritization, acceptance criteria, and backlog management. Declared behavior (local memory in ~/product-owner/, templates for stories/prioritization) is proportional and expected for a PO assistant.
Instruction Scope
Runtime instructions are self-contained and operate on local files under ~/product-owner/. They explicitly state no data is sent externally. One area to note: the skill encourages ongoing context gathering ('Gather info opportunistically' / 'status: ongoing'), which gives the agent latitude to ask follow-up questions over time and persist answers locally — this is reasonable for a PO but is broader discretion than a single-request helper. The SKILL.md does not instruct the agent to read unrelated system files or environment variables.
Install Mechanism
Instruction-only skill with no install spec, no binaries, and no downloads. Lowest-risk install footprint.
Credentials
No required environment variables, credentials, or external config paths are requested. All declared storage is local to the user's home directory and matches the skill's purpose.
Persistence & Privilege
Skill does persist data locally in ~/product-owner/ (memory, backlog, sprints). always:false and no elevated privileges requested. Autonomous invocation is allowed (platform default), but not combined with other red flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install product-owner - After installation, invoke the skill by name or use
/product-owner - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Improved setup flow with natural conversation guidelines
Metadata
Frequently Asked Questions
What is Product Owner?
Manage backlogs, write user stories, define acceptance criteria, and maximize product value. It is an AI Agent Skill for Claude Code / OpenClaw, with 517 downloads so far.
How do I install Product Owner?
Run "/install product-owner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Product Owner free?
Yes, Product Owner is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Product Owner support?
Product Owner is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Product Owner?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.1.
More Skills