← Back to Skills Marketplace
127
Downloads
1
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install pm-workbench
Description
Use when product work needs clearer framing, prioritization, or communication: clarifying a vague request, evaluating whether a feature is worth doing, compa...
Usage Guidance
This skill appears coherent and low-risk: it is a documentation-and-prompt repo for PM workflows with a local Node.js validation script that only reads files and verifies links. Before installing or running anything: 1) review scripts/validate-repo.js yourself (it runs locally and performs file/link checks); 2) running npm run validate and openclaw skills check is recommended to verify the copy on your machine; 3) confirm you trust the skill source before allowing any agent to execute shell/npm commands on your system (agents can run commands if permitted); and 4) no API keys or credentials are required by this skill. If you need higher assurance, run the validation in an isolated environment or inspect the repository files first.
Capability Analysis
Type: OpenClaw Skill
Name: pm-workbench
Version: 1.1.3
The pm-workbench skill bundle is a comprehensive set of instructions and templates designed to assist with product management tasks. The core logic in SKILL.md and the various workflow files in references/ focus entirely on PM methodologies such as requirement clarification, feature evaluation, and prioritization. The only executable code is a local Node.js validation script (scripts/validate-repo.js) used to ensure repository integrity and link consistency. No evidence of malicious intent, data exfiltration, unauthorized command execution, or harmful prompt injection was found across the documentation or code.
Capability Tags
Capability Assessment
Purpose & Capability
The skill name, SKILL.md, README, workflow references, templates, and examples all align with a PM workbench purpose. The only code present is a local validation script (scripts/validate-repo.js) whose behavior (checking docs and file wiring) is coherent with the stated install/validation guidance.
Instruction Scope
SKILL.md contains routing and behavioral rules for PM workflows and does not instruct the agent to access unrelated system files, environment variables, credentials, or external endpoints. The README suggests running local validation commands (npm run validate, openclaw skills check); those operate on local files only.
Install Mechanism
There is no install spec (instruction-only skill), lowering risk. The repository includes a local validation script run via npm run validate; that script performs purely local file reads and consistency checks. Because there is executable code in the repo, users should inspect scripts before running them, but there is no remote download or extract step in the skill metadata.
Credentials
The skill does not request environment variables, credentials, or config paths. Nothing in SKILL.md or the included scripts requires secrets or unrelated service access.
Persistence & Privilege
Skill flags show always: false and default autonomous invocation allowed (normal). The skill does not request permanent system presence or modify other skills or system-wide configs in the repo; local validation is self-contained.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pm-workbench - After installation, invoke the skill by name or use
/pm-workbench - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.3
Version 1.1.1 introduces major documentation, workflow, and artifact upgrades.
- Added extensive new documentation and workflow guides, including multilingual READMEs and starter guides.
- Introduced visual assets for both English and Chinese users.
- Added comprehensive command references and benchmarking documentation for workflow evaluation.
- Expanded example deliverables and reference command combinations for complex, multi-step PM workflows.
- Updated core rules to support multi-step, command-style workflows and clarified compressed artifact expectations.
v1.1.0
pm-workbench 1.0.0 – Initial Release
- Provides a structured “workbench” for key PM workflows like request clarification, feature evaluation, solution comparison, prioritization, roadmapping, and postmortem review.
- Routes tasks to the right workflow by intent, gathering only minimal missing context and asking high-value follow-up questions as needed.
- Delivers outputs as practical, reusable PM artifacts (e.g., decision briefs, prioritization stacks, PRDs) rather than open-ended analysis.
- Emphasizes actionable recommendations, explicit trade-offs, and clear next steps, especially for leaders and executive audiences.
- Includes clear rules for handling uncertainty, compressing artifacts for quick answers, and avoiding mechanical or jargon-heavy responses.
Metadata
Frequently Asked Questions
What is pm-workbench?
Use when product work needs clearer framing, prioritization, or communication: clarifying a vague request, evaluating whether a feature is worth doing, compa... It is an AI Agent Skill for Claude Code / OpenClaw, with 127 downloads so far.
How do I install pm-workbench?
Run "/install pm-workbench" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is pm-workbench free?
Yes, pm-workbench is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does pm-workbench support?
pm-workbench is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created pm-workbench?
It is built and maintained by Bobbie (@bobbielee); the current version is v1.1.3.
More Skills