← Back to Skills Marketplace
848
Downloads
2
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install mvp
Description
Build, validate, and launch minimum viable products with scope discipline, user signals, and iteration speed.
Usage Guidance
This skill appears to be a straightforward, self-contained set of MVP playbooks and templates and is internally consistent with its description. Before installing, verify the path mismatch noted in SKILL.md (it references 'roles/…' files while the bundle uses root filenames) to ensure the agent will correctly locate the role documents. Also: because this is instruction-only, it cannot exfiltrate secrets unless later updated to include network calls or installers — stop and review any future versions that add install steps, environment variables, or external endpoints before granting access.
Capability Analysis
Type: OpenClaw Skill
Name: mvp
Version: 1.0.0
The skill bundle consists entirely of markdown files providing guidance on MVP development. There are no executable scripts, no external network requests, no attempts at prompt injection against the AI agent, and no instructions for the agent to perform any actions beyond processing and presenting the provided information. All content is purely informational and aligns with the stated purpose.
Capability Assessment
Purpose & Capability
Name and description claim product/MVP guidance; the skill is instruction-only and contains multiple role-specific guides and templates that match that purpose. It does not request unrelated binaries, credentials, or system access.
Instruction Scope
SKILL.md directs the agent to select a role and load role-specific guidance; the referenced content is purely editorial (playbooks, templates, interview scripts). Minor inconsistency: SKILL.md's role table lists paths like 'roles/technical.md' but the bundle contains 'technical.md' and similar at the root — this is likely a packaging/path mismatch but not malicious. The instructions do not ask the agent to read system files, call external endpoints, or access secrets.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by an installer.
Credentials
No required environment variables, credentials, or config paths are declared or referenced. The guidance is content-only and does not request sensitive data.
Persistence & Privilege
always is false (no forced inclusion). disable-model-invocation is false (normal) but there is no code that would run autonomously or request extra privileges. Nothing in the skill attempts to modify other skills or system-wide configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mvp - After installation, invoke the skill by name or use
/mvp - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is MVP?
Build, validate, and launch minimum viable products with scope discipline, user signals, and iteration speed. It is an AI Agent Skill for Claude Code / OpenClaw, with 848 downloads so far.
How do I install MVP?
Run "/install mvp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MVP free?
Yes, MVP is completely free (open-source). You can download, install and use it at no cost.
Which platforms does MVP support?
MVP is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MVP?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.
More Skills