← Back to Skills Marketplace
279
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install pump
Description
Design launch momentum before a project goes live. Optimize first-day release logic, trigger sequencing, attention concentration, and breakout timing for pro...
Usage Guidance
This skill appears coherent and low-risk: it only gives planning advice and asks for user-provided launch details. Before installing or using it, be prepared to provide non-sensitive inputs (audience size, channels, goals). If the skill or the agent later asks to perform automated posting, access accounts, or provide API keys, treat that as a separate action and do not share credentials unless you trust and verify the integration. Because it is instruction-only, it will not install binaries or run code on disk; still exercise normal caution and avoid sharing secrets in chat unless necessary.
Capability Analysis
Type: OpenClaw Skill
Name: pump
Version: 1.0.0
The 'Pump' skill bundle is a purely instructional set of guidelines for an AI agent to provide launch strategy and momentum planning. It contains no executable code, scripts, or network requests, and its instructions (skill.md) are strictly aligned with its stated purpose of marketing analysis without any signs of prompt injection or malicious intent.
Capability Assessment
Purpose & Capability
The name and description (launch momentum, first-day sequencing) match the SKILL.md and skill.json capabilities. The skill requests no binaries, env vars, or config paths — which is appropriate for a planning/advisory tool.
Instruction Scope
SKILL.md gives step-by-step guidance for parsing user-provided launch context, diagnosing weaknesses, and producing a launch plan. It does not instruct the agent to read system files, access environment variables, perform network calls, or exfiltrate data. Guardrails explicitly require asking for missing inputs rather than guessing.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. That is the lowest-risk model and is coherent with its advisory purpose.
Credentials
No environment variables, credentials, or config paths are requested. The inputs the skill expects are user-provided launch details (audience size, channels, goals), which are appropriate and proportional.
Persistence & Privilege
always is false and the skill does not request persistent presence or modify other skills. Autonomous invocation is allowed (platform default) but there are no additional privileges requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pump - After installation, invoke the skill by name or use
/pump - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release — provides a framework for designing high-energy product and digital launches.
- Helps identify and resolve weak points in launch momentum, timing, and attention concentration.
- Guides users to sequence pre-launch, launch, proof, participation, and follow-through triggers.
- Supplies a structured output format for launch diagnostics and day-one event planning.
- Includes clear principles and guardrails for when (and when not) to use this skill.
- Requests missing key inputs (like audience or launch window) before proceeding with recommendations.
Metadata
Frequently Asked Questions
What is Pump?
Design launch momentum before a project goes live. Optimize first-day release logic, trigger sequencing, attention concentration, and breakout timing for pro... It is an AI Agent Skill for Claude Code / OpenClaw, with 279 downloads so far.
How do I install Pump?
Run "/install pump" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pump free?
Yes, Pump is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Pump support?
Pump is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pump?
It is built and maintained by AGIsearch (@agisearch); the current version is v1.0.0.
More Skills