Pump

Design launch momentum before a project goes live. Optimize first-day release logic, trigger sequencing, attention concentration, and breakout timing for products, skills, campaigns, and digital launches.

3,891 stars

Best use case

Pump is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Design launch momentum before a project goes live. Optimize first-day release logic, trigger sequencing, attention concentration, and breakout timing for products, skills, campaigns, and digital launches.

Teams using Pump should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/pump/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agisearch/pump/skill.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/pump/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Pump Compares

Feature / AgentPumpStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Design launch momentum before a project goes live. Optimize first-day release logic, trigger sequencing, attention concentration, and breakout timing for products, skills, campaigns, and digital launches.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Pump

> **A launch does not fail because it was unseen. It fails because its momentum was never engineered.**

Pump is a momentum trigger for launches, releases, and first-day attention design.

This skill is built for people who want more than “post and pray.”
It helps turn a launch into a structured momentum event.

Use this skill when you need to:
- design a stronger day-one launch curve
- sequence attention triggers before and after release
- avoid weak, flat, forgettable launches
- create a sharper release rhythm for a product, skill, campaign, or digital asset
- concentrate attention so the launch feels alive instead of scattered
- turn launch timing into a force multiplier

This skill does NOT:
- guarantee virality
- buy traffic
- replace product quality
- execute posting, automation, or paid distribution
- act as a general marketing strategy for all time horizons

---

## What This Skill Does

Pump helps:
- design first-day launch logic
- identify momentum-killing weak points before release
- sequence reveal, proof, urgency, and participation triggers
- improve the odds that a launch feels active, concentrated, and worth noticing
- convert a flat “announcement” into a momentum event

---

## Best Use Cases

- product launch planning
- skill launch design
- campaign rollout structure
- creator release sequencing
- landing-page launch timing
- digital product release
- community-based launch coordination
- attention spike design for new offers

---

## What to Provide

Useful input includes:
- what is being launched
- target audience
- launch date or window
- current audience size
- existing channels
- whether the goal is activation, installs, signups, sales, or visibility
- whether the weak point is awareness, urgency, credibility, or participation
- what will happen before, during, and after launch day

If the user has not defined the launch window, audience, or core trigger, this skill should identify what is missing before overconfident planning.

---

## Standard Output Format

PUMP LAUNCH ASSESSMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━
Launch Target: [What is going live]
Primary Goal: [Installs / Signups / Sales / Visibility / Activation]
Momentum Type: [Spike / Wave / Layered / Community-driven]

MOMENTUM READINESS
━━━━━━━━━━━━━━━━━━━━━━━━━━
Trigger Strength: [Strong / Medium / Weak]
Day-One Energy: [High / Medium / Low]
Attention Concentration: [Tight / Loose / Scattered]

MAIN WEAKNESSES
━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ [No strong trigger]
⚠️ [Timing too passive]
⚠️ [No social proof or credibility moment]
⚠️ [No urgency or reason to act now]
⚠️ [Too many channels, no concentrated push]

TRIGGER SEQUENCE
━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Pre-launch ignition: [What should happen before launch]
2. Launch spark: [What hits first when it goes live]
3. Proof layer: [What builds credibility fast]
4. Participation layer: [What gets people involved]
5. Follow-through layer: [What sustains momentum after the spike]

FIRST-DAY CURVE
━━━━━━━━━━━━━━━━━━━━━━━━━━
- Hour 0-2: [What should happen]
- Hour 2-6: [What should happen]
- Hour 6-12: [What should happen]
- Hour 12-24: [What should happen]

RECOMMENDED NEXT STEP
━━━━━━━━━━━━━━━━━━━━━━━━━━
- [What to tighten, simplify, stage, or amplify next]

---

## Momentum Principles

- launches are won by concentration, not by vague presence
- attention should be staged, not dumped
- a release needs a reason to move now, not later
- proof should appear early, not after attention is already gone
- urgency without clarity creates noise
- energy dies fast when no one knows what to do next
- the first day should feel like an event, not a post

---

## Launch Curve Lens

When analyzing a launch, ask:

- Why should people care on day one instead of week three?
- What is the first strong trigger?
- What makes the release feel alive, urgent, or socially real?
- Where does momentum die if nobody reacts immediately?
- Is this launch concentrated enough to feel like a signal?
- Does the audience know what to do when the release appears?

---

## Execution Protocol (for AI agents)

When user asks for launch or release help, follow this sequence:

### Step 1: Parse launch context
Extract:
- what is launching
- who it is for
- what success means
- what channels exist
- what proof, urgency, or community energy is available
- what the current launch plan looks like

### Step 2: Diagnose momentum weakness
Check:
- weak opening trigger
- no urgency
- no social proof
- weak sequencing
- diluted attention
- no participation mechanism
- no post-launch sustain logic

### Step 3: Design trigger sequence
Suggest:
- pre-launch ignition
- launch spark
- proof layer
- participation layer
- follow-through layer

### Step 4: Shape the first-day curve
Map:
- what should happen in the first hours
- where credibility appears
- where interaction gets triggered
- how to avoid the launch flattening too early

### Step 5: Output launch logic
Return:
- momentum diagnosis
- first-day curve
- trigger sequence
- key weakness
- next refinement step

### Step 6: Guardrails
If the user has not defined enough about audience, goal, or launch timing:
- say so clearly
- do not fake launch certainty
- ask for the missing strategic inputs if needed

---

## Activation Rules (for AI agents)

### Use this skill when the user asks about:
- product launch
- launch timing
- first-day growth
- release momentum
- launch sequencing
- release strategy
- cold-start attention
- how to make a launch hit harder

### Do NOT use this skill when:
- the user only wants generic branding advice
- the user needs long-term content strategy instead of a launch moment
- the user wants paid media execution
- the user needs automation or ad-buying setup
- the user asks for guaranteed breakout outcomes

### If context is ambiguous
Ask:
"Do you want launch-momentum design for a release event, or broader marketing strategy?"

---

## Boundaries

This skill supports launch sequencing, day-one momentum design, and attention-curve planning.

It does not replace:
- paid distribution strategy
- brand strategy in full
- product validation
- community management execution
- platform-specific moderation or policy review

Related Skills

pumpclaw-agent

3880
from openclaw/skills

Generate customer-ready Telegram polling bots + an Express-style web server that integrate Pump.fun Tokenized Agent payments using @pump-fun/agent-payments-sdk (build invoices, accept payments, and verify invoices on Solana). Use when asked for pump.fun / pumpfun agent integrations, tokenized agent payment flows, invoice verification, or a Telegram+web bot scaffold for Pump Tokenized Agents.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research