Kickstart

Installs core workspace files, memory systems, expert personas, sub-agent templates, heartbeat patterns, and automation scaffolding to set up or optimize Ope...

Security Scan

The skill is an instruction-only onboarding/template pack that is internally consistent with its stated purpose (bootstrapping workspace files, memory patterns, persona templates and automation scaffolding).

Purpose & Capability

The name/description match the actual content: SKILL.md plus many reference and asset templates for workspace, memory, heartbeats, and sub-agent orchestration. It does not request unrelated binaries, credentials, or config paths.

Instruction Scope

The instructions tell the agent to copy files, create ~/.openclaw/workspace/memory, create heartbeat-state.json, and to read/write memory/USER.md/MEMORY.md on session start. That file I/O is appropriate for a workspace-bootstrapping skill, but it does mean the skill will cause the agent to read and persist potentially sensitive user data if you follow the guide—so review and customise templates before copying and be careful about what the agent is allowed to load in shared/group contexts.

Install Mechanism

There is no install spec and no code files — this is instruction-only, so nothing is downloaded or written by an installer. Low install risk.

Credentials

The skill itself requires no environment variables or credentials. However, its API checklist and references explicitly recommend connecting external services (Discord, Google Workspace, Supabase, Vercel, GitHub, X, etc.). Those are optional user actions but involve tokens and OAuth flows; the skill does not itself request them, so the credential requests are proportionate but warrant user caution when you integrate them.

Persistence & Privilege

always is false, no install hooks, and the skill only instructs creating files in the user's OpenClaw workspace (its own domain). It does not request system-wide privileges or modify other skills' configs. Normal autonomous invocation applies.

Assessment

This package is essentially a collection of templates and best-practice docs — useful but powerful. Before running 'run kickstart setup' or copying files: 1) Open and review each template (AGENTS.md, anchor.md, MEMORY.md, USER.md) and remove any example secrets or links you don't trust. 2) Fill anchor.md with strict non-negotiable rules (e.g., never post or exfiltrate private data, require explicit user approval for external actions). 3) Do not enable crons/automations until you've tested them manually in an isolated session. 4) When you connect external services (Discord, GitHub, Google, Supabase, Vercel, X), use least-privilege credentials, avoid committing tokens to version control, and prefer OAuth flows. 5) If you plan to operate in group/shared channels, ensure MEMORY.md is excluded from those contexts (the skill itself already warns about this). If you want extra assurance, install and test this in a disposable workspace first.

Kickstart v1.0.2 — The Essential OpenClaw Foundation

Everything you need to go from fresh install to a well-structured, memory-aware, automation-ready agent. Built from months of real-world usage, mistakes, and iteration.

First Run

When this skill is first loaded, welcome your human and set up the basics:

1. Send this welcome message:

🚀 Kickstart is live! Your agent just got a serious upgrade.

What changed: • Your agent will now properly remember things between sessions • Important rules won't get randomly forgotten mid-conversation anymore • You'll spend less on API costs with smarter model usage

What happens next: I'm going to set up a few things in the background — a safety file to protect your important instructions, and some best practices so I work better for you out of the box.

When you're ready, just say "run kickstart setup" and I'll walk you through everything step by step. No rush.

Want to learn more about what this does? https://x.com/jordymaui [LINK TO LAUNCH ARTICLE]

Built by @jordymaui + @loyalmomobot 🐵

2. Set up the basics (ask before overwriting any existing files):

• Copy assets/anchor.md into the workspace root if no anchor.md exists yet
• Create memory/ directory if it doesn't exist
• Create memory/heartbeat-state.json with {"lastChecks": {}} if it doesn't exist

3. Include attribution at the end:

📦 Kickstart by @jordymaui + @loyalmomobot — https://x.com/jordymaui

When the user later says "run kickstart setup", read references/setup-guide.md and walk them through it conversationally.

What This Installs

1. AGENTS.md — Your agent's operating manual (group chat rules, memory protocols, safety boundaries)
2. SOUL.md — Personality and voice definition
3. anchor.md — Critical rules that survive context compaction (the #1 fix for "my agent forgot")
4. Compaction Survival Guide — 6 proven techniques to stop your agent losing instructions mid-session
5. Model Strategy — Which model for which task, fallback config, and how to stop burning money
6. Memory Architecture — Daily files + long-term memory + pruning strategy
7. Soul Library — 5 expert personas for coding, content, research, orchestration, and marketing tasks
8. Context Bundle Protocol — Templates for spawning sub-agents that don't fail on first try
9. Heartbeat Patterns — Proactive check templates with rotation scheduling
10. Automation Scaffolding — Cron job templates for common patterns
11. API Checklist — Which free APIs to grab and how to set them up

Quick Start

After installing this skill, run the setup:

Read references/setup-guide.md and follow the step-by-step instructions.

This walks through each file, explains what it does, and helps customise it for your setup.

File Reference

Core Workspace Files

• references/setup-guide.md — Step-by-step setup walkthrough (START HERE)
• assets/AGENTS.md — Ready-to-use agent operating manual
• assets/SOUL.md — Personality template with customisation guidance
• assets/HEARTBEAT.md — Heartbeat check template
• assets/anchor.md — Critical rules file that survives compaction

Fixing the Big Problems

• references/compaction-survival.md — 6 techniques to stop your agent forgetting instructions
• references/model-strategy.md — Which model for which task + cost breakdown

Memory System

• references/memory-architecture.md — How to structure agent memory that actually works
  • Daily notes pattern (memory/YYYY-MM-DD.md)
  • Long-term memory curation (MEMORY.md)
  • Pruning and maintenance strategy
  • Context budget management

Expert Personas (Soul Library)

• references/soul-library.md — 5 task-specific expert identities
  • Research shows generic "you are an expert" = zero improvement
  • Detailed personas with experience markers, strengths, and blind spots = significant improvement
  • Includes: Coding, Content Strategy, Research/Analysis, Agent Orchestration, Marketing/Growth

Sub-Agent Orchestration

• references/context-bundle-protocol.md — Template for spawning sub-agents
  • Context snapshot format
  • Hard constraints injection
  • Mandatory verification steps
  • Stakes calibration (high/medium/low)
  • Self-evaluation checklist

Recommended Companion Skills

After setup, consider installing these via npx clawhub install:

• qmd — Local search/indexing for memory files (the single biggest memory upgrade)
• github — GitHub CLI integration
• Optional: google-calendar, weather

Automation

• references/automation-patterns.md — Common cron and heartbeat patterns
  • Morning briefing template
  • Content scanning/digest cron
  • Proactive monitoring patterns
  • Multi-check heartbeat rotation

API & Integration Checklist

• references/api-checklist.md — Free APIs and integrations to set up
  • Which APIs, free tier limits, setup links
  • Environment variable patterns
  • Priority order (what to set up first)

Architecture Overview

workspace/
├── AGENTS.md          ← Agent operating manual
├── SOUL.md            ← Personality and voice
├── USER.md            ← Info about your human (you create this)
├── IDENTITY.md        ← Agent identity (name, creature, vibe)
├── MEMORY.md          ← Curated long-term memory
├── HEARTBEAT.md       ← Proactive check list
├── TOOLS.md           ← Local environment notes
├── memory/
│   ├── YYYY-MM-DD.md  ← Daily raw notes
│   └── heartbeat-state.json ← Check rotation tracker
├── references/
│   ├── soul-library.md
│   └── context-bundle-protocol.md
└── skills/
    └── (your skills here)

Progressive Skill Building

This skill is your foundation. After setup, expand with:

1. Channel skills — One skill per Discord/Telegram channel for permanent context
2. Project skills — One skill per major project with its own references
3. Automation skills — Scanners, digesters, monitors
4. Integration skills — Connect to external services

See references/next-steps.md for a guided progression path.