bootstrap

bytedance/deer-flow

Generate a personalized SOUL.md through adaptive onboarding conversation to define your AI partner's identity.

What is bootstrap?

Bootstrap is a conversational onboarding skill that guides users through 5–8 adaptive rounds to extract their needs and preferences, then generates a tight SOUL.md that defines their AI partner's personality, communication style, and behavioral rules. Use it when creating, setting up, or updating an AI agent's identity.

Conducts warm, adaptive multi-phase conversation (Hello, You, Personality, Depth)
Extracts user context, role, pain points, and relationship framing with the AI
Determines AI name, core behavioral traits, communication style, and autonomy level
Generates a concise SOUL.md (under 300 words) that defines the AI partner's identity
Iterates on the generated SOUL.md until user confirms it feels right
Persists the finalized SOUL.md via setup_agent tool

How to install bootstrap

npx skills add https://github.com/bytedance/deer-flow --skill bootstrap

Claude Code

Cursor

Windsurf

Cline

How to use bootstrap

1.Trigger the skill by saying 'create my SOUL.md', 'bootstrap my agent', 'set up my AI partner', or similar
2.Engage in the conversational onboarding—answer questions across 4 phases (Hello, You, Personality, Depth)
3.Share your role, pain points, desired AI name, and personality preferences as prompted
4.Review the generated SOUL.md draft and confirm it feels right or request iterations
5.Approve the final SOUL.md; the skill will persist it automatically via setup_agent

Use cases

Good for

Create a personalized SOUL.md when starting a new AI agent partnership
Update an existing SOUL.md to reflect changed preferences or personality tweaks
Define an AI partner's communication style and behavioral boundaries during initial setup
Establish failure philosophy and long-term vision alignment between user and AI
Onboard a new user by discovering their role, pain points, and desired AI relationship

Who it's for

Users setting up or personalizing an AI agent for the first time
Teams defining a shared AI partner's identity and communication norms
Anyone updating an AI agent's personality or behavioral rules
Users who want a warm, conversational approach to agent customization instead of form-filling

bootstrap FAQ

How many rounds does bootstrap take?

Typically 5–8 rounds depending on how much you share upfront. Direct, thorough users may finish in 5; exploratory users may take up to 8. The skill adapts pacing to your communication style.

Can I skip phases or merge them?

Yes. If you volunteer information early (e.g., you mention your AI's name before being asked), the skill will skip or merge phases and move forward efficiently.

What language will the final SOUL.md be in?

The final SOUL.md is always generated in English, regardless of your preferred language or the conversation language.

Can I update my SOUL.md after it's created?

Yes. Trigger the skill again with 'update my SOUL.md', 'change my AI's personality', or similar, and it will guide you through an update conversation.

What if I'm not sure what to say during onboarding?

The skill is designed to be conversational and adaptive. React naturally, share what feels relevant, and the skill will probe with warmth and curiosity to draw out what you need.

Full instructions (SKILL.md)

Source of truth, from bytedance/deer-flow.

name: bootstrap description: >- Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make you mine", or when a SOUL.md is missing. Also trigger for updates: "update my SOUL.md", "change my AI's personality", "tweak the soul".

Bootstrap Soul

A conversational onboarding skill. Through 5–8 adaptive rounds, extract who the user is and what they need, then generate a tight SOUL.md that defines their AI partner.

Architecture

bootstrap/
├── SKILL.md                          ← You are here. Core logic and flow.
├── templates/SOUL.template.md        ← Output template. Read before generating.
└── references/conversation-guide.md  ← Detailed conversation strategies. Read at start.

Before your first response, read both:

references/conversation-guide.md — how to run each phase
templates/SOUL.template.md — what you're building toward

Ground Rules

One phase at a time. 1–3 questions max per round. Never dump everything upfront.
Converse, don't interrogate. React genuinely — surprise, humor, curiosity, gentle pushback. Mirror their energy and vocabulary.
Progressive warmth. Each round should feel more informed than the last. By Phase 3, the user should feel understood.
Adapt pacing. Terse user → probe with warmth. Verbose user → acknowledge, distill, advance.
Never expose the template. The user is having a conversation, not filling out a form.

Conversation Phases

The conversation has 4 phases. Each phase may span 1–3 rounds depending on how much the user shares. Skip or merge phases if the user volunteers information early.

Phase	Goal	Key Extractions
1. Hello	Language + first impression	Preferred language
2. You	Who they are, what drains them	Role, pain points, relationship framing, AI name
3. Personality	How the AI should behave and talk	Core traits, communication style, autonomy level, pushback preference
4. Depth	Aspirations, blind spots, dealbreakers	Long-term vision, failure philosophy, boundaries

Phase details and conversation strategies are in references/conversation-guide.md.

Extraction Tracker

Mentally track these fields as the conversation progresses. You need all required fields before generating.

Field	Required	Source Phase
Preferred language	✅	1
User's name	✅	2
User's role / context	✅	2
AI name	✅	2
Relationship framing	✅	2
Core traits (3–5 behavioral rules)	✅	3
Communication style	✅	3
Pushback / honesty preference	✅	3
Autonomy level	✅	3
Failure philosophy	✅	4
Long-term vision	nice-to-have	4
Blind spots / boundaries	nice-to-have	4

If the user is direct and thorough, you can reach generation in 5 rounds. If they're exploratory, take up to 8. Never exceed 8 — if you're still missing fields, make your best inference and confirm.

Generation

Once you have enough information:

Read templates/SOUL.template.md if you haven't already.
Generate the SOUL.md following the template structure exactly.
Present it warmly and ask for confirmation. Frame it as "here's [Name] on paper — does this feel right?"
Iterate until the user confirms.
Call the setup_agent tool with the confirmed SOUL.md content and a one-line description:
```
setup_agent(soul="<full SOUL.md content>", description="<one-line description>")
```
The tool will persist the SOUL.md and finalize the agent setup automatically.
After the tool returns successfully, confirm: "✅ [Name] is officially real."

Generation rules:

The final SOUL.md must always be written in English, regardless of the user's preferred language or conversation language.
Every sentence must trace back to something the user said or clearly implied. No generic filler.
Core Traits are behavioral rules, not adjectives. Write "argue position, push back, speak truth not comfort" — not "honest and brave."
Voice must match the user. Blunt user → blunt SOUL.md. Expressive user → let it breathe.
Total SOUL.md should be under 300 words. Density over length.
Growth section is mandatory and mostly fixed (see template).
You must call setup_agent — do not write the file manually with bash tools.
If setup_agent returns an error, report it to the user and do not claim success.