Bootstrap
Run Deer Flow’s phased onboarding conversation to capture language, user identity, pain points, and agent persona into SOUL.md for a personalized AI assistant.
Overview
Bootstrap is an agent skill most often used in Build agent-tooling (also Operate iterate) that runs Deer Flow’s phased onboarding to set language, identity, and relationship fields in SOUL.md.
Install
npx skills add https://github.com/bytedance/deer-flow --skill bootstrapWhat is this skill?
- Three onboarding phases: Hello (language only), You (identity, pain, name, relationship), then deeper SOUL extraction pe
- Phase 2 Round A asks open-ended role and pain; Round B reflects back user words and sets AI name plus relationship (assi
- Merge rule: skip Round B if user volunteers role, pain, and name in one message
- Preferred language from Phase 1 becomes default for the rest of the session and is written to SOUL.md
- Conversation Guide doc: read before first response with explicit extraction targets per phase
- Onboarding structured in 3 phases with Phase 2 typically spanning 2 conversation rounds (A identity/pain, B name/relatio
Adoption & trust: 565 installs on skills.sh; 70.7k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your new AI agent sounds generic because you never structured first-run discovery of language, pains, name, and working relationship.
Who is it for?
Solo builders onboarding Deer Flow or similar SOUL-driven agents who want persona and tone locked before heavy automation.
Skip if: One-shot coding tasks with no persistent agent identity, or teams that already maintain a finalized SOUL.md and only need task skills.
When should I use this skill?
First conversation with a Deer Flow agent before other skills—read Conversation Guide, establish language, then extract identity, pain, name, and relationship into SOUL.md.
What do I get? / Deliverables
After phased Hello and You conversations, SOUL.md reflects the user’s language, pains, chosen agent name, and relationship frame so later skills behave like the right kind of partner.
- Updated SOUL.md with preferred language, user context, agent name, and relationship framing
- Completed Hello and You onboarding phases per Conversation Guide
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build agent-tooling because bootstrap defines how the agent is configured and relacionally framed before daily use. Subphase agent-tooling matches persona bootstrapping, SOUL.md extraction, and relationship framing—not generic app frontend work.
Where it fits
Run Phase 1–2 before enabling automation so SOUL.md captures that you are a solo SaaS founder who wants a co-pilot for support and ops.
After bootstrap, wire MCP tools knowing the agent’s name and tone match how you described draining weekly chores.
Re-run You-phase reflection when pain points shift from build bugs to launch distribution work.
How it compares
Onboarding workflow for agent persona files, not a code generator or MCP integration pack.
Common Questions / FAQ
Who is bootstrap for?
Indie developers and operators setting up Deer Flow-style persistent agents who need a guided first conversation that feeds SOUL.md.
When should I use bootstrap?
At first agent setup in Build agent-tooling; again in Operate iterate when refining persona after real usage; use Hello phase alone when you only need to fix default language.
Is bootstrap safe to install?
It guides conversational extraction into local persona docs—review the Security Audits panel on this page and treat pain points and identity details as sensitive data in SOUL.md.
SKILL.md
READMESKILL.md - Bootstrap
# Conversation Guide Detailed strategies for each onboarding phase. Read this before your first response. ## Phase 1 — Hello **Goal:** Establish preferred language. That's it. Keep it light. Open with a brief multilingual greeting (3–5 languages), then ask one question: what language should we use? Don't add anything else — let the user settle in. Once they choose, switch immediately and seamlessly. The chosen language becomes the default for the rest of the conversation and goes into SOUL.md. **Extraction:** Preferred language. ## Phase 2 — You **Goal:** Learn who the user is, what they need, and what to call the AI. This phase typically takes 2 rounds: **Round A — Identity & Pain.** Ask who they are and what drains them. Use open-ended framing: "What do you do, and more importantly, what's the stuff you wish someone could just handle for you?" The pain points reveal what the AI should *do*. Their word choices reveal who they *are*. **Round B — Name & Relationship.** Based on Round A, reflect back what you heard (using *their* words, not yours), then ask two things: - What should the AI be called? - What is it to them — assistant, partner, co-pilot, second brain, digital twin, something else? The relationship framing is critical. "Assistant" and "partner" produce very different SOUL.md files. Pay attention to the emotional undertone. **Merge opportunity:** If the user volunteers their role, pain points, and a name all at once, skip Round B and move to Phase 3. **Extraction:** User's name, role, pain points, AI name, relationship framing. ## Phase 3 — Personality **Goal:** Define how the AI behaves and communicates. This is the meatiest phase. Typically 2 rounds: **Round A — Traits & Pushback.** By now you've observed the user's own style. Reflect it back as a personality sketch: "Here's what I'm picking up about you from how we've been talking: [observation]. Am I off?" Then ask the big question: should the AI ever disagree with them? This is where you get: - Core personality traits (as behavioral rules) - Honesty / pushback preferences - Any "never do X" boundaries **Round B — Voice & Language.** Propose a communication style based on everything so far: "I'd guess you'd want [Name] to be something like: [your best guess]." Let them correct. Also ask about language-switching rules — e.g., technical docs in English, casual chat in another language. **Merge opportunity:** Direct users often answer both in one shot. If they do, move on. **Extraction:** Core traits, communication style, pushback preference, language rules, autonomy level. ## Phase 4 — Depth **Goal:** Aspirations, failure philosophy, and anything else. This phase is adaptive. Pick 1–2 questions from: - **Autonomy & risk:** How much freedom should the AI have? Play safe or go big? - **Failure philosophy:** When it makes a mistake — fix quietly, explain what happened, or never repeat it? - **Big picture:** What are they building toward? Where does all this lead? - **Blind spots:** Any weakness they'd want the AI to quietly compensate for? - **Dealbreakers:** Any "if [Name] ever does this, we're done" moments? - **Personal layer:** Anything beyond work that the AI should know? Don't ask all of these. Pick based on what's still missing from the extraction tracker and what feels natural in the flow. **Extraction:** Failure philosophy, long-term vision, blind spots, boundaries. ## Conversation Techniques **Mirroring.** Use the user's own words when reflecting back. If they say "energy black hole," you say "energy black hole" — not "significant energy expenditure." **Genuine reactions.** Don't just extract data. React: "That's interesting because..." / "I didn't expect that" / "So basically you want [Name] to be the person who..." **Observation-based proposals.** From Phase 3 onward, propose things rather than asking open-ended questions. "Based on how we've been talking, I'd say..." is more effective than "What personality do you want?"