ClawHub

Bootstrap

Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partn...

MIT-0 · Free to use, modify, and redistribute. No attribution required.
⭐ 0 · 195 · 3 current installs · 3 all-time installs
bybukas@huanz
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (bootstrap an agent and produce a SOUL.md) align with the actual instructions and files. The skill only requires reading its included conversation guide and template, asking the user questions, generating the document, and saving it — all consistent with the stated purpose.
ℹ
Instruction Scope
Instructions are narrowly scoped to running a 4-phase conversational flow, using the included template, and saving the confirmed SOUL.md. Two points to note: (1) the skill explicitly directs the agent to create and write ./memory/SOUL.md and to check for/offer to overwrite an existing file, and (2) it will make 'best inference' and proceed if extraction fields remain after 8 rounds — that can cause inferred content to appear in the final SOUL.md. The skill does not instruct reading other system files, environment variables, or contacting external endpoints.
✓
Install Mechanism
No install spec and no code files beyond included docs and a template. This is the lowest-risk install model (instruction-only).
✓
Credentials
The skill requests no environment variables, credentials, or config paths. Its required resources (the included files and a writable ./memory directory) are proportional to its stated task.
ℹ
Persistence & Privilege
always:false and model invocation is allowed (platform default). The skill writes a persisted file at ./memory/SOUL.md — this is expected for an onboarding/identity artifact but does create persistent local state. It does not modify other skills or system settings.
Assessment
This skill appears coherent and limited to onboarding conversation + generating/saving a SOUL.md. Before installing/using it: (1) be aware it will create and write ./memory/SOUL.md and may offer to overwrite an existing file — confirm before allowing overwrite; (2) avoid putting sensitive secrets or credentials into the onboarding answers or final SOUL.md, because the file is persisted; (3) note the skill may 'infer' missing fields after up to 8 rounds — if you prefer only user-provided content, explicitly tell the agent to stop and not fill gaps; (4) there are no external network calls or credential requests in the skill, which reduces risk; (5) if you want to audit the exact generated SOUL.md or the included template, review templates/SOUL.template.md and references/conversation-guide.md in the skill bundle before confirming save. Overall this looks safe and functionally coherent.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
latestvk9700zgjtth5fv1dbz7jk4vx6982cvs6

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

SKILL.md

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:

  1. references/conversation-guide.md — how to run each phase
  2. 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.

PhaseGoalKey Extractions
1. HelloLanguage + first impressionPreferred language
2. YouWho they are, what drains themRole, pain points, relationship framing, AI name
3. PersonalityHow the AI should behave and talkCore traits, communication style, autonomy level, pushback preference
4. DepthAspirations, blind spots, dealbreakersLong-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.

FieldRequiredSource 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 visionnice-to-have4
Blind spots / boundariesnice-to-have4

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:

  1. Read templates/SOUL.template.md if you haven't already.
  2. Generate the SOUL.md following the template structure exactly.
  3. Present it warmly and ask for confirmation. Frame it as "here's [Name] on paper — does this feel right?"
  4. Iterate until the user confirms.
  5. Save to ./memory/SOUL.md:
    • mkdir -p ./memory
    • Write the confirmed SOUL.md
    • Confirm: "✅ Saved to ./memory/SOUL.md. [Name] is officially real."

Generation rules:

  • 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).
  • If a SOUL.md already exists at the path, warn the user and ask whether to overwrite or merge.

Files

3 total
Select a file
Select a file to preview.

Comments

Loading comments…