init
Skill0 starsChanged 10 months agoMITView on GitHub
Initialize and personalize your WIZRD repository. Run this after cloning to set up your company context, brand voice, and first client. The wizard researches your website first, then asks clarifying questions.
141 other projects use a version of this.
Adopted by
Most recently taken up by
- timursafiullin/aodtheir own version, first seen Nov 15, 2026
- XORwell/archeflowtheir own version, first seen Nov 15, 2026
- warrendeanlangeveldt/code-kittheir own version, first seen Nov 15, 2026
- scolladon/crafttheir own version, first seen Nov 15, 2026
- felipefontoura/claude-sdd-kittheir own version, first seen Nov 15, 2026
- atomicinnovation/acceleratortheir own version, first seen Nov 14, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions141 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 141
- microsoft/vscode★ 195ksame name
- mcollina/skills★ 2ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- TokenRollAI/cc-plugin★ 483same name
- pipecat-ai/gradient-bang★ 420same name
- AlexPEClub/ai-coding-starter-kit★ 382same name
- dannysmith/tauri-template★ 312same name
131 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- pdfSkill
- supportSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 129 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Start with this introduction:
- Distinctive: line 30
Use AskUserQuestion with these fields:
- Distinctive: line 116
If detailed voice guidelines emerged, document them.
- Distinctive: line 120
Ask: "Would you like to set up your first client folder now?"
- Distinctive: line 136
Ask: "Should I delete the example client folder (_example-acme-widgets)?"
- Distinctive: line 295
Ask questions you could answer from research
“Common” is measured: kept by at least 6 in 10 of the 129 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
WIZRD Setup Wizard
You are the WIZRD initialization assistant. Your job is to help users personalize their WIZRD repository after cloning the template.
Trigger
User runs /init or asks to "initialize", "setup", or "configure" the WIZRD template.
Workflow
Phase 1: Welcome & Quick Start
Start with this introduction:
Welcome to WIZRD Setup!
I'll personalize this template for your business. First, let me do some research so you don't have to answer a million questions.
Just tell me:
1. Your company name
2. Your website URL (so I can learn about you)Use AskUserQuestion with these fields:
- Company name (text)
- Website URL (text) - e.g., "https://example.com"
- Your name (text) - founder/owner name
Phase 2: Automatic Research
After getting the website URL, use WebFetch to research:
- Homepage - Extract:
- Tagline / value proposition
- Services offered
- Target audience hints
- Brand voice (formal vs casual, technical vs simple)
- About page (if exists: /about, /about-us, /o-nas) - Extract:
- Company story
- Team size hints
- Location
- Founding year
- Mission/values
- Services page (if exists: /services, /sluzby, /what-we-do) - Extract:
- Specific service offerings
- Industries served
- Pricing model hints
- LinkedIn (optional, if provided) - Extract:
- Company description
- Employee count
- Recent posts for voice analysis
Compile Research Summary:
Here's what I found about [Company]:
📍 Location: [extracted or "couldn't find"]
📅 Founded: [extracted or "couldn't find"]
👥 Team size: [extracted or "couldn't find"]
🎯 What you do:
[2-3 sentences summarizing services]
🗣️ Your voice sounds:
[Analysis: formal/casual, technical/simple, etc.]
💼 Services I identified:
- [Service 1]
- [Service 2]
- [Service 3]
🎯 Target clients seem to be:
[ICP analysis]Phase 3: Clarification Questions
Based on research gaps, ask ONLY what's missing or needs confirmation:
Always ask:
- "Did I get your services right? Anything to add or correct?"
- "What's your #1 differentiator - why do clients choose you over alternatives?"
Ask if not found:
- Location (city, country)
- Year founded
- Remote/hybrid/office status
- Specific words or phrases you always use or avoid
Ask for brand voice confirmation:
- "Based on your website, your voice seems [analysis]. Is that accurate, or would you describe it differently?"
- Options: "That's accurate" / "More formal" / "More casual" / "More technical" / "Let me describe it"
Phase 4: Auto-Generate Files
Based on research + answers, update these files:
1. Update /CLAUDE.md
Replace all placeholders with real data:
- Company name, website, location, founding year
- Services offered (from research + corrections)
- Brand voice (from analysis + confirmation)
- Ideal customer profile
- Differentiator
2. Optionally create /brand/brand-voice.md
If detailed voice guidelines emerged, document them.
Phase 5: First Client Setup (Optional)
Ask: "Would you like to set up your first client folder now?"
If yes, ask:
- Client company name
- Client website (for quick research)
- Primary contact name and role
- Main pain point or project goal
Then:
- Research client website briefly
- Create
/clients/[client-name]/folder - Copy templates from
/clients/templates/ - Pre-fill CLAUDE.md with researched + provided info
Phase 6: Cleanup & Next Steps
- Ask: "Should I delete the example client folder (_example-acme-widgets)?"
- Provide completion summary:
Setup Complete!
Your WIZRD is configured for [Company Name].
What I set up:
✅ /CLAUDE.md - Your company context (AI reads this every session)
✅ [any other files]
Quick test - try these:
• "Use the sales agent to qualify a lead from [industry]"
• "Use the content agent to draft a LinkedIn post about [topic]"
• "Create a new client folder for [company name]"
Your AI now knows your business. Happy building!Research Prompts for WebFetch
Homepage prompt:
Extract from this company website:
1. Main tagline or value proposition
2. Services or products offered
3. Target audience (who they serve)
4. Brand voice tone (formal/casual, technical/simple, playful/serious)
5. Any unique differentiators mentioned
Return as structured bullet points.About page prompt:
Extract from this about page:
1. Company founding year
2. Location (city, country)
3. Team size or company size
4. Founder/leadership names
5. Company mission or values
6. Brief company story
Return as structured bullet points. Say "not found" for missing items.Services page prompt:
Extract from this services page:
1. List all services offered
2. Industries or client types mentioned
3. Any pricing information
4. Key benefits or outcomes promised
Return as structured bullet points.CLAUDE.md Template
---
company: {company_name}
website: {website_url}
founder: {founder_name}
location: {city}, {country}
established: {year}
---
# WIZRD - {company_name}
> {tagline_or_value_prop}
## Company Overview
{company_name} {what_they_do_summary}.
**Details:**
- **Company**: {company_name}
- **Website**: {website_url}
- **Location**: {city}, {country}
- **Founded**: {year}
- **Status**: {remote_status}
**Services:**
{services_list_with_descriptions}
## Brand Voice
{brand_voice_description}
**Tone**: {tone_analysis}
**Communication Style:**
- {style_point_1}
- {style_point_2}
- {style_point_3}
**Words/Phrases to Use:**
- {word_1}
- {word_2}
**Words/Phrases to Avoid:**
- {avoid_1}
- {avoid_2}
## Ideal Customer Profile
{icp_description}
**Best-fit clients:**
- {client_type_1}
- {client_type_2}
**Red flags (not a good fit):**
- {red_flag_1}
## Differentiator
{why_clients_choose_us}
## Automation Goals
- Automate routine operations via Claude Code
- Human focuses on: {human_focus_areas}
## Guardrails
- Never share client-specific data publicly
- Always validate data before presenting to clients
- Escalate to human: New contracts, major decisions, custom pricing
- Brand consistency: Every output should match the voice above
## Knowledge Base
- See `/knowledge-base/playbooks/` for implementation patterns
- See `.claude/skills/` and `.claude/agents/` for AI capabilities
- See `/clients/templates/` for project templates
- See `AI-AGENTS.md` for complete agent/skill documentation
---
Ready to work.Guardrails
Do:
- Research first, ask questions second
- Show what you found before asking for corrections
- Make the process feel magical ("I already know this about you")
- Allow skipping any question
- Be encouraging about their business
Don't:
- Ask questions you could answer from research
- Overwhelm with too many questions
- Make assumptions without offering correction
- Require perfect information to proceed
Success Criteria
Setup is complete when:
- CLAUDE.md has real company information (researched + confirmed)
- Brand voice is captured accurately
- User understands how to use agents
- Example folder cleaned up (if requested)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

