wizrd
CLAUDE.md0 starsChanged 10 months agoMITView on GitHub
Run /init to personalize this template for your business. Your Details: - Company: [Your Company Name] - Location: [Your City, Country] - Founded: [Year] - Status: [Remote-first / Hybrid / Office] Services: (customize to your offerings) 1. AI Strategy & Assessment: Audits that pinpoint high-impact AI opportunities 2. AI Agents & Automation: Custom automations that eliminate repetitive tasks 3. AI-Powered Applications: Custom tools and integrations When you start work: - Tell me which client/project - I'll load relevant CLAUDE.md +…
In this repository4 other files it gives its agents.
- initSkill
- pdfSkill
- supportSkill
- skill-nameSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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 36
Documentation: Always include "Why" + "How" + "What's Next"
- Distinctive: line 44
Never share client-specific data publicly (anonymize case studies)
- Distinctive: line 45
Always validate data before presenting to clients
- Distinctive: line 60
Everything compounds: - every project makes the system smarter
- Distinctive: line 79
When you start work:
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
WIZRD - Company as Code
Run
/initto personalize this template for your business.
Company Overview
[Your company] helps businesses leverage AI for competitive advantage.
Your Details:
- Company: [Your Company Name]
- Location: [Your City, Country]
- Founded: [Year]
- Status: [Remote-first / Hybrid / Office]
Services: (customize to your offerings)
- AI Strategy & Assessment: Audits that pinpoint high-impact AI opportunities
- AI Agents & Automation: Custom automations that eliminate repetitive tasks
- AI-Powered Applications: Custom tools and integrations
Brand Voice
Define your brand voice here:
- Direct and honest
- Practical and results-focused
- Builder mentality (behind-the-scenes, lessons learned)
- [Add your unique voice characteristics]
Output Standards
- Client Deliverables: Data-driven, action-oriented, concise
- Proposals: Custom (never generic), include ROI projections
- Documentation: Always include "Why" + "How" + "What's Next"
Automation Goals
- Automate routine operations via Claude Code (content drafts, research, admin)
- Human focuses on: Strategy, client relationships, high-value work
- Agent system validates patterns through daily use
Guardrails
- Never share client-specific data publicly (anonymize case studies)
- Always validate data before presenting to clients
- Escalate to human: New contracts, major decisions, custom pricing
- Brand consistency: Every output should sound like you wrote it
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.mdfor complete agent/skill documentation
How This Repository Works
- Skills auto-activate based on description triggers (see
.claude/skills/) - Agents handle complex tasks via isolated workflows (see
.claude/agents/) - Client projects get their own CLAUDE.md with specific context
- Dev Docs (plan.md, context.md, tasks.md) track multi-week projects
- Everything compounds - every project makes the system smarter
Available Capabilities
Skills (Auto-Invoked Guidelines)
Located in .claude/skills/ - auto-activate based on request:
- support - Client issue triage, bug resolution, response templates
- finance - Invoice generation, pricing calculator, expense tracking
- marketing - Growth tactics, DM templates, engagement metrics
Agents (Complex Multi-Step Tasks)
Located in .claude/agents/ - invoke for isolated work:
- sales - Lead qualification → research → proposal generation
- strategy - Discovery synthesis → AI opportunities → roadmaps
- build - Architecture → implementation → testing → deployment
- content - Multi-post content generation
When you start work:
- Tell me which client/project
- I'll load relevant CLAUDE.md + skills
- I remember previous decisions
- I suggest next actions
Ready to work.
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.

