Chris Lawrence
Community@Lawrence908
Chris Lawrence maintains 20 skills spanning multi-agent orchestration, full-stack development, adversarial QA, self-hosted infrastructure, and technical writing for homelab and production projects.
Agent Skills by Chris Lawrence
Showing 20 vetted skills indexed across 1 GitHub repositories.
prompt-design
Generate consolidated prompts that orchestrate multiple skills into ordered execution plans.
advisory-board
Orchestrate isolated multi-agent deliberation and adjudication for high-stakes decisions.
deep-research
Orchestrate parallel research agents and write a cited report to disk.
prompt-engineering
Designs structured LLM prompts with constraints, examples, and output formats for specific tasks.
agent-orchestration
Design multi-step agent workflows combining skills, tools, and context sources.
mcp-integration
Design and integrate Model Context Protocol servers and tools with LLM clients.
ui-design
Design and build production-grade frontend interfaces from context gathering through visual direction, implementation, and polish.
python-refactor
Refactor Python modules and services into modular, testable structures without changing behavior.
full-systems-audit
Audit a codebase end to end and produce a routed findings backlog with stable IDs.
frontend-nextjs
Develop and debug Next.js applications with React, TypeScript, and App Router patterns.
visual-qa-dogfood
Verifies UI changes with screenshot evidence and an absurdity ledger of visual defects.
dragon-hunt
Runs adversarial end-to-end bug hunts across auth, data, API, and deployment surfaces.
fastapi-development
Design and implement FastAPI applications with Pydantic validation, dependency injection, and async SQLAlchemy.
docker-compose-editing
Create, modify, and diagnose docker-compose.yml files for self-hosted service stacks.
api-debugging
Diagnose API errors including authentication failures, routing problems, and integration issues.
technical-documentation
Create structured technical documentation including READMEs, API references, guides, and runbooks.
word-docs
Convert markdown drafts into styled Word documents using pypandoc and python-docx.
academic-essay
Write, edit, and proofread thesis-driven academic essays with MLA and APA formatting.
spec-from-conversation
Extract structured specifications and implementation plans from conversation transcripts.
seo-titles
Write HTML title tags and meta descriptions optimized for search ranking and click-through.
Frequently Asked Questions About Chris Lawrence
FAQPage SchemaWhat tasks can I accomplish with Chris Lawrence's skill registry?▼
You can orchestrate multi-agent research runs, design prompts, integrate MCP servers with Linear and GitHub, build Next.js and FastAPI applications, refactor Python modules, audit codebases, edit docker-compose stacks, debug OAuth and webhook failures, and produce Word documents, academic essays, and SEO title tags.
Who is the target audience for these skills?▼
Self-hosting developers and solo engineers running homelab infrastructure with Proxmox and Docker, plus builders shipping Next.js and FastAPI applications who need adversarial QA, codebase audits, and screenshot-backed visual verification before declaring work complete.
How do the multi-agent and orchestration skills work in practice?▼
The advisory-board skill runs conflicting agents in isolation, then an adjudicator resolves them into a ranked recommendation persisted for re-testing. Deep-research coordinates parallel investigation across web, docs, papers, and code, writing a referenced report to disk suitable for unattended overnight execution.
What prerequisites or dependencies do these skills require?▼
Word document conversion requires pypandoc and python-docx with optional mermaid pre-rendering. MCP integration requires configuring clients like Claude Desktop or Cursor and OAuth setup for Linear or GitHub. Docker-compose editing assumes an existing self-hosted service stack with volumes, networks, and environment files.
How do the QA and auditing skills prevent shipping defects?▼
Visual-qa-dogfood forces screenshot-backed verification of any user-visible change and logs an absurdity ledger of defects. Dragon-hunt runs adversarial end-to-end testing across auth, data, and deployment surfaces, while full-systems-audit maps architecture and tech debt into a routed backlog with stable IDs.