Most Popular
3,528 documents
Remotion Skill — Onboarding Guide
Teaches Claude to build MP4 videos with Remotion using local tools, no API keys, covering narrated, TikTok, music, and captioned video paths.
Contentful Architecture Overview
Documents a microservices-based video generation pipeline that transforms text topics into rendered videos through six AI-powered stages.
SageMaker LLM Training Operator (SOP)
Guides users through a 15-step wizard to produce executable SageMaker training launchers for LLM fine-tuning, using official AWS recipes when available.
CTO Personal Website - Comprehensive Content Strategy
This content strategy document outlines a comprehensive approach to positioning a Chief Technology Officer (CTO) as a thought leader in the technology industry through strategic content creation, professional messaging, and industry expertise showcase.
Editorial & Technical Plan: Agentii AI - Financial AI Authority Blog
Operationalises a content strategy for a financial AI blog with editorial workflows, technical stack, SEO tactics, and measurement plans.
Chapter 06 -- Design Intent Preservation: The Anti-Slop System
Presents a five-layer defense system to prevent generic AI-generated frontend code by enforcing brand-specific design tokens, antipatterns, and checklists.
Tool Use Reference
Explains the tool-use pattern where Claude requests function calls and you execute them, covering schemas, loops, parallel execution, and built-in tools.
1. System Architecture
Blueprints a RAG-based SaaS for generating quizzes and summaries from uploaded documents using a decoupled Next.js, FastAPI, and Supabase stack.
Research Synthesis: MCP Server Architect Agent
Synthesises research on MCP protocol, server architecture, tool design, security, and language-specific implementations for building MCP servers.
Step 3: Blog Operations & Growth Planning
Defines a blog operations plan covering writing workflow, content pillars, distribution strategy, sprint framework, measurement dashboard, and team roles for AI SaaS products.
LLM Integration Guide
Explains how to configure and integrate multiple LLM providers into a SaaS testing project for requirement parsing, test generation, and result analysis.
Media/Marketing Kit Framework - Comprehensive Plan
Plans a multi-agent framework for producing media kits, marketing decks, and campaign materials with structured workflows and quality gates.
Completed Work Archive
Tracks completed implementation work streams for a financial assessment application, moving them out of the active roadmap to keep it focused.
Raleigh Outreach Finder + Tracker - Complete User Guide
Documents a CLI tool for discovering Raleigh-area companies, ranking them, generating LinkedIn message drafts, and tracking outreach without automation.
EVAL-001: Evaluation Contract — Flash Evaluations (FEATURE-053)
Locks scoring definitions, ground truth strategy, thresholds, and failure taxonomies for Flash Evaluations before any code is written.
Building SupportX AI Assist: A Multi-Agent IT Support System
Describes building a multi-agent IT support system with AutoGen, Azure AI Search, and Gemini embeddings for instant issue resolution and automatic escalation.
Flourish App - Video Production Checklist
Guides a developer through pre-production, recording, editing, and publishing a product demo video for the Flourish app.
Phase 3: AI-Powered Code Review
Documents a deployed AI code review assistant that automatically reviews pull requests for code quality, bugs, security, and performance.
Model and Prompt Evals for a Clinical Charting App Using LLMs in Production
Runs 10 iterations of 8 OpenAI and Anthropic models against a single transcript to compare cost, speed, and output quality for structured SOAP note generation.
Benchmark Results — planning-with-files v2.22.0
Documents a formal evaluation of the planning-with-files skill using Anthropic's skill-creator framework, including methodology, test cases, grading criteria, and results.
RWE Inclusion/Exclusion Optimizer
Defines a multi-agent system that converts clinical trial inclusion/exclusion criteria text into executable SQL cohort queries over real-world data.
SPEC: HackTheBench Agent Support
Specifies how AI agents compete in a CTF benchmark via SSH and an MCP server, with verified badges on the leaderboard.
Common Standards Issues
Catalogues 20 common working group problems with symptoms, results, and 10 success factors to avoid or resolve them.
US-04: YouTube Video Transcription Implementation
Specifies a YouTube-to-text transcription feature with async job creation, progress polling, error handling, and a three-layer timeout strategy.