Most Popular
3,528 documents
The Low Hanging Fruit of AI Self Improvement
Presents a framework for identifying AI self-improvement opportunities by mapping tasks onto overlapping S-curves, with concrete categories and capability estimates.
Security
Documents a cybersecurity risk assessment for a travel agency and recommends three security controls for the highest-risk asset.
AI Agent Configuration
Defines AI agent skills for code review and enforces pre-push lint, format, and validation checks via mise and git hooks.
MessageAI Rubric
Defines a 100-point grading rubric for a messaging app project with AI features, covering infrastructure, mobile quality, AI implementation, and deliverables.
What If You Could Run 20 AI Agents in One Terminal?
Describes a prototype that runs multiple CLI coding agents in parallel tmux panes, each with its own workspace and task queue.
Payload Analytics Plugin API Documentation
Documents configuration, client-side JavaScript API, REST endpoints, and data structures for a Payload CMS analytics plugin.
Phân tích các thành phần thiếu trong RAG System hiện tại
Audits a RAG codebase and proposes 10 missing components with code sketches to make it production-ready.
Eyedeea Photos Cloud - Demo Video + Marketing Launch Kit
Provides a complete launch kit for a photo cloud product, including a 90-second demo script, ad copy, email sequence, and a two-week calendar.
Remotion Video Production Skill
Defines a complete Remotion video production workflow with project structure, animation rules, schema patterns, and rendering commands.
Windsurf Agentic Chat
Defines the system prompt for Cascade, an agentic AI coding assistant in the Windsurf IDE, with tool usage and communication rules.
AI Implementation Guide: CS01 Case Study
Documents how two AI features, Term Sheet Analyzer and DealCraft Negotiation, are built with Gemini, Supabase, and Vercel serverless functions.
-PLUIE: Personalisable metric with Llm Used for Improved Evaluation
Lists 16 arXiv papers on LLM evaluation, fine-tuning, and interpretability, each with title, authors, link, and abstract.
SYSTEM PROMPT — Adaptive Mixed-Precision Quantization via Learned Dispatch
Defines a complete Python project for input-dependent mixed-precision quantization of LLMs, from profiling to runtime inference.
Zhou Lin
Presents a game developer's résumé covering 20+ years of technical art and engine programming experience.
Creative Brief
Structures a creative brief with fields for objectives, audience, messaging, visual direction, deliverables, timeline, budget, and approvals.
Toasty — AI Triage & Responsible Disclosure Assistant (2026 — 350 hours)
Outlines a 16-week, 350-hour plan to build an AI assistant that triages issues, detects duplicates, extracts repro steps, and flags PII for OWASP BLT.
Projen Pipelines - LLM Context
Documents the projen-pipelines library for LLMs, covering architecture, step types, CDK integration, and deployment options.
CONTEXT
Defines a Node.js Puppeteer scraper that extracts CVE IDs, metadata, and additional resource links from the Wiz vulnerability database into structured JSON.
NOTES
Guides building a public-facing water quality app with map integration, data processing, and stakeholder-specific presentation.
Joonbeom Park
Presents a personal resume with experience, projects, publications, and education for a software engineer and researcher.
evals.md — Structuring Evals in LLM Projects
Guides when and how to add evaluation tests to LLM projects, from vibe-checking to CI-blocking golden datasets.
Command Configuration
Generates production-ready mitigation strategies, implementation code, and defensive measures for LLM vulnerabilities across three defense layers.
Ralph Loop Prompt
Defines a strict session protocol for an AI agent that implements one story per session, enforces feature branches, lock files, testing, and CI verification before marking work complete.
H2SPEC Compliance Status
Tracks 146 h2spec HTTP/2 protocol tests, showing 145 passing and 1 failing with details on the remaining issue.