Recently Added
3,528 documents
Lesson 11 - Evals (Regression Testing for Agents)
Defines a regression testing system for agents using golden datasets and hard/soft assertions to catch regressions after prompt changes.
AI provider (AI Gateway example)
Shows how to evaluate MCP tool calls using Evalite, Vitest, and the AI SDK MCP client.
❤️ Evaluations and Feedback Loops for LLM Products
Explains how to build evaluation and feedback loops for LLM products, using a question-to-SQL pipeline as a running example.
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.
Gen-AI Evaluation
Synthesizes model and system evaluation best practices from Chip Huyen's AI Engineering book for generative AI applications.
System operators
Guides system operators through health checks, Docker management, multi-instance setup, and dependency vulnerability remediation for a paired-omics data application.
Metamodel Database SOPs
Defines schedules, processes, and conventions for maintaining a metamodel database with Liquibase changelogs and MDF model files.
HCS-25 (Signal Family): SimpleMath / SimpleScience Evals (Informative)
Defines a minimal evaluation methodology for baseline correctness trust signals using arithmetic and multiple-choice science questions.
How to create a standard operating procedure
Walks through building a Lua-based standard operating procedure with checklists, voices, and sound mappings for the X-Plane AudioChecklist plugin.
oba-gwas-sop
Guides adding GWAS requested trait terms to OBA and EFO through pattern matching, term creation, release, and import.
454_sop
Walks through a 454 pyrosequencing 16S rRNA gene sequence processing pipeline using mothur, from raw flow files to chimera-free, classified sequences.
VCR Standard Operating Procedure (SOP)
Defines mandatory visual verification steps and framing rules for VCR shader elements to prevent clipping and off-center renders.
evals
Explains how to save and replay agent conversations to detect behavior changes over time.
Prompt Evaluation Quickstart
Evaluates and compares prompt variations for sentiment classification using a RAGAS quickstart template.
동일 출처 정책 (Same-Origin Policy)
Explains the same-origin policy and lists five workarounds: document.domain, CORS, postMessage, proxy server, and JSONP.
NTU Assistant Skill
Routes user requests to specialised NTU academic systems via Chrome DevTools MCP, handling login, data extraction, and file generation.
lemlist
Guides AI agents through lemlist's MCP and REST APIs for cold outreach, campaign management, and CRM sync.
Wiki Generator
Defines a multi-step workflow for an AI agent to generate a structured project wiki with diagrams, code examples, and cross-links.
at` Language Agent Skill
Teaches an LLM how to write, debug, and understand the `at` programming language with syntax, builtins, and constraints.
ระบบรับรองแหล่งผลิต GAP พืช (Web Application)
Documents the architecture, roles, routes, and components for a Thai GAP plant certification web application built with Vue 3 and Vuetify.
DAUB UI — Component Library
Documents 73 CSS/JS components and 20 theme families from the daub.dev library, plus an MCP server for generating UI specs from natural language.
Incident Report Generator — 資安事件通報報告產生器
Generates Taiwan government-format cybersecurity incident reports as.docx files via a Python script and config JSON.
ClawdSign Integration Skill
Lets an AI agent claim a unique visual signature on ClawdSign, verify its identity, and optionally share it on social media.
SATI
Documents the SATI SDK and CLI for registering Solana agents with on-chain NFT identities, verifiable feedback, and reputation.