tool-design

Design every tool as a contract between a deterministic system and a non-deterministic agent. Unlike human-facing APIs, ...

github

multi-agent-patterns

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. Wh...

github

latent-briefing

Hierarchical multi-agent systems often pay for the same context twice. The orchestrator accumulates a long reasoning tra...

github

hosted-agents

Hosted agents run in remote sandboxed environments rather than on local machines. When designed well, they provide unlim...

github

filesystem-context

Use the filesystem as the primary overflow layer for agent context because context windows are limited while tasks often...

github

evaluation

Evaluate agent systems differently from traditional software because agents make dynamic decisions, are non-deterministi...

github

context-optimization

Context optimization extends the effective capacity of limited context windows through strategic compression, masking, c...

github

context-degradation

Diagnose and fix context failures before they cascade. Context degradation is not binary — it is a continuum that manife...

github

context-compression

When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approa...

github

bdi-mental-states

Transform external RDF context into agent mental states (beliefs, desires, intentions) using formal BDI ontology pattern...

github

memory-systems

Memory provides the persistence layer that allows agents to maintain continuity across sessions and reason over accumula...

github

project-development

This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectur...

github

context-fundamentals

Context is the complete state available to a language model at inference time — system instructions, tool definitions, r...

github

comprehensive-research-agent

This skill addresses common failures in multi-step research tasks: unhandled tool errors, missing validation, opaque rea...

github

interleaved-thinking

Debug and optimize AI agents by analyzing their reasoning traces. This skill uses MiniMax M2.1's interleaved thinking to...

github

digital-brain-skill

A structured personal operating system for managing digital presence, knowledge, relationships, and goals with AI assist...

github

book-sft-pipeline

A complete system for converting books into SFT datasets and training style-transfer models. This skill teaches the pipe...

github

advanced-evaluation

This skill covers production-grade techniques for evaluating LLM outputs using LLMs as judges. It synthesizes research f...

github

smoke-test

This skill guides the Agent through DeerFlow's full end-to-end smoke test workflow, including code updates, deployment (...

github

video-generation

This skill generates high-quality videos using structured prompts and a Python script. The workflow includes creating JS...

github

vercel-deploy-claimable

Deploy any project to Vercel instantly. No authentication required. Packages your project into a tarball (excludes nodem...

github

systematic-literature-review

This skill produces a structured systematic literature review (SLR) across multiple academic papers on a research topic....

github

surprise-me

Deliver an unexpected, delightful experience by dynamically discovering available skills and combining them creatively. ...

github

ppt-generation

This skill generates professional PowerPoint presentations by creating AI-generated images for each slide and composing ...

github