智能体
Agent 规划、多步流程与编排
agent-context-system
AndreaGriffiths11
A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at session start, update the scratchpad at session end, and promote stable patterns over time. Works across Claude Code, Cursor, Copilot, Windsurf. Subagent-ready. No plugins, no infrastructure, no background processes.
chain-system
DeevsDeevs
"Create, list, and load multi-session chain links that capture work context for later continuation. Use when you want to save current progress, resume a project from a prior session, or inspect chain history. Triggers: chain link, chain load, chain list, save context, resume work, continue later, session handoff."
dev-workflows
NickCrew
Use when running builds, executing tests, or improving developer experience workflows - provides structured guidance for build/test execution and DX improvement.
agent
treasure-data
Build LLM agents using tdx agent pull/push with YAML/Markdown config. Covers agent.yml structure, tools (knowledge_base, agent, web_search, image_gen), @ref syntax, and knowledge bases. Use for TD AI agent development workflow.
digdag
treasure-data
Treasure Workflow (digdag) for TD. Covers .dig syntax, session variables (session_date, session_date_compact), td> operator, _parallel/_retry/_error directives, and tdx wf commands.
agent-prompt
treasure-data
Write effective system prompts for TD AI agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.
field-agent-deployment
treasure-data
Best practices for developing, testing, and deploying production-ready Field Agents including R&D workflows, version control, testing strategies, and release management
agent-test
treasure-data
Run automated tests for LLM agents using tdx agent test. Covers test.yml format with user_input/criteria, single and multi-round tests, evaluation by judge agent, and criteria development workflow.
aps-doc-id-unification
treasure-data
Expert documentation generation for ID unification layers. Documents identity resolution algorithms, merge strategies, match rules, entity graphs, and multi-workflow orchestration. Use when documenting ID unification processes.
field-agent-documentation
treasure-data
Comprehensive template and guidelines for documenting Field Agents including technical specifications, system prompts, tool specifications, user interactions, and standardized documentation structure
backward-heat-1d-schrodingerization
unitarylab
A Schrödingerization-based solver for the 1D backward heat equation, addressing its ill-posed nature by transforming unstable exponential growth into a structured evolution system. Supports classical matrix methods and quantum-inspired Trotter simulation.
eigensolvers
unitarylab
Quantum eigensolver algorithms for operator spectrum estimation, covering exact classical diagonalization with NumPyEigensolver and variational excited-state solving with VQD.
qaoa
unitarylab
Skill for understanding, using, and implementing the Quantum Approximate Optimization Algorithm (QAOA) for Max-Cut problems via the QAOAAlgorithm class.
agents-md-improver
ericmjl
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
vqe
unitarylab
Skill for understanding, using, and implementing the Variational Quantum Eigensolver (VQE) for finding the ground state energy of the 2-qubit Ising Hamiltonian via the VQEAlgorithm class.
advection-schrodingerization
unitarylab
A Schrödingerization-based solver for the 1D advection equation, supporting both direct unitary evolution (under periodic and central difference discretization) and general transformation for non-unitary cases. Enables classical and quantum simulation through Hamiltonian formulation.
superpowers-workflow
anthonylee991
Enforces a disciplined workflow for coding, debugging, refactoring, and automation: brainstorm -> plan -> implement with verification (prefer TDD) -> review -> finish. Use for almost any non-trivial change.
repo-task-proof-loop
DenisSergeevitch
Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASK_ID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's Claude guide file with the workflow, and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
weaviate-cookbooks
weaviate
Use this skill when the user wants to build AI applications with Weaviate. It contains a high-level index of architectural patterns, 'one-shot' blueprints, and best practices for common use cases. Currently, it includes references for building a Query Agent Chatbot, Data Explorer, Multimodal PDF RAG (Document Search), Basic RAG, Advanced RAG, Basic Agent, Agentic RAG, and optional guidance on how to build a frontend for each of them.
aaif-governance-interleave
plurigrid
Bridge layer connecting the Agentic AI Foundation (AAIF) governance structure — Linux Foundation stewardship of MCP, goose, AGENTS.md — to the plurigrid/asi skill graph. Formalizes AAIF-compatible skill registration, IPSIE identity profiles, and the cross-protocol interoperability surface. Maps the AAIF platinum member ecosystem (AWS, Anthropic, Block, Bloomberg, Cloudflare, Google, Microsoft, OpenAI) to specific ASI skill integration points.
tdd
helderberto
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants test-first development, or requests TDD workflow.
writing
edwinhu
"This skill should be used when the user asks to 'write a paper', 'start a writing project', 'draft an article', 'write about', 'brainstorm writing topics', 'gather sources for a paper', 'what should I write about', or needs the writing workflow entry point for source gathering, topic discovery, and project setup before outlining and drafting."
writing-review
edwinhu
"This skill should be used when the user asks to 'review my writing', 'check document structure', 'find issues in draft', 'review transitions', or needs hierarchical document review that produces REVIEW.md for /writing-revise."
write-a-skill
jasonraimondi
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.