Structured methodology for objectively evaluating, comparing, and selecting AI tools for vendor replacement initiatives, ensuring data-driven decisions.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Structured methodology for objectively evaluating, comparing, and selecting AI tools for vendor replacement initiatives, ensuring data-driven decisions.
[阅读文献入门](https://web.stanford.edu/class/ee384m/Handouts/HowtoReadPaper.pdf)
Read ~/fazm/inbox/skill/AGENT-VOICE.md first — it has your persona, tone rules, examples, and investigation workflow.
Read ~/fazm/inbox/skill/AGENT-VOICE.md first for persona, tone rules, and investigation workflow.
Expertise in negotiating favorable terms with AI vendors, optimizing contracts, managing commercial relationships, and ensuring value alignment throughout the vendor lifecycle.
* 参考：https://www.bilibili.com/video/av20695016
>
Use when researching GitHub repositories, code patterns, issues, discussions, and implementations - provides systematic 6-phase workflow with gh CLI (primary) and web fallback, quality indicators for repository assessment, and structured synthesis with citations
>
Foundational patterns for distributed systems — consensus, consistency models, replication, partitioning, clock synchronization, distributed transactions, and failure modes. Use when designing or evaluating any system that spans multiple nodes, processes, or failure domains.
Domain patterns for peer-to-peer system architecture — network topologies, NAT traversal, peer discovery, data distribution, consistency without central authority, identity and trust, and incentive mechanisms. Use when designing or evaluating a decentralized, peer-to-peer, or mesh-networked system.
An AI agent is a system that uses a language model as its reasoning engine to decide what actions to take, execute those actions, observe the results, and iterate until a task is complete. While a sta
- Do not commit automatically. Only commit when explicitly asked.
This repository contains a hard real-time OS project. Changes must preserve determinism, explicit invariants, and reproducible workflows.
This repository implements the deterministic runtime layer for GitHub-backed agentic development orchestration.
Dados, privacidade e política
Presentational placeholder view for incomplete later onboarding steps.
Instructions for Codex or other agents working in this repo.
**Status**: Approved
AI-powered agents appear on-chain, from trading bots to DAO participants, raising big questions.
>These rules define how the agent should communicate, act, and collaborate with the user during development and automation tasks.The objective is to maintain clarity, reliability, and discipline while
**Type:** Deterministic Agent (Pricing & Quoting)
Gerencie agentes isolados (workspaces + autenticação + roteamento).
**Research Date**: 2026-01-21
- For Python development assume `uv` to be installed. Assume Python versions to be installed and maintained via `uv python install`.
Repository-level operating rules for Codex and collaborators.
To create or edit subagents, use the **agent-kit:claude-agent-development** skill.
- Agents extend `LlmAgent` or `BaseAgent`
I want to develop features in parallel using Git worktrees and subagents: $ARGUMENTS
Local Claude Code agents for DevTrack PM workflow — project-vision (PM), devtrack-engineer, post-generator
Demo the SubagentStop hook by spawning 3 agents and viewing the activity log
Agents support the "small steps, verify often" principle from `.claude/docs/APPROACH.md`.
> Claude Code: read this at the start of every session alongside CLAUDE.md.
**Search Demand:** VERY HIGH (launched yesterday, April 8, 2026)
> Every logical service in EOM is described here: its responsibility boundary,
- Funciones propósito único, preferiblemente <20 líneas
Use small, explicit roles. Do not delegate understanding or product truth.
Этот файл описывает, **как мы используем AI внутри проекта**. Он превращает
Sync agent configuration files to project
> **Purpose**: Define autonomous AI agents with roles, goals, and tools for DataOps workflows
No two agents may edit the same file concurrently. Ownership during a workflow:
**Responsibilities:**
When and how to use parallel subagents when working in k8s-vollminlab-cluster
**Launches multiple parallel agents for grunt work - same task, different inputs.**
**BEFORE doing ANYTHING else in a new session, you MUST:**
Use the installed `qrspi-codex-orchestrator` skill as the default orchestration layer for software-development work in this repository.
Agent/tooling skills and helper documentation for local automation.
Keep local WO lifecycle work aligned to the approved anchor and prevent local execution context from becoming program authority.
Use these agent definitions when the request is large, parallelizable, or needs tighter role separation.
This file serves as the project entry point for general AI agents. Before executing PPT generation tasks, **you MUST first read `skills/ppt-master/SKILL.md`** for the complete workflow and rules.