Intelligence artificielle

RavBogard

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

leolkli

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. USE FOR: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech. DO NOT USE FOR: Function apps/Functions (use azure-functions), databases (azure-kusto), general Azure resources.

nyaomaru

Run Prettier for the is-kit repository. Use when asked to format or check formatting in this project. Always consult AGENTS.md in the repo root before executing commands.

mdrideout

Prepare to work in the Junjo AI Studio repo by reviewing core docs (README, AGENTS, ADRs, testing/db docs, docker-compose/Dockerfiles, GitHub workflows) and then confirming readiness with a brief explanation of the system data flow. Use when starting a new task in this codebase, onboarding, or when asked to “prepare”, “review conventions/architecture”, or “understand how the system works” before making changes.

severeon

NeuroScript standard library catalog. Lists all primitive and composite neurons with signatures, shapes, parameters, and categories. Use when looking up available neurons, checking signatures, or finding which neuron to use.

Toby1009

Validate Marlowe Core JSON drafts for schema correctness, semantic consistency, and supported-subset compliance before lowering to Sui Move. Use when JSON is authored by humans or agents and must be checked for explicit timeouts, party/token references, bounded choices, completeness, and unsupported constructs.

RafaellsAlmeida

storyteller agent

kunhuang12345

Portable tmux-based workflow to drive one or multiple long-running Codex CLI “workers” from another process (e.g. Claude CLI) by (1) starting/reusing a tmux session running `codex`, (2) injecting prompts into the Codex pane via `tmux send-keys`/buffer paste, and (3) polling the worker’s Codex JSONL session logs to extract the next assistant reply. Each worker runs with an isolated `CODEX_HOME` (default `~/.codex-workers/<worker_id>`) to prevent log cross-talk when multiple Codex workers run concurrently. Use when you need to submit/wait/read Codex replies in tmux, manage multiple Codex workers, or troubleshoot the tmux worker and log binding.

BenWeatherall

Guides the ai-context-writer subagent in maintaining AI_CONTEXT_REPOSITORY.md, documenting repository architecture, directory structure, component responsibilities, data flow, and extension points for the python-vis project. Use when creating or updating the repository AI context file.

nicanac

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isnt just storage - its retrieval. A million stored facts mean nothing if you cant find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

alfred1137

Expert guidelines for Python ML and LLM workflows. Covers code quality, experiment tracking, and data handling. Use when working on AI/ML components or data pipelines.

1105564578

用于侵蚀沟初筛与精细测量的AI分析与治理建议。适用于：封装/修改AI分析流程、调整治理判断逻辑、优化提示词、对接SiliconFlow或类似OpenAI风格接口。