Agent 工作流

release-beta

16Kagent-workflows

Cut a beta release of Paseo. Use when the user says "release beta", "cut a beta", "ship a beta", "beta release", or "/release-beta".

release-stable

16Kagent-workflows

Cut a stable release of Paseo (fresh patch or minor, or promote from beta). Use when the user says "release stable", "ship stable", "promote", "release:patch", "release:minor", "release:promote", or "/release-stable".

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt this vault, Obsidian vault, second brain setup, persistent wiki.

wiki-ingest

Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this URL, process this source, read and file this source, batch ingest, ingest these sources.

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an `.stl`, `.obj`, `.ply`, or `.3mf` mesh, wants a build-orientation recommendation, or wants DfAM redesign guidance before slicing with `$gcode` or regenerating geometry with `$cad`.

earthtojake

orchestration

使用Orca编排进行结构化多智能体协调：线程化消息、阻塞式询问/回复流程、任务分发、worker_done/升级等待、任务DAG、决策门、协调器循环，或将工作分解到多个智能体。当用户要求完全所有权交接时，包括“hand off”、“handoff”、“handover”、“give this to another agent”或“another worktree”等表述，且用户未明确要求监督、监控、等待结果或协调DAG时，应改用`orca-cli`。对于普通终端控制、轻量级终端提示、shell命令、Orca工作树管理、读取或等待终端，以及Orca内嵌浏览器的自动化，请使用`orca-cli`。对于浏览器窗口、Web视图、Orca应用UI或Orca内嵌浏览器之外的桌面UI，请使用Computer Use。

stablyai

orca-cli

使用公开的 `orca` CLI 操作 Orca 管理工作树、文件夹上下文、终端、仓库、自动化、工作树注释以及 Orca 应用内嵌的浏览器。当用户提到 "$orca-cli"、"use orca cli"、"Orca worktree"、"child worktree"、"cardStatus"、"spawn codex/claude in a worktree"、"read/wait/send Orca terminal"、"terminal send"、"full handoff"、"handover"、"give this to another agent"、"another worktree"、"Orca browser" 或 "control the browser inside Orca" 时使用。当任务涉及 Orca 管理的状态时，优先使用此工具而非原生的 `git worktree`、临时 PTY、Playwright 或 Computer Use。对于 Orca 内嵌浏览器之外的浏览器窗口、WebView 或桌面 UI，请使用 Computer Use。

stablyai

paseo-advisor

14Kagent-workflows

Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself.

react-doctor

14Kagent-workflows

在完成功能、修复错误、提交 React 代码之前，或当用户输入 `/doctor`、要求扫描、分类或清理 React 诊断时使用。涵盖 lint、可访问性、包体积、架构。包括回归检查以及获取规范手册的完整本地分类工作流。

millionco

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

nanogpt

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

seo-ecommerce

电商SEO分析：Google Shopping可见性、亚马逊市场情报、产品Schema验证、竞争对手定价分析及市场关键词缺口。结合页面产品SEO与DataForSEO Merchant API的市场数据。当用户提及“电商SEO”、“产品SEO”、“Google Shopping”、“市场SEO”、“产品Schema”、“亚马逊SEO”、“产品列表”、“购物广告”或“商家SEO”时使用。

seo-google

Google SEO API：Search Console（搜索分析、网址检查、站点地图）、PageSpeed Insights v5、CrUX 现场数据（含25周历史）、Indexing API v3 和 GA4 自然流量。提供真实的 Google 现场数据，涵盖核心网页指标、索引状态、搜索表现和自然流量趋势。当用户提到“搜索控制台”、“GSC”、“PageSpeed”、“CrUX”、“现场数据”、“索引 API”、“GA4 自然流量”、“网址检查”或“真实 CWV 数据”时使用。

paseo-loop

运行 Agent 循环，直到满足退出条件。当用户表达“循环”、“盯盘/盯住”、“持续尝试直到”、“每隔 X 检查一次”、“监视/观察”或需要迭代式自主执行时使用。

paseo-committee

组建由两个高推理能力 Agent 组成的评估委员会，抽离当前局限，进行根因分析并制定可行方案。适用于卡壳、陷入死循环、视野狭窄（隧道视觉）或面临复杂规划难题时。

paseo-handoff

带着完整的上下文将当前任务移交给另一个 agent。当用户输入“handoff”、“hand off”、“hand this to”或希望将工作交接给另一个 agent 时使用。

paseo

用于管理工作区、工作区脚本、Agent、定时任务（Schedule）和心跳检测（Heartbeat）的 Paseo 参考指南。

ian-xiaohei-illustrations

生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务；默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。

helloianneo

huggingface-local-models

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

huggingface

huggingface-best

Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.

huggingface

huggingface-datasets

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

huggingface