AI & ML

runkids-my-skills Bundle

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

hacklyc Bundle

把用户的可复用需求封装成标准化的 Agent-CLI 工具，并用 `myagents tool add` 注册进 MyAgents 工具注册表——注册后所有未来会话（builtin / Claude Code / Codex / Gemini 全 runtime）的 AI 都会在 system prompt 里自动发现它。触发场景：(1) 用户说「把 XX 封装成工具」「做成一个工具」「注册个工具」「写个 CLI」「以后能直接用」；(2) 用户描述一个会反复出现的自动化需求——文档/文件批量处理、调用某个云 API、用某个多模态大模型做图像/视频理解等，即使没说"工具"两个字；(3) 你发现自己第二次为同类需求写几乎一样的脚本——这时要主动提议把它升格为注册工具，不要等用户开口。反向边界：一次性任务就地解决、不铸工具；接入现成的 MCP server 用 `myagents mcp`，不归这里。

hacklyc Skill

Methodology for writing or improving prompts and system prompts that drive any LLM. Use when authoring or revising a prompt for a model task — grouping, classification, extraction, generation, copywriting, labeling, agent instructions, prompt templates, skill instructions — to decide how much to constrain the model based on the task type (open-ended vs single-correct-answer) and write the most fitting instructions. Triggers: "write a prompt", "help me write or improve a prompt", "how should I change this prompt", "this prompt isn't working", "write instructions for the model", "prompt-writer". Not for: answering the user's question directly, or writing articles and documents meant for human readers (those are not prompts that drive a model).

devstefancho-claude-plugins Bundle

Maintains an LLM-powered personal wiki (capture → raw → wiki → schema) that self-organizes from memos, AI conversations, and research. Use when user mentions wiki init, wiki capture, wiki ingest, wiki distill, wiki query, wiki lint, wiki update, 위키 초기화, 위키에 적어줘/메모, 이 대화 위키에 정리, 위키 추가, 위키 정리, 위키 질문, 위키 검사, 위키 업데이트, or wants to build/maintain a knowledge base.

devstefancho-claude-plugins Bundle

Projects one local policy file onto Claude Code, Grok, and Cursor Agent — deny rules, guideline files, and an optional read-deny hook. Use when the user says 에이전트 권한 맞춰, 권한 동기화, grok이랑 cursor 권한, 같은 보안 설정, deny 규칙 맞춰줘, agent policy sync, sync permissions across agents, 에이전트 설정 통일.

hacklyc Bundle

让 Agent 建立 MyAgents Task 的完整产品心智模型，并创建、验证和治理需要持久追踪、独立 Session 或未来触发的工作：理解 Task 与立即执行/Record/Goal 的边界，以及 once/scheduled/recurring、Session routing、结束条件和 command Detector。用户提到创建 Task、定时、稍后、周期检查、持续关注、满足条件才处理时使用；普通立即执行、仅保存 Record 或明确要求 Goal Mode 的工作不使用。

hacklyc Bundle

MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Space 等功能异常，或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。 先用 `/myagents-docs` 确认正确产品预期，再以本地状态、CLI、日志和必要 probe 分类、修复、验证；确认产品缺陷或功能建议后， 在用户确认下形成并提交脱敏 Issue。普通“是什么/怎么用/入口在哪”不使用本 skill，直接使用 `/myagents-docs`。

hacklyc Skill

内置小助理在当前设备上安装、补齐、升级或修复独立本地工具、CLI 与运行环境时使用。用户直接要求“帮我安装某个工具”、 收到 Space 自定义工具的安装请求，或启用 MCP 时发现缺少本地命令，都应使用本 Skill。负责核对来源、选择适合当前系统的安装方式、 避免污染用户项目、控制高权限与敏感信息风险，并在完成后实际验证。MCP 配置导入、MyAgents Skill/Plugin 安装、项目依赖管理和 Agent-CLI 工具注册不使用本 Skill。

chachamaru127 Skill

Read-only delegate to cursor-agent (Composer) for questions, investigation, design discussion, and adversarial sanity checks. No worktree, no cherry-pick, no Lead diff review — cursor-agent is locked to ask mode and cannot write. Use when user says: ask cursor, cursor sanity check, get a second opinion, adversarial review, design discussion, investigate with cursor, cursor:ask. Do NOT load for: implementation, refactor, file edits, commit/push work, anything requiring write access (use cursor:do or breezing --cursor instead).

chachamaru127 Skill

Configure and verify the Cursor backend for Claude Code Harness. Use when user invokes cursor:setup, wants Cursor as the local default implementation backend, or asks to check Cursor plugin/agent readiness. Distribution default remains opt-in; only local env/user settings are changed when explicitly requested.

chachamaru127 Bundle

Long-running task loop using /loop (Claude Code dynamic mode) and ScheduleWakeup to re-enter with fresh context on each wake-up. Internally invokes harness-work through Agent. Trigger: long-running, loop, wake-up, autonomous. Do NOT load for: one-shot task execution, review, release, planning.

devstefancho-claude-plugins Bundle

Locates a previous Claude Code or Codex CLI session's JSONL transcript and prints metadata (title, first/last prompt, branch) plus the last N conversation turns so work can continue. Use when the user says "resume", "이어가자", "이전 세션 내용 보여줘", "what was I working on", or provides a session UUID.

chachamaru127 Skill

This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.

chachamaru127 Bundle

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

chachamaru127 Bundle

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.

chachamaru127 Skill

Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~/.claude/writing-lint/proposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts/writing-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts/writing-rule-approve.sh), listing pending proposals (use scripts/writing-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine / PostToolUse hook does that).

januarylabs Bundle

Keep repository documentation accurate and agent-legible through drift detection and deterministic fixes. Use when asked to scan docs for stale content, broken links, metadata/nav drift, API coverage gaps, or to run recurring documentation gardening in on-demand or scheduled maintenance loops.

januarylabs Bundle

Test code built on AI SDK v7 using its real `ai/test` utilities and V4 provider protocol. Use when writing, fixing, reviewing, or migrating tests around AI SDK agents, generation, streaming, structured output, tools, provider registries, model modalities, or simulated streams. Trigger for requests to test an agent, mock a model, fake a stream, simulate a tool call, test retry logic, inspect prompts, or debug hanging streams and empty output. Remove V3 fixtures and custom helpers that duplicate public AI SDK APIs.

scalekit-inc Skill

Guides users through adding OAuth 2.1 authorization to Model Context Protocol (MCP) servers using Scalekit. Use when setting up MCP servers, implementing authentication for AI hosts like Claude Desktop, Cursor, or VS Code, or when users mention MCP security, OAuth, or Scalekit integration.

scalekit-inc Skill

Integrates Scalekit Agent Auth into a project to handle OAuth flows, token storage, and automatic refresh for third-party services (Gmail, Slack, Notion, Calendar). Use when a user needs to connect to an external service, authorize OAuth access, fetch access or refresh tokens, or execute API calls on behalf of a user.

scalekit-inc Skill

Add OAuth 2.1 authorization to FastMCP servers using Scalekit provider plugin. Use when building FastMCP servers, when users mention FastMCP authentication, Python MCP servers with Scalekit, or need rapid OAuth integration with minimal code.

scalekit-inc Skill

Guides developers through creating a Scalekit MCP server with authenticated tool access. Use when building an MCP server, exposing Scalekit tools over MCP, or connecting AI agents via LangChain/LangGraph MCP adapters.

scalekit-inc Skill

Walks through a structured production readiness checklist for Scalekit MCP authentication implementations. Use when the user says they are going live, launching to production, doing a pre-launch review, or wants to verify their MCP server authentication is production-ready.

microsoft-foundry-foundry-samples Bundle

Fetch the user's financial profile (risk tolerance, investable cash, horizon, goals, current holdings, constraints) from the profile API while keeping the API credential secret. Use when an investment or planning agent needs the user's financial profile before producing analysis or a plan. Composes a Key Vault read (agent identity) with a profile-API call so the credential never enters the model context. Returns only the profile JSON.

microsoft-foundry-foundry-samples Skill

Contoso Outdoors customer-support tone and formatting guidelines.

microsoft-foundry-foundry-samples Skill

When and how to escalate Contoso Outdoors customer-support tickets.

wulnut Bundle

现代 C++ (C++17/20) 编码规则和最佳实践，包括 STL、智能指针、RAII 和性能优化

wulnut Skill

RIPER-5 严格模式协议，包含研究、创新、规划、执行、审查五个阶段的代码开发工作流

wulnut Bundle

Git 提交规范和分支 management 最佳实践，包括 Conventional Commits 格式和分支命名约定

microsoft-foundry-foundry-samples Bundle

Estimate whether a stock looks cheap or expensive using a price-to-earnings (P/E) based fair-value method. Use when the user asks if a stock is over- or under-valued, or for a fair-value / target price.

microsoft-foundry-foundry-samples Bundle

Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.

microsoft-foundry-foundry-samples Bundle

Creates colorful PDF travel guides for cities, including itinerary ideas, neighborhoods, food, practical tips, and photo-worthy stops. Use when the user asks for a travel guide, city guide, itinerary, trip plan, or PDF document for a destination.

nvidia Skill

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, provider profile, provider refresh, policy set, policy get, settings, service expose, forward, port forward, BYOC, bring your own container, inference, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.

nvidia Skill

Debug why inference.local, direct external inference, or supervisor-only system inference is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees inference verification failures, hits protocol mismatches, or needs to diagnose inference on local vs remote gateways. Trigger keywords - debug inference, inference.local, system inference, sandbox-system, local inference, ollama, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, failed to verify inference endpoint, host.openshell.internal.

nvidia Skill

Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow labels. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.

jeudy100 Skill

Analyze an agent or skill definition by name and suggest improvements for clarity, structure, and error handling.