Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
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 →Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
Use this skill to help users work with the open Agent Skills ecosystem through the `skills` CLI.
用户收到了一个 GitHub Issue（bug 报告、疑问、feature request），需要 AI 协助分析问题、判断是否要做、起草回复。AI 全程主导推进，用户只在关键节点做判断。
用户有一个模糊的想法或已有的功能模块，想看看它未来能演化成什么样。AI 全程主导引导，从价值本质出发，帮用户看到多种截然不同的终局可能性。
obsidian-helper
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
>-
'Recover from broken agent state including crash recovery, context overflow, merge conflicts, and corrupted worktrees.'
Manage Claude Code sessions with naming, checkpointing, and resume strategies.
>-
Autonomous goal execution — give a goal, get a plan, confirm, execute, report. You steer, Claude drives.
Faithful implementation of the Outline Agent from PaperOrchestra
Faithful implementation of the Section Writing Agent from PaperOrchestra
Start a ralph style looping session
'深度调研的多实例（多 Agent）编排工作流：把一个调研目标拆成可并行子目标，用 Codex CLI（`codex exec`）在默认 `workspace-write` 沙箱内运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付“成品报告文件路径 + 关键结论/建议摘要”。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及“深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研”等场景。'
Create professional, print-ready HTML documents that export to PDF with customizable branding.
Respond terse like smart caveman. All technical substance stay. Only fluff die.
>
>
>
>
>-
Fixation is the default state. When a generator (human or LLM) has been working on a problem, attention concentrates on the current framing and subsequent ideas tend to be local variations on it. This
Classify construction data by type (structured, unstructured, semi-structured). Analyze data sources and recommend appropriate storage/processing methods
Forecast project outcomes using historical data: cost overruns, schedule delays, risk probabilities. Machine learning models for construction prediction.
Predict project completion dates using ML models. Forecast schedule delays based on current progress, historical patterns, and risk factors.
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
>
>
>
>
A clear description of what this skill does and when to use it
developing-incremental-models
Adapts SDD for Codex while preserving Claude Code behavior. Use when working in Codex, setting up Codex compatibility, mapping Claude tools to Codex tools, or explaining how SDD should run outside Claude Code.
Produces time and complexity estimates for features, tasks, or sprints using story points, t-shirt sizing, or day estimates. Use when the user asks for an estimate, wants to size a feature, or mentions estimation or planning poker.
Before ANY command, check for Pro signals: `.ham/config.json` with `"pro": true`, `enabledImporters` with more than `"claude"`, or any `**/AGENTS.md` files.
forensify
Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.
Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.
robius-widget-patterns
Secure-by-default environment variable management for Claude Code sessions.
Voice agents represent the frontier of AI interaction - humans
Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL), Energy-Based Models (EBMs) e código PyTorch completo.
Automate HR operations in Workday -- manage workers, time off requests, absence balances, and employee data through natural language commands.
ALU execution pattern for ephemeral autonomous work. Detects hooked work, enters GUPP autonomous mode, executes the assigned bead, commits and pushes results, then self-terminates. Never coordinates other agents.
Traditional physical education rotates through activities on a weekly or biweekly schedule: basketball this week, volleyball next week, fitness the week after. Daryl Siedentop's Sport Education model
Pull-based work assignment channel implementing GUPP (Get Up and Push Protocol). Manages single-active-work-item hooks per agent with filesystem persistence and atomic state transitions.
Durable asynchronous messaging channel for inter-agent communication. Implements write-once read-many filesystem mail using atomic writes and directory-based mailboxes.
TypeScript best practices and patterns. Use when writing TypeScript, fixing type errors, or working with generics.
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.