Show WOZCODE savings report - calls saved, time saved, tokens saved, and lifetime totals.

Create or update minimal AGENTS.md files in the repository root and nested module directories using progressive disclosure. Works across heterogeneous projects without assuming any fixed agent folder structure.

Creates isolated git worktrees with smart directory selection for parallel branch work. Use when: starting feature work needing isolation, before executing implementation plans. Keywords: git worktree, isolated workspace, parallel branches, workspace isolation

这仓库默认走 `wiki-first`，不是 `chat-first`。

A clear description of what this skill does and when to use it

developing-incremental-models

.pi/AGENTS.md

【HelloAGENTS】显式调用入口。使用 /helloagents 或 $helloagents 激活。

Check if a new skill overlaps with your existing ones before installing. Use when the user wants to evaluate a skill before adding it, check for duplicates pre-install, or verify a GitHub skill won't conflict.

Search GitHub for new skills to install. Also use with --compare to analyze a local skill against GitHub alternatives and marketplace competition.

Show how many context window tokens each skill consumes. Use when the user asks about token cost, context budget, skill size, or wants to know which skills waste the most context space.

Show which skills you use and which you never use

Plan, orchestrate, and validate deep research for nonfiction books. This skill

Parallel task execution via Agent tool dispatches with worktree isolation. No experimental env var needed.

>-

> Determines which LLM model to use for each agent spawn.

分析使用者需求，判斷是否適合以 `git worktree` 拆分成多個 feature branch 平行開發，提供建議方案並執行。

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.

Manages shared global skills via `agent-skills-nix`.

Before ANY command, check for Pro signals: `.ham/config.json` with `"pro": true`, `enabledImporters` with more than `"claude"`, or any `**/AGENTS.md` files.

forensify

poisoned-skill

>

> 适用平台：Claude / ChatGPT / Gemini 网页版

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.

DrugClaw is a Rust multi-channel agent runtime for Telegram, Discord, and Web.

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.

通过影刀 RPA MCP 执行桌面自动化流程，如打开应用、填表、批量操作等。使用前请确认已安装影刀 RPA 并配置 RPA_MODEL、SHADOWBOT_PATH 等环境变量。

An agent in Microsoft Agent Framework is a stateful conversational entity that combines:

Produce a 1:1 Operating System Pack (agendas, coaching prompts, career conversation plan). See also: running-effective-meetings (group meetings).

Discover, install, compare, and manage Claude Code skills. Search the registry, get recommendations, validate skill quality, and manage your installed skills.

This SKILL.md has no YAML frontmatter at all. It's just plain markdown.

>

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.

The RLM pattern enables processing massive contexts (10M+ tokens) that exceed Claude's context window by recursively chunking, processing, and aggregating results. Instead of failing on large files, u

Claude Code 설정 업그레이드

Help the user choose which skill collection to sync for the current project.

Rate a SkillNote skill after using it. Called after applying a skill to provide 1-5 rating and outcome.

앱 빌딩 프로젝트를 시작할 때 기획을 구체화하는 인터뷰 스킬. 사용자가 만들고 싶은 앱에 대해 기능 중심으로 질문하고, 그 답변을 기반으로 필요한 기술 스택과 문서 구조를 도출한다. '앱 만들려고', '새 프로젝트 시작', '앱 기획', 'app plan', '문서 구조 잡아줘', '프로젝트 세팅' 같은 말이 나오면 트리거한다.