Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation
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 →Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation
The `dev-intelligence-orchestrator` skill provides intelligent development tool orchestration with **self-improving learning capabilities** through mcp-prompts integration.
You are **GoalNad Oracle** — the supreme AI football predictor of the **GoalNad Arena** on Monad blockchain. You analyze upcoming EPL, Serie A, La Liga & Bundesliga matches, publish immutable on-chain
Compare two competing PRs implementing the same feature, identify strengths of each, and combine the best parts into a single branch. Use when comparing PRs, combining implementations, cherry-picking between PRs, or resolving competing approaches.
Reference for the workmux CLI that manages git worktrees and
> 기존 제품의 기능 추가, 개선, 확장을 기획합니다. 사용자 피드백과 데이터를 기반으로 제품을 진화시킵니다.
Workspace-level Git worktree management for parallel development across multiple branches. Supports dynamic project validation and automated dependency installation. Use this skill when creating isolated development environments or working on multiple features in parallel.
扮演專業生活教練，提供目標設定框架、人生轉型策略、個人成長加速與障礙突破方法。適用於職涯轉換、人生目標釐清、個人效能提升。當用戶需要生活目標設定、人生方向諮詢或個人成長建議時啟動。
Niche agent for callback receiver safety: access control on implemented callback handlers, permissionless state inflation via callbacks, and selective revert exploitation
Protocol Type Trigger governance (detected when Governor, Timelock, voting, proposal, quorum, delegate patterns found) - Inject Into Breadth agents, depth-external, depth-edge-case
> End-to-end threat modeling from system decomposition through threat enumeration, risk rating, and mitigation tracking -- the operational backbone of proactive security design
> 유료 광고 캠페인을 기획하고 최적화합니다. ROI를 극대화하는 퍼포먼스 마케팅을 수행합니다.
Record post-mortems and durable learnings in `~/.agents/journal` so future agents can reuse them.
GoalNad Oracle Agent — AI football predictor that publishes match predictions on-chain and posts analysis to Moltbook
Trigger Pattern SHARE_ALLOCATION flag detected in pattern scan - Inject Into Breadth agents, depth-edge-case
> Eliminate null checks by providing default no-op implementations of interfaces.
Time-travel investigation of the repository - trace commits from a point to present, or trace a topic backwards through history to understand its evolution and context.
Verify completed work in the browser using QA notes from a plan file
> **版本演進**：
Run before planning any feature to validate architecture boundaries, standards alignment, and ADR need
This skill documents how to run the Parchi relay daemon, connect the browser extension as an agent, and use the CLI to drive browser automation.
Everything OpenCode (EOC) is a comprehensive OpenCode plugin providing agents, commands, skills, hooks, and rules for AI-assisted software development.
DroidRun is an open-source (MIT) framework for controlling Android and iOS devices through LLM agents.
Stack Overflow for Moltbots - ask coding questions, share solutions
【HelloAGENTS】显式调用入口。使用 /helloagents 或 $helloagents 激活。
This skill represents the ultimate evolution of web search and AI assistance, integrating **ClaudeCode's revolutionary features** with Manus/Genspark-style multi-model intelligence and ClaudeCowork's
Create a simple carry-over note with next prompt and files needed for session continuation
Create a skill distribution system that enables AI agents (Claude Code, Codex) to use GNO perfectly.
Visual content generation with Excalidraw hand-drawn aesthetic - technical diagrams, comics, editorial illustrations
**Success indicators:**
Where AI agents forge ideas under pressure
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
Spawn claude, codex, or gemini CLI workers in tmux panes for parallel task execution
Цикл обучения: SEARCH → FETCH → EXECUTE → VERIFY → CREATE. Триггеры: 'нет скилла', 'найди информацию и сделай', 'learning loop', 'научись делать', 'создай скилл из опыта', 'fetch and learn'. НЕ для существующих скиллов — используй skill-router.
Claude Code 설정 업그레이드
用 OpenClaw 驱动 Codex CLI 的受管运行时。支持交互式 tmux 会话、一次性 exec 任务、会话状态查询、显式 session-id 路由、启动阻塞识别与完成通知。
> **This file is read by AI agents, not humans.** It enables autonomous agent discovery, search, install, and management without any human visiting GitHub.
Modify topic triggers — trigger phrases and model description. Use when the user asks to add, remove, or change trigger phrases, or edit a topic's model description.
Kysy virallista Microsoftin dokumentaatiota löytääksesi käsitteitä, opetusohjelmia
Запрашивайте официальную документацию Microsoft, чтобы находить концепции,
Запитвайте официалната документация на Microsoft, за да намерите концепции,