Work with hosted Proof documents and Proof SDK-compatible deployments over HTTP. Use when creating, reading, editing, or reviewing shared docs with the agent API or bridge routes.

Execute a skill within the main conversation

Run Clippy with pedantic, nursery, and cargo lints enabled for comprehensive code quality checks.

Review new skills for claude-skills-library standards. Use when adding new skills to verify they meet quality and structure requirements.

Generates automated Jest tests for a source file using ctest-generated .md as reference. Use when the user wants to generate, write, or create tests based on ctest analysis output.

大家好，我是二哥！

Coalescence is a hybrid human/AI scientific peer review platform. Agents search papers, post analysis, vote, and build domain reputation alongside humans and other agents.

Systematic code review methodology for pre-commit quality assurance. Checks for anti-patterns, code smells, naming consistency, and over-engineering.

Realiza una revisión completa de código siguiendo las convenciones y patrones establecidos en el proyecto SportsCards.

PR-Native, Meta-Review–Driven Agent Communication Protocol (v1.1)

A meta-skill for creating, reviewing, editing, and listing Claude Code skills.

Agent-first stock and market analysis skill for A-shares, Hong Kong stocks, and US stocks. Use when an agent needs structured stock analysis, market review, strategy-based analysis, or reusable command-line execution for equity research. Supports unified request/response contracts, Tushare-backed market data, news-search-assisted workflows, and deterministic scripts.

Git/GitHub operations toolkit with configurable domain for search, PR review, and code discovery

Discover code, repositories, and perform PR reviews using GitHub API and CLI

Comprehensive GitHub CLI wrapper. Manage repos, issues, PRs, workflows, releases, gists, and more via the gh CLI.

Configure and manage GitHub MCP server with 1Password token management. Use when working with GitHub repositories, issues, pull requests, and workflows.

GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.

Collect and organize first-hand research materials for technical writing. Use when the user wants to gather official documentation, source code examples, GitHub issues, or original technical resources before writing. Outputs structured research files ready for the writing phase.

successfully downloaded text file (SHA: 6756f0b5d9b808add2f90962079dc381875a53c1)---

Use when the /systems-design mode is active. 9-phase structured design methodology -- problem framing, system classification, constraints, candidate architectures, tradeoff analysis, risk review, refinement, migration planning, and documentation. Governs conversation flow, delegation patterns, and user validation checkpoints.

Use when the /systems-design-review mode is active. 7-step design review methodology -- understand the design, classify the system, evaluate against codebase, adversarial analysis, tradeoff validation, synthesis, and action items. Governs conversation flow, delegation patterns, and user validation checkpoints.

Adversarial review of a system design from 6 critical perspectives -- SRE, security, staff engineer, finance, operator, and developer advocate. Produces a unified risk assessment. Use for INTERACTIVE on-demand reviews during a design conversation (/adversarial-review). For RECIPE-DRIVEN reviews (where prior step context is needed), use the systems-design-critic agent instead.

Multi-agent orchestration for software development. You coordinate teams of AI agents that build, review, and test code.

Web utility to import Statement of Work (SOW) documents into ScopeStack. Users upload Word/PDF files, AI extracts services/subservices, users review/edit mappings, then export JSON for ScopeStack API.

- When capturing the scene (e.g., creating frame previews), hide auxiliary objects such as helpers or editor gizmos so they never appear in captured output.

You are the Coding Agent for this repository.

This file provides guidance for agents working within this repository, which is structured as a "Self-Correcting Coding Agent Team." This team of specialized AI agents collaborates to develop, review,

Full spec: `.opencode/OES.md`

This file is loaded by Cursor to reduce repeated context and to keep future edits consistent.

> **Context:** This is a monorepo built with Bun, Astro, Hono, and Effect TS.

Universal guidelines for AI agents and developers. This file is used verbatim across multiple projects.

- Follow your assigned role strictly — it defines scope and boundaries for your actions.

本文件為本庫的協作與工程化規範（適用於整個專案目錄）。目標：免費優先（Free-first）的 CI / Security / Review / 文件骨架，並避免動到既有業務邏輯。

- `app.py`: Flask web UI for tagging, manual video review, and NFO metadata plan/write/history workflows.

Guidelines for AI agents working on this Astro-based static site.

> [!NOTE]

- Review the root `README.md` first for product context and local run instructions.

这个仓库是中文主导、双语术语的 AI 开发运行协议。

<!-- Parent: ../AGENTS.md -->

This directory covers building autonomous agents, not using agent products.

You are the Dev Agent responsible for implementing code changes in this repository.

> **Note for Claude Code users:** See [`CLAUDE.md`](CLAUDE.md) for development commands, architecture details, and code style requirements.

파일 수 > 3개 / 독립 작업 > 2개 / 리팩토링 범위 > 1 디렉토리 → 병렬 에이전트 사용

**Agents analyze existing code** - use for reviews, audits, and quality checks.

The lead agent (Claude main) should invoke specialized agents when:

<!-- Parent: ../AGENTS.md -->

This skill provides Apple Human Interface Guidelines for macOS. Apply these rules when building, reviewing, or designing Mac apps using SwiftUI or AppKit.

Comprehensive code review knowledge base for React applications (framework-agnostic). Contains rules across security, performance, architecture, and quality categories. Each rule includes detailed exp