开发技能

Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL

中文简介正在准备中。当前显示原文说明。

Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.

中文简介正在准备中。当前显示原文说明。

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

中文简介正在准备中。当前显示原文说明。

Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.

中文简介正在准备中。当前显示原文说明。

Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning.

中文简介正在准备中。当前显示原文说明。

Prepare compact factual project context for another session or coding tool without copying transcripts or secrets.

中文简介正在准备中。当前显示原文说明。

Refine an already working product frontend in a dedicated finishing pass, preserving its identity while improving hierarchy, components, copy and responsive behavior. Use after the core flow works or when the user asks for frontend polish; not for product ideation or a new visual direction.

中文简介正在准备中。当前显示原文说明。

Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "help me look at this project", "learn about XXX", "what is this project like", "analyze this repo", or any request to explore/evaluate a GitHub project. Covers architecture, community health, competitive landscape, and cross-platform knowledge sources.

中文简介正在准备中。当前显示原文说明。

Install or update the M365 Agents Toolkit (ATK) CLI and VS Code extension. Triggers: "install atk", "update atk", "install agents toolkit", "update agents toolkit", "install the toolkit", "setup atk", "get atk", "install atk cli", "install atk extension", "install atk vsix", "update the vs code extension", "install latest atk", "upgrade atk"

中文简介正在准备中。当前显示原文说明。

Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).

中文简介正在准备中。当前显示原文说明。

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

中文简介正在准备中。当前显示原文说明。

Create React Flow node components with TypeScript types, handles, and Zustand integration. Use when building custom nodes for React Flow canvas, creating visual workflow editors, or implementing node-based UI components.

中文简介正在准备中。当前显示原文说明。

Microsoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication routing, Express hosting, streaming responses, and Copilot Studio client integration. Triggers: "Microsoft 365 Agents SDK", "@microsoft/agents-hosting", "AgentApplication", "startServer", "streamingResponse", "Copilot Studio client", "@microsoft/agents-copilotstudio-client".

中文简介正在准备中。当前显示原文说明。

Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.

中文简介正在准备中。当前显示原文说明。

Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, AgentApplication routing, and MSAL-based auth. Triggers: "Microsoft 365 Agents SDK", "Microsoft.Agents", "AddAgentApplicationOptions", "AgentApplication", "AddAgentAspNetAuthentication", "Copilot Studio client", "IAgentHttpAdapter".

中文简介正在准备中。当前显示原文说明。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).

中文简介正在准备中。当前显示原文说明。

Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.

中文简介正在准备中。当前显示原文说明。

Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, custom agents, skills, and deployment patterns. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).

中文简介正在准备中。当前显示原文说明。

Sysinternals DebugView CLI (DbgViewCli) for capturing and analyzing usermode and kernel-mode Windows debug output from the command line. USE FOR: capturing OutputDebugString output, kernel DbgPrint/KdPrint capture, boot-time debug logging, remote debug monitoring, filtering debug output by PID or process name, crash dump analysis, automated debug capture with bounded execution. DO NOT USE FOR: non-Windows platforms, application-level logging frameworks (log4j, serilog), Azure Monitor or cloud telemetry, ETW tracing (use WPR/xperf instead), user-mode crash dumps (use WinDbg). Triggers: "debug output", "DbgView", "DebugView", "kernel debug", "capture debug logs", "boot logging", "OutputDebugString", "DbgPrint", "KdPrint", "remote debug monitor", "debug capture CLI".

中文简介正在准备中。当前显示原文说明。

SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.

中文简介正在准备中。当前显示原文说明。

SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pocock's grill-with-docs (MIT). NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.

中文简介正在准备中。当前显示原文说明。

Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.

中文简介正在准备中。当前显示原文说明。

Have Codex implement a concrete work order and have Claude independently inspect the final changes. Preserves the explicit Codex builder choice; use claudex-loop for host-based planning and automatic reviewer selection.

中文简介正在准备中。当前显示原文说明。

Harden a plan with independent Claude/Codex review, then optionally build and cross-inspect it. Start in either Claude Code or Codex: the host plans and the other provider reviews. Use for claudex this plan, claudex-loop, or the legacy crucible trigger; not for trivial edits.

中文简介正在准备中。当前显示原文说明。