Software Development AI Skills

Use @data-client/react hooks for data fetching, mutations, and rendering - useSuspense, useFetch, useQuery, useCache, useLive, useDLE, useSubscription, useController, DataProvider, AsyncBoundary,…

后端架构模式、API设计、数据库优化以及适用于Node.js、Express和Next.js API路由的服务器端最佳实践。

Click page elements by CSS selector or text content. When you need to click buttons, links, or select options. PREREQUISITE - must use browser_navigate to open target page first.

Safely inspect, edit, validate, hot reload, and recover the OmniFlow Python runtime inside OpenOmniBot. Use when changing the VLM planner, prompts, GUI execution policy, replay, retry, checker,…

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

Contributes to and debugs Node.js core, including nodejs/node commit and PR tone, contribution workflows, native crashes, V8 performance, node-gyp builds, N-API bindings, and libuv issues. Use when…

Use when adding, debugging, or validating a bring-your-own VLM in VSS RT-VLM, including custom Hugging Face or NGC checkpoints, vLLM adapters or plugins, model shims, and model-specific runtime…

小红书内容发布技能。支持图文发布、视频发布、长文发布、定时发布、标签、可见性设置。 当用户要求发布内容到小红书、上传图文、上传视频、发长文时触发。

For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what…

Install or upgrade the standalone OpenGUI Codex or WorkBuddy plugin on macOS from verified prebuilt GitHub releases. Use for plugin installation, not phone actions or DSH installation.

Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.

CTF Web 挑战专用侦察方法。当面对 CTF 靶场目标需要快速发现攻击入口时使用。与真实渗透的 recon 不同——CTF 是单个应用、有意留线索、侦察应在 2-3 轮内完成。覆盖源码泄露、备份文件、隐藏路径、页面线索提取

Establish a finding before you publish it, and correct it after — headlines that overstate what actually reproduces at the layer a user sees, reporting code that no entry point can reach or that is…

Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS

Iterative Five Whys root cause analysis drilling from symptoms to fundamentals

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Futu OpenD 安装助手。自动下载安装Futu OpenD 并升级 Python SDK。支持 Windows、MacOS、Linux。用户提到安装、下载、启动、运行、配置 OpenD、开发环境、升级 SDK、futu-api 时自动使用。

Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via get_context.py --mode phase. Use when coming back to…

Run the Lathe worker loop so the web UI's Ask / Verify / Add-a-part buttons drive work directly in this session instead of handing back a command to paste. Use when the user invokes /lathe-work (start…

Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own `modal` CLI + token, and bringing…

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image…

Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a…

Build a new GAIA agent with the SDK end-to-end: scaffold the package, write the Agent subclass, register @tool functions, compose reusable tool mixins, set the model + system prompt, and test it…

Use the "Preview in LiveCodes" GitHub Action to generate preview playground links for pull request code changes. Automates playground creation and PR comments.

Enter brainstorm mode to explore a feature or enhancement idea. Stays in discussion mode only — no planning, no implementation. Use /agtx:sweep when ready to push outcomes to the board.

Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when:…

Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to…

Web performance measurement and debugging toolkit. Use when the user asks about web performance, wants to audit a page, or says "analyze performance", "debug lcp", "check ttfb", "measure core web…

Turn a git log into user-facing release notes grouped by feature and fix. Use when asked for release notes from this git log, a changelog entry from these commits, or to turn commits into release…

Analyse the SUB/WAVE radio station's unified event log (state/logs/events-*.jsonl) and give the operator a diagnostic report on how the station is behaving — Navidrome/ Subsonic API call patterns, the…

Entry point for the Simulation Challenge skill set. Use when the user mentions the challenge, leaderboard, submitting a model, or any of the /api/challenge/* endpoints — this skill picks the right…

Run /document `pr` | `changelog` | `release-note` | `postmortem` (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does…

通过微信向多个联系人群发消息。当用户提到微信群发、批量发微信、群发助手时使用。

Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3…

审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工

When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.

Report the compatibility redirect to `ap-run-coordinator`; this retired role cannot perform new work.

Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not…

Start a new task in an isolated Git worktree branched from origin/main so multiple agents can work on the same repo in parallel without conflicts. Use at the beginning of every new feature, fix, or…

抓取 GitHub 上 star 涨得最快的项目（Trending 榜），打分标注是否与研究方向相关， 生成 Obsidian 笔记到 GitHubTrending 文件夹。默认周榜。 触发词："GitHub 周榜"、"star 涨得最快"、"过去一周 GitHub 热门"、"GitHub trending"、 "看看这周 GitHub 上火了什么"、"GitHub 日榜"、"GitHub 月榜"

Run lint+format+type-check+test in parallel (pre-commit quality gate)

Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has an approved optimization plan from xcode-build-orchestrator,…

Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X',…

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding…

AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。 学习者想构建、保护、调试、验证或运行 MCP clients、servers、transports、gateways、 registries 或 conformance gates 时，开始或续学此路线。每次调用教学一课，并将 wire…

深度研究技能，用于系统性调研与分析。适用于研究、调研、竞品分析、市场分析或结构化信息收集等需求。

Use this skill when exploring, analyzing, or understanding project/code structure. Required for tasks like "analyze project", "explore codebase", "understand how X works".

Navigate the Formisch monorepo structure. Use when finding code locations, understanding architecture, locating source files, or implementing features across packages and frameworks.

Use when bringing 3D assets into Roblox Studio or preparing avatar items: import from Blender, GLB, FBX or OBJ files, AI-generated or image-to-3D meshes (Scenario or other tools), wrong scale or size…

This skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs to "check a plan before committing", wants another view after repeated failures, or…

Use when the user mentions flaky tests, tests that pass locally but fail in CI, race conditions in tests, or needs to diagnose WHY a specific test fails.