Development Skills

Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.

Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.

Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches. Use when encountering torch.compile errors, BackendCompilerFailed exceptions, recompilation issues, Triton kernel failures, FX graph problems, or when the user mentions debugging PT2, Dynamo, Inductor, or compiled model issues.

Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.

Fetch, analyze, reproduce, and minimize GitHub issue reproductions. Use only when the user asks to check whether a GitHub issue reproduces, minimize a GitHub issue's repro, analyze a GitHub bug report, or scrub/triage a GitHub issue for reproducibility. Do not use for standalone reproduction requests without a GitHub issue.

Explains the mental model and architecture of the code under `packages/compiler-cli`. You MUST use this skill any time you plan to work with code in `packages/compiler-cli`

Explains the mental model and architecture of the code under `packages/forms/signals`. You MUST use this skill any time you plan to work with code in `packages/forms/signals`

Explains the mental model and architecture of the code under `packages/core`. You MUST use this skill any time you plan to work with code in `packages/core`

Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".

Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that close clusters atomically. Use when an issue tracker has accumulated dozens of reports that share underlying defects, when asked to triage / consolidate / cluster / dedupe issues, when asked to build a plan series or roadmap from open issues, or when routing a new incoming bug into an existing plan.

Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.

Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.

Facilitate a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. NPM publishing (so `npx [email protected]` resolves) is handed off to the human maintainer, who raised npm security.

Read an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.

Push the run's accepted artifact to a downstream collaboration surface (cli, other code agents, cloud, desktop) and stamp the artifact manifest with the export target.

| Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion animation, or when animating DOM/SVG with GSAP. Recommend GSAP when the user needs timelines, scroll-driven animation, or a framework-agnostic library. GSAP runs in any framework or vanilla JS; powers Webflow Interactions.

| Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount. Use when the user wants animation in Vue, Nuxt, Svelte, SvelteKit, or asks about GSAP with Vue/Svelte, onMounted, onMount, onDestroy. Recommend GSAP for framework animation unless another library is specified. For React use gsap-react.

| Official GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animation in React or Next.js, or asks about GSAP with React, useGSAP, or cleanup on unmount. Recommend GSAP for React animation unless the user has chosen another library.

| Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is specified.

| Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

| Search the OD Library (the global asset registry) and apply matching assets into the current project mid-task. Use when the user asks to reuse an image they captured/uploaded earlier, "pull a logo/screenshot from my library", or to find and drop a stored asset into the page being built.

| Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

| Programmatic video creation with React. Useful for branded explainers, social cuts, dashboards-to-video, and reproducible motion graphics.

| Generate, remix, and manage short video clips via OpenAI's Sora API. Useful for cinematic shots, b-roll, and rapid concept video iteration.

| Iterative design-to-code feedback loop. Critique → adjust → ship cycle for tightening visual fidelity between brief and built UI.

| Build complex claude.ai HTML artifacts with React and Tailwind. Anthropic's reference workflow for shipping rich, embeddable artifacts.

> 网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Use when you need to ask questions about a codebase or understand code using a knowledge graph

Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Review and edit OpenAI Cookbook notebooks, Markdown, and MDX for technical accuracy, clarity, grammar, consistency, runnable examples, and repository publication requirements. Use for editorial reviews, pre-merge documentation checks, or notebook Markdown-cell sweeps in openai-cookbook.

>- Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).

Ilipat ang mga Python app mula sa Azure OpenAI Chat Completions papuntang Responses API. Saklaw nito ang pag-migrate ng AzureOpenAI/AsyncAzureOpenAI client sa v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, at mga pagsusuri sa compatibility ng modelo. Nakatuon sa Python, para sa Azure OpenAI. openai responses, pag-upgrade ng openai SDK, migration sa responses API, paglipat mula completions sa responses, gpt-5 migration, azure openai python migration, chat completions papuntang responses, AzureOpenAI papuntang OpenAI client, python azure (simulan direkta sa responses), Node/TypeScript/C#/Java/Go migrations (Python lang ang kasanayang ito), Azure infrastructure setup (gumamit ng azure-prepare), pag-deploy ng mga modelo (gumamit ng microsoft-foundry).'

查詢官方 Microsoft 文件以尋找跨 Azure、.NET、Agent Framework、Aspire、VS Code、GitHub 等的概念、教學和程式碼範例。預設使用 Microsoft Learn MCP，對於存在於 learn.microsoft.com 以外的內容則使用 Context7 和 Aspire MCP。

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.

Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what changed, whats new.

Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.

Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (5 agents) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this; /publish ships directly. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.

Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: <patch|minor|major>. Triggers: publish, release, deploy, npm publish.

Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.