Recently added agent tools.

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

Use when the sandbox app fails to build, boot, render, authenticate, call AI routes, read offers, or deploy cleanly.

## Overview This skill enables validation in the domain of climate-science (earth-sciences). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform validation operations related to climate-science. This includes tasks such as: - interpret data - predict events - analyze samples The skill leverages remote sensing and follows best practices established in the earth-sciences

Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships.

Gerencia e valida a consistencia causal de tramas ramificadas e linhas do tempo alternativas usando grafos de eventos.

name: arbx-g-g005-advanced-react-19-usetransitionuseoptimistic description: "Post-Doc skill alineada al monorepo hefarica/arbitragex-v2 (Frontend Doctrinal (Next.js + Playwright)). Se activa cuando: server actions form state. Doctrina OMEGA Zero-Mocks · Fail-Closed · El Remoto Manda." --- > **Dominio:** Frontend Doctrinal (Next.js + Playwright) > **Nivel:** Post-Doc > **Trigger:** server actions form state > **Repos de referencia:** vercel/next.js · facebook/react · microsoft/playwright · TanSta

## Overview This skill enables simulation in the domain of dark-matter (astronomy). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform simulation operations related to dark-matter. This includes tasks such as: - model phenomena - analyze spectra - measure distances The skill leverages orbital mechanics tools and follows best practices established in the astronomy c

Technical reference on Lightning Network channel factories, multi-party channels, LSP architectures, and Bitcoin Layer 2 scaling without soft forks. Covers Decker-Wattenhofer, timeout trees, MuSig2 key aggregation, HTLC/PTLC forwarding, and watchtower breach detection.

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services.

Use when the user asks to create a QA/review scenario sheet from an Amaranth 10 screen design document and a target Google Sheets URL. This skill copies the standard template tab into the destination spreadsheet using Google Sheets MCP tools, renames it, fills header metadata, preserves formulas/formatting, and writes dense step-by-step test cases.

Design, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations. Use when creating Helm charts, packaging Kubernetes applications, or impl...

## Overview This skill enables prediction in the domain of programming-languages (computer-science). It represents expert-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform prediction operations related to programming-languages. This includes tasks such as: - optimize code - analyze complexity - implement algorithms The skill leverages testing frameworks and follows best practices established

## Overview This skill enables measurement in the domain of recommender-systems (data-science). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform measurement operations related to recommender-systems. This includes tasks such as: - build models - extract features - analyze datasets The skill leverages visualization libraries and follows best practices established in

>

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.

Use when the user wants to create a comic/manga from a story, premise, or prompt. Executes the full pipeline: story analysis, character design, storyboard planning, image prompt composition, and image generation. Produces final comic page images as output.

>

Audit components for hardcoded tenant strings, non-semantic colors, or missing feature flags. Use before PR review or to check tenant isolation readiness.

## Overview This skill enables interpretation in the domain of data-mining (data-science). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform interpretation operations related to data-mining. This includes tasks such as: - build models - extract features - predict outcomes The skill leverages visualization libraries and follows best practices established in the data-s

Maintain this repository's GCP onboarding documentation. Use when changes touch Google Cloud setup, OAuth consent or clients, Google API scopes, Secret Manager, Cloud Run, GitHub Pages deployment configuration, backend environment variables, or frontend environment flags that a new project/environment must configure.

Open the prefab edit stage for a prefab instance or prefab asset GameObject. Modifications inside the edit stage propagate to all instances. Pair with 'assets-prefab-close' to exit the stage when done.

The full Triton Ascend example of the ReLU element by element operator. The standard mode for demonstrating vector 's element by element operation: 1D split, mask border processing, staggering. The code structure of this example can be consulted when generating the elementwise type operator.

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

Skrift form system — Pydantic-backed forms with CSRF protection, template rendering, and hook integration.

Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.

## Overview This skill enables synthesis in the domain of power-systems (engineering). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform synthesis operations related to power-systems. This includes tasks such as: - analyze structures - analyze structures - design components The skill leverages FEA tools and follows best practices established in the engineering com

Run frontclippy against a local HTML file, live URL, snapshot JSON, suite, or manifest and summarize the findings. Use when the user asks to audit a UI, inspect frontclippy output, emit SARIF, or run capture plus analysis.

## Overview This skill enables testing in the domain of optogenetics (neuroscience). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform testing operations related to optogenetics. This includes tasks such as: - record neural activity - model circuits - study behavior The skill leverages electrophysiology equipment and follows best practices established in the neurosc

使用 wrangler CLI 操作 Cloudflare。当用户提到 Cloudflare、CF、Workers、Pages、R2、D1、KV、CDN、DNS、WAF 等时触发此技能。

The doctrine for `/roadmap-review` — interactive triage of roadmap-shape drift, walked one item at a time, with paste-ready resolution phrasing for the active sizing lens.

This skill should be used when the user asks to "swap tokens", "trade ETH for USDC", "exchange tokens on Uniswap", "buy tokens", "sell tokens", "convert ETH to stablecoins", "find memecoins", "discover tokens", "research tokens", "tokens to buy", "find tokens to swap", "what should I buy", or mentions swapping, trading, researching, discovering, buying, or exchanging tokens on any Uniswap-supported chain. Supports both known token swaps and token discovery workflows (discovery uses keyword searc

Turn 'should never happen' into 'cannot happen' by defining owned inductive invariants and enforcing them at parse/construct/API/DB/lock/txn boundaries with a verification signal. Use when prompts mention invariants, impossible states, validation sprawl, cache/index drift, idempotency/versioning, retries/duplicates/out-of-order events, race/linearization bugs, loop correctness, or hardening another workflow (for example /tw-fix) with invariant checks first.

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Build production-ready REST APIs with contract-first design, secure auth, robust testing, and deployment runbooks.

>

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Generate and edit images using NVIDIA FLUX models. Use when user asks to generate images, create pictures, edit photos, or modify existing images with AI. Supports text-to-image generation and image editing with text prompts.

Investigate sudden drops in organic traffic or rankings and run a structured forensic SEO incident response with triage, root-cause analysis and recovery plan.

Run all five review agents on changes, synthesize findings, triage based on developer thinking, and fix approved items. Trigger when the user says "review", "run the agents", "run all four", "run all five", "full review", "code review", or similar.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

AI video production, script writing, and image generation via MCP. Generate video scripts, AI images, and short-form or long-form videos from any topic. Public tools (pricing, quotes) are fully anonymous. Brand-scoped tools (queue status, content lookup) require a free API key. Paid tools require USDC on Base via x402 — the agent must explicitly approve each payment — or can be called with an API key if the brand has prepaid tokens.

Guidance for using asc cli in this repo (flags, output formats, pagination, auth, and discovery). Use when asked to run or design asc commands or interact with App Store Connect via the CLI.

Reviews pull request diffs for correctness, security, maintainability, and test coverage. Use when the user asks for a code review of a change set, patch, or PR description.

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, v

Run local ComfyUI workflows via the HTTP API. Use when the user asks to run ComfyUI, execute a workflow by file path/name, or supply raw API-format JSON; supports the default workflow bundled in assets.

Create a README.md file for the project

Validate CTO Build Framework governance artifacts and file version-bound evidence (runs, reviews, evidence packets) without inflating claims. Use for independent re-execution, internal-consistency reviews, and verdict filing.

Fetch and extract readable text content from a URL, then summarise or present key information.

>