oimiragieo/agent-studio - 第 12 页

svelte-expert

Svelte and SvelteKit expert including components, stores, and routing

原文语言：英语

swarm-coordination

Multi-agent swarm coordination patterns. Orchestrates parallel agent execution, manages agent communication, handles task distribution, and coordinates results aggregation.

原文语言：英语

system-health-check

Verifies repository baseline test passing state and available memory/GPU resources to ensure safe mission execution.

原文语言：英语

tall-stack-general

General guidelines for TALL stack development, emphasizing Laravel and PHP best practices.

原文语言：英语

task-delegation

Agent task delegation patterns — spawn protocols, handoff metadata, drain gate, parallel limits, and model selection for multi-agent orchestration

原文语言：英语

task-management-protocol

Protocol for task synchronization, context handoff, and cross-session coordination using Claude Code task tools. Ensures agents properly update tasks with findings and enables seamless work continuation.

原文语言：英语

tauri-native-api-integration

Rules for integrating Tauri's native APIs in the frontend application.

原文语言：英语

tauri-security-rules

Security-related rules for Tauri application development.

原文语言：英语

tauri-svelte-typescript-general

General rules for developing desktop applications using Tauri with Svelte and TypeScript for the frontend.

原文语言：英语

tauri-svelte-ui-components

Rules specific to Svelte UI component development in Tauri applications.

原文语言：英语

tdd

Canon TDD for humans and AI agents. Use for production code changes by writing tests first, proving RED, implementing minimal GREEN, and refactoring safely. 2026 edition adds TDP, flakiness gate, ralph-loop integration, memory-search in Step 0, PBT as Step…

原文语言：英语

team-orchestration

6-phase multi-agent pipeline with approval gates. Orchestrates Plan→Design→Implement→Review→Test→Deploy phases with explicit entry/exit criteria, phase-level agent assignment, and human-in-the-loop approval checkpoints.

原文语言：英语

telegram-polling

Use when building, debugging, or documenting Telegram bot polling flows that need safe agent routing, state tracking, and final-only replies without webhooks.

原文语言：英语

template-creator

Creates and registers templates for agents, skills, workflows, hooks, and code patterns. Handles post-creation catalog updates, consuming skill integration, and README registration. Use when creating new template types or standardizing patterns.

原文语言：英语

template-renderer

Render templates by replacing {{TOKEN}} placeholders with actual values, supporting all three templates (specification, plan, tasks) with schema validation and security sanitization

原文语言：英语

template-updater

Research-backed template refresh workflow for updating existing templates with placeholder verification and rendering validation.

原文语言：英语

thinking-tools

Structured thinking patterns for agent self-reflection. Includes think-about-collected-information (validate research), think-about-task-adherence (stay on track), and think-about-whether-you-are-done (completion validation).

原文语言：英语

tool-creator

Creates tool files for the Claude Code framework. Tools are executable utilities organized by category in .claude/tools/.

原文语言：英语

tool-updater

Research-backed CLI tool refresh workflow for updating existing tools with TDD checkpoints and CLI invocation validation.

原文语言：英语

track-management

Track management methodology - creating and managing logical work units (features, bugs, refactors) through specification, planning, and implementation phases.

原文语言：英语

transcription

Audio and video transcription using Whisper AI via the transcribe-anything package. Supports local files, YouTube URLs, and microphone input with multiple backends (faster-whisper, openai-whisper, Whisper API).

原文语言：英语

tsconfig-json-rules

Defines general rules for tsconfig.json. It suggest using strict TypeScript checks

原文语言：英语

tts-generation

AI text-to-speech generation using OpenAI TTS, ElevenLabs, and Google TTS backends. Converts text to audio files with voice selection, speed control, and format options.

原文语言：英语

typescript-expert

TypeScript and JavaScript expert including type systems, patterns, and tooling

原文语言：英语

uat-verify

Verify completed work against acceptance criteria, collect evidence, and produce a PASS/FAIL UAT report

原文语言：英语

ui-components-expert

UI component library expert including Chakra, Material UI, and Mantine

原文语言：英语

user-flow-validator

Test user journey assertions against real surfaces (Web UI, CLI, API) with evidence collection and isolation boundaries

原文语言：英语

user-research

UX research methodology skill — usability testing protocols, user interview frameworks, persona development, journey mapping, heuristic evaluation (Nielsen's 10), A/B test analysis, accessibility auditing, and research synthesis using NNGroup methodology.

原文语言：英语

using-git-worktrees

Create isolated development workspaces with safety verification. Use when needing parallel development branches.

原文语言：英语

variant-analysis

Discover vulnerability variants by identifying similar code patterns across a codebase using CodeQL and Semgrep pattern matching, finding instances where a known bug class may recur.

原文语言：英语

vercel-ai-sdk-best-practices

Best practices for using the Vercel AI SDK in Next.js 15 applications with React Server Components and streaming capabilities.

原文语言：英语

verification-before-completion

Gate function preventing unverified completion claims. Use before claiming any task is done.

原文语言：英语

visual-and-observational-rules

Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.

原文语言：英语

voice-clone-generator

Use when generating new content that must match an established writing style profile. Loads the style profile from style-analyzer, constructs a style-constrained system prompt, generates content, and performs A/B comparison against original samples for…

原文语言：英语

vue-expert

Vue.js ecosystem expert including Vue 3, Composition API, Nuxt, and Pinia

原文语言：英语

wave-executor

Fresh-process orchestration for EPIC-tier batch pipelines. Spawns a new Bun process per wave via the Claude Agent SDK, preventing GC-related crashes in long-running sessions.

原文语言：英语

web-artifacts-builder

Build elaborate, multi-component web artifacts using React 18 + TypeScript + Tailwind CSS + shadcn/ui. Produces a single self-contained HTML file with all assets inlined. Use for complex artifacts requiring state management, routing, or shadcn/ui components.…

原文语言：英语

web3-expert

Web3 and blockchain expert including Solidity, Ethereum, and smart contracts

原文语言：英语

webapp-testing

Test local web applications using Playwright with Python. Verify frontend functionality, debug UI behavior, capture screenshots, and view browser console logs. Supports static HTML files, dynamic webapps with running servers, and automated test generation.

原文语言：英语

webmcp-browser-tools

WebMCP — browser-side API that lets web applications expose their own functionality as MCP tools TO AI agents. Use when designing or integrating with web apps that surface UI actions (forms, buttons, data queries) as callable agent tools. NOT for web scraping…

原文语言：英语