MCP HubMCP Hub
스킬 목록으로 돌아가기

agent-usage-optimizer-keyword-route-classification

vamseeachanta
업데이트됨 Today
67 조회
3
2
3
GitHub에서 보기
기타word

정보

이 Claude 스킬은 사용자 요청의 키워드를 기반으로 개발 작업을 특정 처리 경로(A, B, C, 벌크, 장문맥락)로 분류합니다. 이를 통해 단순 작업, 표준 구현, 복잡한 아키텍처 작업, 대량 작업, 그리고 대규모 맥락 작업을 적절하게 라우팅하여 에이전트 사용을 최적화합니다. 개발자는 이를 통해 자신의 질의가 올바른 범위와 리소스를 가진 가장 적합한 에이전트에 의해 처리되도록 보장합니다.

빠른 설치

Claude Code

추천
기본
npx skills add vamseeachanta/workspace-hub
플러그인 명령대체
/plugin add https://github.com/vamseeachanta/workspace-hub
Git 클론대체
git clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agent-usage-optimizer-keyword-route-classification

Claude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요

문서

Keyword → Route classification

Keyword → Route classification

Compound / Route C keywords:
  architecture, design, system, multi-file, refactor, security review,
  cross-repo, orchestrat, compound, plan, spec

Standard / Route B keywords:
  implement, feature, review, documentation, test, bug, fix, config,
  update, migrate, integration

Simple / Route A keywords:
  generate, scaffold, unit test, snippet, function, debug, format,
  check, validate, search, grep

Bulk keywords:
  summarise, summarize, batch, bulk, all files, across repos, report

Long-context keywords:
  large file, full repo, 1000 lines, entire codebase, cross-repo scan

Output format for ad-hoc recommendation:

Task: "implement OAuth login for the API"
Route: B (Standard)

  Primary:    Claude Sonnet  [quota: <CLAUDE>% — OK]
  Secondary:  Codex          [quota: <CODEX>%  — OK]

  Rationale: Standard feature implementation with moderate complexity.
             Sonnet provides quality output within quota headroom.
             Codex is secondary for focused function-level generation.

GitHub 저장소

vamseeachanta/workspace-hub
경로: .claude/skills/ai/agent-usage-optimizer/keyword-route-classification

연관 스킬

content-collections

메타

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

스킬 보기

cloudflare-turnstile

메타

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

스킬 보기

cloudflare-cron-triggers

테스팅

This skill provides comprehensive knowledge for implementing Cloudflare Cron Triggers to schedule Workers using cron expressions. It covers setting up periodic tasks, maintenance jobs, and automated workflows while handling common issues like invalid cron expressions and timezone problems. Developers can use it for configuring scheduled handlers, testing cron triggers, and integrating with Workflows and Green Compute.

스킬 보기

llamaindex

메타

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

스킬 보기