agent-usage-optimizer-keyword-route-classification
About
This Claude skill classifies development tasks into specific processing routes (A, B, C, Bulk, Long-context) based on keywords in the user's request. It helps optimize agent usage by routing simple tasks, standard implementations, complex architecture work, bulk operations, and large-context jobs appropriately. Developers use it to ensure their queries are handled by the most suitable agent with the correct scope and resources.
Quick Install
Claude Code
Recommendednpx skills add vamseeachanta/workspace-hub/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agent-usage-optimizer-keyword-route-classificationCopy and paste this command in Claude Code to install this skill
Documentation
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 Repository
Related Skills
content-collections
MetaThis 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.
cloudflare-turnstile
MetaThis 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.
cloudflare-cron-triggers
TestingThis 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.
llamaindex
MetaLlamaIndex 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.
