rtk-optimizer
Optimize command outputs with RTK (Rust Token Killer) for 70% token reduction
Explore
13,214 skills indexed with the new KISS metadata standard.
Optimize command outputs with RTK (Rust Token Killer) for 70% token reduction
Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.
Nuxt SEO meta-module with robots, sitemap, og-image, schema-org. Use when configuring SEO, generating sitemaps, creating OG images, or adding structured data.
Automate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle invitations. Always search tools first for current schemas.
Analyze a GitHub pull request including diff, comments, related issues, and local code context
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
Convert Android XML layouts to Jetpack Compose. Use when asked to migrate XML layouts, convert views to composables, or help with Compose migration. Handles layouts, widgets, attributes, styles, and resource references.
When working with JSON data in LLM prompts (especially large arrays or tabular data), consider the token-efficient TOON (Token-Oriented Object Notation) format which reduces tokens by 30-70% while maintaining lossless JSON representation and structural validation. Use for reading/writing .toon files, converting JSON↔TOON, or optimizing structured data for LLM consumption with guardrails like [N] counts and {field} headers.
When working with JSON data in LLM prompts (especially large arrays or tabular data), consider the token-efficient TOON (Token-Oriented Object Notation) format which reduces tokens by 30-70% while maintaining lossless JSON representation and structural validation. Use for reading/writing .toon files, converting JSON↔TOON, or optimizing structured data for LLM consumption with guardrails like [N] counts and {field} headers.
Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking.
自动从 Anna's Archive 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。
Convert Android XML layouts to Jetpack Compose. Use when asked to migrate XML layouts, convert views to composables, or help with Compose migration. Handles layouts, widgets, attributes, styles, and resource references.
When working with JSON data in LLM prompts (especially large arrays or tabular data), consider the token-efficient TOON (Token-Oriented Object Notation) format which reduces tokens by 30-70% while maintaining lossless JSON representation and structural validation. Use for reading/writing .toon files, converting JSON↔TOON, or optimizing structured data for LLM consumption with guardrails like [N] counts and {field} headers.
Este archivo documenta las instrucciones y configuraciones para agentes de IA que trabajan en este repositorio.
This file provides guidance to AI agents when working with code in this repository.
This project enforces commit messages via [commitlint](https://commitlint.js.org/)
This document provides guidelines for AI coding agents working in the JSON Visualization codebase.
`services/` hosts all runtime microservices, including FastAPI backends (`budapp`, `budcluster`, `budsim`, `budmodel`, `budmetrics`, `budnotify`, `ask-bud`, `budeval`), the Rust gateway (`budgateway`), and Next.js frontends (`budadmin`, `budplayground`). Shared automation lives in `scripts/`, infras
Main backend. Exposes all business logic via REST. Producer only (never consumes from RabbitMQ).
Four things that actually determine whether AI-operated business works — instructions, architecture, system thinking, and where the real bottleneck is.
**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.
> Parent rules: [`/workspace/backend/agents.md`](../agents.md)
Guidelines for AI agents working on the lading codebase. For detailed rationale
The call intelligence system uses a multi-agent orchestration architecture where 6 specialized AI agents process call transcripts in parallel, each producing domain-specific artifacts. The orchestration layer coordinates agent execution, deduplicates outputs, and routes artifacts through approval wo