菜单
Compress long prompts and contexts while preserving semantic meaning — reduce token count without losing information.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Sends messages between agents, broadcasts to channels, and retrieves message history for inter-agent communication.
Spawns, manages lifecycle, and terminates autonomous AI agents from the 40+ built-in agent catalog.
Optimize prompts and context windows to reduce token usage while preserving quality.
Animated desktop character state machine for Sven's Tauri companion app. Manages character form (ORB, ARIA, REX, ORION), state transitions (idle→thinking→speaking→celebrating), walk cycles, thought bubbles, sound effects, and real-time agent event sync.
Multi-model deliberation system. Sends queries to multiple LLMs simultaneously, has them peer-review each other's responses anonymously, then a chairman model synthesizes the best answer. Supports configurable council composition, voting strategies, and cost tracking.
Interactive educational autograd engine — port of Karpathy's micrograd. Build, train, and visualise tiny neural networks step-by-step to learn how backpropagation works.
| name | prompt-compressor |
| description | Compress long prompts and contexts while preserving semantic meaning — reduce token count without losing information. |
| version | 0.1.0 |
| publisher | acmecorp |
| handler_language | typescript |
| handler_file | handler.ts |
| when-to-use | Use when the user has a long prompt or context that needs to be shorter, or when hitting token limits. |
| inputs_schema | {"type":"object","properties":{"action":{"type":"string","enum":["compress","decompress_plan","benchmark"]},"text":{"type":"string"},"target_ratio":{"type":"number","description":"Target compression ratio (0.0-1.0). E.g. 0.5 means halve the token count."},"preserve_code":{"type":"boolean"}},"required":["action","text"]} |
| outputs_schema | {"type":"object","properties":{"result":{"type":"object"}}} |
Compresses long contexts while preserving semantic information. Uses multiple techniques: abbreviation, structure extraction, key-phrase retention, and whitespace optimization.
