하나의 Skill, 완전히 새로운 가능성. 다음 워크플로를 찾아보세요.
acon-context-compression-agents
Reduce memory overhead of long-horizon LLM agents by learning task-specific context compression strategies. A learnable compressor adapts by analyzing failure cases, achieving 26-54% memory reduction while preserving 95%+ accuracy, enabling smaller models to act as efficient long-context agents.
ai-gif-compressor
web developers, marketers, social media managers compress GIF files into compressed GIF files using this skill. Accepts GIF, MP4, WebM, APNG up to 200MB, renders on cloud GPUs at 720p, and returns MP4 files in 10-30 seconds. Designed for reducing GIF file size for web and social media use.
caffeine-overdose
Goes wide and exhaustive — every option, every edge, every step spelled out, the opposite of a compressor; invoke via /caffeine-overdose when you want maximum thoroughness and nothing left implicit.
context-compressor
Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.
core-context-compressor
Use this skill when the user says 'compress context', 'context summary', 'token save', 'compression', 'condense', 'summarize conversation', 'context budget', 'reduce tokens', 'context window'. Produces a structured compressed summary of current session context. Do NOT use for: general note-taking or file writing.
ehr-semantic-compressor
1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work. 2. Validate that the request matches the documented scope and stop early if the task would require unsupported as.
fibonacci-quasicryth-compression
Introduce Quasicryth, a text compressor using Fibonacci quasicrystal tilings for phrase-level compression. Prove that aperiodic structures never structurally collapse at depth, enabling compression at arbitrary hierarchy levels. Bridge quasicrystal mathematics with practical compression, achieving 22.59% ratio on enwik9 with unbounded scaling advantages.
generation-and-refinement
Use FlashRAG generators, prompt templates, OpenAI/vLLM/HF/FastChat backends, multimodal generation, refiners/compressors, and judgers as reusable components.
ppt-compressor
This skill should be used when the user wants to compress a PowerPoint (.pptx) file by reducing the size of embedded videos and large images. It handles the complete workflow of extracting media from .pptx archives, compressing videos with a bundled ffmpeg (no installation required) and images with Pillow, and repackaging into a valid .pptx file. Trigger ph…
structured-context-compressor
Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.
video-compressor
视频压缩与静默片段剪切工具。使用 FFmpeg CRF 模式压缩视频，适配屏幕录制/课件场景；支持检测并去除静默静止片段。自动检测硬件与源码率并选择最优编码方案（高码率源走 VideoToolbox 硬件加速，低码率录屏自动改用 x264 CRF 自适应编码）。本技能应在用户需要压缩视频、减小视频大小、去除视频空档时使用。不要用于：视频剪辑、音频提取、格式转换。
video-scrub
把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流）， 隐私保证来自结构，不来自枚举。 难点不在容器 tag，在**看不见的那几层**：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——`ffprobe` 一个都看不见。 五个藏身处逐一堵死，每一处都有实测。 默认 `--mode copy`：**画面逐字节照搬**（cmp 验证过），只重编音频，53 秒的片子 1.3 秒跑完； `--mode encode` 完整重编码，多杀掉码流…
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage