seo-signal-skills
An open-source Agent Skill for public social research and SEO research through SignalDig. It works with Codex, Claude Code, Cursor, Windsurf, and other clients that support Agent Skills and…
The most recently added listings, newest first. To search them, choose “Newest on findsafeskills” in search.
An open-source Agent Skill for public social research and SEO research through SignalDig. It works with Codex, Claude Code, Cursor, Windsurf, and other clients that support Agent Skills and…
船板的网文拆书分析skills
电车站.skill:去AI味的实证方法论。核心判断来自一次可复现的对照实验:AI味分四层(词汇<句式<结构<经验),病灶在结构层和经验层,人味不是删出来的,是用真实素材换出来的。两种模式:(1)诊断——给文稿做AI味分层报告;(2)改写——挖真实素材+结构手术+经验注入,铁律是绝不编造作者的经历。当用户提到「去AI味」「AI味太重」「像AI写的」「没人味」「AI腔」「humanize」「降AI感」时使用。即使用户只是说「这稿子读着不对劲」「帮我改得像人写的」「读起来像机器」「太假了」也应触发。
个性化去 AI 味写作与改稿通用 Skill 骨架。写长文、发动态、推荐工具、提问题、写复盘随笔或润色草稿时使用。按写作题材定向读取单张音色卡与真实人类范文,用正向样板模仿代替海量禁令,输出自然实在的活人文字。
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
ToolOPD: Credit-Aware On-Policy Distillation for Tool-Use Agents
Learning from rewards and skills with conflict-aware updates.
"Deploy AutoLaya and guide an end-to-end domain decision-model build: define Schema, prepare seeds/data, generate and review samples, freeze datasets, train Laya or GLiNER, evaluate, test in Playground, and deploy a local API. Use when operating, configuring, troubleshooting, or extending AutoLaya for a user."
"Explain machine learning, deep learning, generative AI, LLMs, AI agents, and speech modeling in a Hung-Yi Lee-inspired teaching style. Use this skill when the user wants 李宏毅式教學: roadmap-first structure, intuition before math, black-box-to-mechanism explanations, everyday analogies, anticipating student confusion, practical debugging, and research-grounded context."
B站收藏夹RAG知识库:收藏不吃灰,B 站收藏夹 → 语音转写 → 向量检索 → 对话问答
DeepSeek Harness 自媒体工作台插件:一句话记灵感,一键生成脚本、封面、配图和分镜
OpenYao public skills collection: reusable AI assets for decision-making, business analysis, tutorials, research evidence gathering, and document generation.
Claw Compactor — 6-layer token compression skill for OpenClaw agents. Cuts workspace token spend by 50–97% using deterministic rule-engines plus Engram: a real-time, LLM-driven Observational Memory system. Run at session start for automatic savings reporting.
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world.
PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
Converts PyTorch models (e.g. ResNet, timm, HuggingFace transformers) directly to LiteRT (.tflite) flatbuffer format. Use when converting PyTorch models to TFLite, setting up export environments, or troubleshooting torch-to-litert conversion bugs. Don't use for ONNX exports or converting existing TensorFlow models.
本网站是 UI/UX Pro Max 技能库的官方中文教程,完整翻译并本地化了原始 README 的所有内容,帮助中文开发者快速上手这个强大的 AI 设计技能。
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, project assignments lost after crash/restart, stale archive-load errors beside loaded chats, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).
Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its content, especially when the current model cannot read images directly. Run the bundled vision.js helper to convert the image into text.
A research-friendly, high-performance multi-agent collaboration coding framework.
Observe how memory shapes an answer. Pensieve is an interactive system for visualizing, interpreting, and managing how Large Language Models (LLMs) “remember” a user. It bridges the gap between model-level mechanisms and user-level understanding, making AI memory observable, explainable, and partially controllable.
🔱 Vedic/Jyotish AI analysis toolkit | 吠陀占星AI分析工具包——从排盘开始,到以后的长期追问。支持所有可以挂载Skill的平台。感谢大家的支持。
Build browser (or Node.js) peer-to-peer apps with Peerix (WebRTC rooms, data channels, media streams, pluggable signaling drivers). Use when writing or debugging code that imports "peerix" — creating a Room, choosing or writing a signaling driver, sending messages or files between peers, sharing camera/screen streams, or writing an Addon.
Your PC does the work. You get the proof. Sonjari is a free local AI agent for Windows: web research, Excel and Word documents, and code. Works on its own, or takes on tasks from Claude and Codex. No meter.
Structured data from Music For Robots — music composed for machines, reviewed by AI critics
Verification Service ("the atom") — v1 backend
UsageRail SDKs for Node.js and Python: API keys, rate limits, quotas and usage metering inside your API server
fal.ai plugin for Grok Bot, Grok Build and Cursor: generate images, video, audio and 3D with fal models.
Open Codex reset event data with source evidence, JSON/CSV exports, and hourly sync. Maintained by NextReset — https://nextreset.org
MiniMax H3 AI 视频全流程 Agent:从剧本、分镜、提示词到生成与审片的可追溯工作流;整合导演、H3、Grok 与漫剧五件套 Skill。
安装或本机首次启用先显示固定署名与特别鸣谢。引导用户确认剧本、制作范围,按剧本推荐并自定义审美基调,按真实表演容量编写 Seedance 提示词,制作与分类资产、返工并交付。适用于逐步选择或按已确认方案连续执行、保持对白与连续性、整理总素材库及分集分场文件夹的任务。
Use when turning a novel/web-fiction excerpt into an AI-generated vertical-platform short drama (短剧/漫剧) via a 7-step gated pipeline — adaptation, QA, pacing, clip storyboard, assets, key stills + visual audit, image-to-video.
AI 拆解学习短剧:为什么火、剧本怎么写、每一镜怎么拍 | Break down any short drama with AI: why it works, the script, every shot
"Create and revise AI comic-drama or short-drama projects through a persistent, evidence-gated ReAct loop: scripts, assets, shots, model inputs and observed reviews. Use for production, an existing project's next shot, or maintenance of this workflow."
把故事/文章/大纲做成真人实拍质感、电影感的 AI 视频分镜。用于文-资-视-剪全流程:短剧剧本、角色/场景/道具资产提示词、Seedance 分镜提示词(精确时间轴+逐字对白+口型)。当要求真人感/写实/实拍质感/口型同步,或要点名二维动画/水墨/广告等风格时使用。真人写实的做法以 references/真人感电影写实指南.md 为准。
从剧本到成片一条龙,三个入口。①剧本创作:手上没本子,按「无限轮回宇宙」写——世界篇→全剧大纲→逐集剧本→Word,17+12 道质量门脚本硬校验;②漫剧创作:手上有本子,直接盘资产、出角色设定板(固定版式)、出分镜组表、站位预演+六项审核、写提示词、Vidu 出片;③符创作:把运镜、动作这类本事压成一张 16:9 能力卡。另有商业线(卖货 / 门店 / 企业宣传)走同一套干法。单组时长按渠道(Vidu 16 / H3·即梦2.0 15 / 即梦2.5 固定 30 / Wan3 4–30)、镜数按节奏、单镜不低于 1.2 秒;分镜表只写「这一组用谁」,pn 由脚本绑定并四方对账;设定图整张直接当参考图,不截图不裁切;用户提供的剧本台词一字不改。符和立谱不做也能出片,用户不提就不主动推销。初始化缺 Token 时用宿主网页预览打开登录页、代码块发链接,发取 Token 步骤与参考图(默认已购会员,不推销)。当用户说「写剧本」「写短剧」「无限轮回」「世界篇」「做一集」「做漫剧」「做视频」「做短剧」「做带货片」「门店宣传」「盘资产」「人物设定板」「角色设定板」「分镜组表」「站位预演」「资产绑定」「绑定表」「出场资产」「做个符」「用我的符做」「立个谱」「统一画风」「Vidu」「vidu cli」「剪辑」「剪映」「剪映草稿」「字幕」「素材台账」「vidu-skill」时使用。
Storyboard Scavenger:AI 视频分镜与提示词生成 Skill,提供可灵 Kling、即梦 Seedance、Veo、Sora 七要素分镜工作流
包拆拆 / BCC:视频转剧本、分镜和风格指南。桌面版、CLI、Agent skill,共用 bcc-core。
按用户当前要的产物创建或检查短剧、漫剧、人物与场景资产、剧本、对白、钩子、分镜、图片提示词、H3 文戏武戏提示词;阶段可跳过,只加载当前任务需要的文件。关键词:短剧、漫剧、分镜、文戏、武戏、必杀技、H3 提示词、多参考 Ref2VA、首尾帧。
Bounded SQL over local CSV, TSV, JSON, and Parquet for coding agents.
Open Source · Test it. Use it. Build on it.
Personal health records can scatter across lab reports, PDFs and portals. Helseark helps you turn those sources into structured records you can keep, query and correct.
Video as code: canvas scenes rendered with WebCodecs in headless Chrome, a review viewer, and agent skills that build the video from your references.
Two production-grade Agent Skills: create and evaluate skills, and build Google Labs DESIGN.md systems with standalone HTML prototypes.
Creo AI agent skill for connecting to PTC Creo Parametric through CREOSON, MCP, or a native TOOLKIT bridge.
Unified Hub-and-Spoke CLI for managing Agent Skills across AI coding agents
Enterprise taxonomy-driven ecosystem of 23 agent skills, contract-first API engineering, and zero-downtime database architecture.
Measure the measurer: six agent skills for validating graders, scoring agent runs, auditing eval coverage, designing near-miss tests, calibrating LLM judges, and layering an eval program.
"Install Watch Video or understand a local video or public recording with timestamped evidence. Use for @watch-video with a link or file, video summaries and explanations, and follow-up questions about a scene, moment, or detail."