Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Read the content of a video file or a folder of videos and get a usable transcript. Extracts burned-in (hard) subtitles by cropping the subtitle band and running PP-OCRv4, falls back to faster-whisper speech-to-text when there are no burned-in subs, and pulls embedded subtitle tracks and keyframes alongside. Use when asked to 读取视频 / 视频内容 / 视频转文字 / 提取字幕 / transcribe a video / summarize what a video says / 把这个视频讲了什么整理出来. Built for social-platform clips where the subtitle is printed into the picture, which is far more accurate than speech recognition on a Japanese or English dub over Chinese subs.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Use when building, reviewing, or polishing any user-facing UI — web pages, admin dashboards, mobile screens, React/React Native/Tailwind/antd components, forms, menus, tables, cards, charts, dialogs, empty states, login/signup, pricing or landing pages — or when asked for a UI/UX review, design feedback, or to make a screen look or feel better.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Riset data permintaan pasar (market demand research) dari web dengan metode yang ketat — memecah permintaan user jadi daftar data yang harus ditemukan, mencari di banyak sumber, memverifikasi angka di halaman aslinya, mencocokkan minimal dua sumber, menormalkan mata uang/tahun/satuan, menandai estimasi, lalu menulis laporan Markdown bersumber lengkap. Gunakan skill ini setiap kali user minta data atau riset pasar, ukuran pasar (market size, TAM/SAM/SOM), CAGR atau pertumbuhan pasar, tren permintaan atau tren pencarian, potensi pasar suatu produk/jasa, negara/segmen dengan permintaan tertinggi, harga pasar, pesaing dan pangsa pasar, data impor/ekspor suatu komoditas, atau validasi ide bisnis/produk dengan data — walaupun user tidak menyebut kata "riset", misalnya "produk X laku nggak di Eropa?", "cariin data pasar buat ...", "how big is the market for ...", "is there demand for ...".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Switch Claude accounts, keep working on the same project: shared Claude Code sessions, scheduled tasks, briefings and /handoff across accounts on one computer (Windows, macOS beta).
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
인스타그램 캐러셀(카드뉴스, 인스타 공식 최대 세로 비율 3:4 1080×1440 PNG)을 브리프 → 팩트시트 → 원고 → 스타일 선택 → A/B 변형 → 렌더·자동 게이트 → 발행 패키지 순서로 만든다. 실무자가 캐러셀/카드뉴스를 만들거나, 디자인 스타일을 고르거나, 표지·2번 카드·CTA·표지 사진·장수·순서·스타일 중 하나를 A/B로 비교하려 할 때 사용한다.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
用照片做老年人居家跌倒/磕绊风险评估,按 MZ/T 218—2024《老年人居家环境适老化改造通用要求》给出分级、条款依据与改造建议,产出三色标注图与可打印 HTML 报告。触发场景:用户给出老人房间/卫生间/卧室照片要做适老化评估、居家隐患排查、改造建议,或提到 MZ/T 218、适老化改造、防跌倒、扶手、防滑。
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A big model thinks, a local LLM does the work for free, the big model checks. Claude skill + PowerShell scripts for Ollama and any OpenAI-compatible server.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
YouTube Hunter — record YouTube live streams, download videos, cut them into 9:16 Shorts with karaoke subtitles, write trend-based titles/descriptions/tags in any language, and auto-upload to YouTube. Use for "youtube hunter", "record the stream", "make shorts from this video", "trend tags", "upload to youtube", "auto mode".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Varre o código de um projeto, diagnostica se Machine Learning é tecnicamente viável, estima os ganhos, sugere a infra e gera um plano em Markdown (ML_PLANO.md) para outra IA construir o ML sob medida. Agnóstica de banco. Não faz perguntas. Use para "/create_ML", "viabilidade de ML", "dá para colocar ML neste projeto?", "plano de ML", "diagnóstico de ML".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Make a punchy vertical "What if…?" science / space explainer reel (Shorts, Reels, TikTok) in a neon flat-vector space style — deep navy/violet starfields, glowing two-tone planets, rounded pill tags on leader lines, zoom-inset cards, dashed orbits, "Not to scale" tags, full-bleed surface scenes, an original kid + critter duo who react in close-ups, and bold 2–3-word captions in the lower third — built in Remotion with an original Web Audio score + SFX (wordless) or a Fish Audio voiceover. Use whenever the user asks for a neon space-explainer / space / astronomy / "what if Earth…" / science explainer short, wants a reference space-explainer reel's style adapted, says "use the neon-space-explainer skill", or asks to re-time, re-score or re-render earth-rings or a project made with this skill.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Turns long gaming streams and videos (GTA 6 and any other game) into finished vertical 9:16 Shorts that show ONLY the gameplay, never the streamer's face. Takes a Twitch, YouTube or Kick VOD link or a video file, transcribes it on this computer, finds the best moments from chat spikes, voice peaks and viewer clips, hides the facecam, adds word-by-word captions, a hook, a cover and post text, runs a quality check, lets the user approve each Short, can add the user's own HeyGen avatar as a webcam under the game with an English commentary and captions, then can publish the approved ones with Blotato. Use it whenever the user wants to clip a stream, make Shorts, Reels or TikToks from a gameplay video or Twitch link, "make 5 Shorts from <link>", "clip this VOD", "gameplay only, no face", wants their avatar, face or voice commentary on the Shorts, or wants to review or post clips this skill made, even if they don't name the skill.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Build a cute, animated, mobile-friendly celebration website (birthday, anniversary, graduation, wedding…) for someone special — themed colours, a cat/bunny/bear character, number candles you can blow out, 3D photo carousel, draggable polaroids, tap-the-hearts messages, scrapbook and a 3D photo world. Use when the user wants to make a birthday/wish/greeting website, a surprise page for a friend or partner, or asks for "a cute website with photos and messages".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Chuẩn hoá tài liệu Word (.docx) theo thể thức báo cáo nhà nước (Nghị định 30/2020/NĐ-CP) và quy ước báo cáo khoa học, luận văn. Gồm tạo mục lục, danh mục bảng/biểu đồ/hình tự động; đánh số chỉ mục, chương (số La Mã/Ả Rập); chú thích bảng biểu; phông, cỡ chữ, lề, giãn dòng; văn phong kỹ thuật (khẩu ngữ, câu dài, viết tắt, dấu câu, chính tả thống nhất); thể thức văn bản hành chính (quốc hiệu, tiêu ngữ, tên cơ quan, số ký hiệu, địa danh ngày tháng, tên loại, trích yếu, nơi nhận, vị trí và định dạng chữ ký); cỡ chữ, đậm/nghiêng từng thành phần và từng cấp tiêu đề; vị trí, kích thước ảnh; định dạng bảng; số trang; tạo văn bản mẫu đúng thể thức; kiểm tra số liệu, dấu thập phân, ngày tháng. Dùng khi người dùng nói "đánh mục lục", "danh mục bảng", "chuẩn hoá format", "format theo chuẩn nhà nước", "Nghị định 30", "kiểm tra thể thức", "quốc hiệu tiêu ngữ", "chữ ký", "nơi nhận", "soạn công văn/báo cáo/tờ trình mẫu", "văn phong", "rà soát câu chữ", "luận văn", "báo cáo".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Tidy the images and videos in messy Mac folders (Downloads, Desktop, screenshots, old exports) by sight. Builds a local page that shows every picture and video as one long list of thumbnails; the person sorts them into their own buckets with number keys; then Claude proposes where each bucket goes and moves files only after the person's yes, with a log that undoes it. Use when someone wants to clean up, sort, organize or declutter pictures, screenshots or videos on their Mac.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Build professional, distinctive, pitch-ready business websites — including scroll-driven "3D" heroes (AI video scrubbed by scroll), real-time Three.js / React Three Fiber scenes, GSAP + Lenis motion, and treated-video shaders — that do NOT look AI-generated. Covers the brief, reverse-engineering reference sites, design system (type, colour, layout, copy), hero/asset pipeline, performance and accessibility, visual QA with screenshots, a slop linter, deployment, and pitching the site to a local business. Use this whenever the user wants to build, redesign or polish a website or landing page, mentions 3D websites, scroll animations, Awwwards-style or "$10K" sites, Three.js/GSAP/Spline, wants a site "like" another site, wants to rebuild a business's site to pitch or sell it, or complains a site looks generic / like AI slop — even if they don't say "webbuild".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Minecraft 整合包诊断与治理:证据化审计模组冲突、材质链、动画栈与性能瓶颈
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Mentor-style guide for writing public policy memos, policy briefs and ministerial submissions (مذكرة سياسات، موجز سياسات، ورقة سياسات). It walks the writer through problem definition, audience and persona analysis, precise goals and indicators, options and criteria, actionable recommendations, the narrative, and a final review against assessor criteria, coaching rather than writing the whole memo for them. Use it whenever someone is preparing, planning, reviewing or improving any public policy paper, memo or brief, in Arabic or English, including academy or university assignments, think-tank briefs, submissions to a minister or government body, or when they ask how to turn an idea into a policy recommendation, even if they never say the word "skill" or "mentor".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A decision log for your AI. It records what you chose, what you rejected and why, and checks it before suggesting anything.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Plan, build and teach the launch of a small-budget Meta (Facebook and Instagram) ad test for any app, SaaS or small-business product that has a website and a web app. Produces ad creatives (feed, square, story and link shapes, in any languages including right-to-left), a Facebook page profile picture and cover, Meta Pixel and sign-up tracking, ad copy, and a one-step-at-a-time campaign walkthrough for a first-time advertiser. Use when asked to "run ads", "set up Meta ads", "make social ads", "add the Meta pixel", "teach me to advertise", or to prepare an ad test on a small budget.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Skill de Claude Code para figuras de geología con aspecto de informe real: secciones con fallas y discordancias, cortes de alteración en vetas, modelos de yacimiento y columnas estratigráficas.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Rules and a starter site for AI assistants (Claude, ChatGPT, Codex, Cursor) that build and maintain multilingual company websites on Hostilo
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Set up a quiet daily watch for serious security holes in the software behind the user's websites and servers (WordPress, Drupal, Joomla, Ubuntu, Debian, Nginx, Apache, PHP, Docker, app libraries and more). Reads official security lists, filters them to what the user runs, stays silent when nothing concerns them, and sends a Telegram message in plain words with a ready instruction to forward to a developer or AI agent. Use when the user wants to monitor vulnerabilities or CVEs for their site or server, get security alerts in Telegram, or stop learning about critical security holes from social media.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Build a Google Play and App Store submission pack for an app (icons, framed screenshots in the exact store sizes, feature graphic, listing text with character limits, console form answers, blocker analysis) into a store/ folder in the project. Use when asked to make an app "Play Store / App Store ready" or to prepare store assets, listings or console form answers.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Claude skill for practising German for the Swiss FIDE integration test: writing, reading, listening and speaking, with FIDE-style feedback.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Unofficial CLI for the Nmbrs Reporting (Visionplanner) public API, with a Claude skill. Safe for AI agents: every change is a plan you apply.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Claude skill that designs, validates and exports 3D-printable parts for your own printer (STL/3MF/STEP). EN/ES.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Design, remix, slice and prepare 3D prints with Bambu Studio on macOS (Bambu Lab A1 mini by default). Use when the user wants to modify a model they liked, design a part from scratch, slice an STL/3MF, or print on their Bambu printer; Turkish triggers: "3D baskı", "bunu bas", "tasarla", "Bambu Studio".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Write, edit and read Feishu / Lark cloud docs (飞书云文档 on any feishu.cn / larksuite.com tenant) by driving the real editor, either in the user's logged-in ego browser or in a normal Google Chrome (Playwright, one-time login). Builds rich docs from Markdown — headings, lists, todos, native tables, coloured callouts (高亮块) with icons, N-column layouts (分栏), coloured text and labels, images, and editable native mind maps / flowcharts (Mermaid → 画板) — following a style guide distilled from Feishu's official templates — and edits, inserts or deletes blocks in existing docs without clobbering the user's edits. Use whenever the user asks to write or update a 飞书文档, put a report or 思维导图 into Feishu, or read what a Feishu doc currently says.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Ask your AI agent to check your computer for viruses and suspicious programs. Works on Windows, macOS, and Linux.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Agent skill: one sentence about a business in, a working multi-tenant management system out.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
An Agent Skill for calm software: monochrome, text-first, one-purpose app design with measured type & spacing. (EN/KO)
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
"Plain spoken American English, aka Hemingway style or US government plain language: plain words, loose sentences, no British words, no deck speak, shrugging tone. Use for all writing."
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
UGC creator skill for Claude Code, Codex, Cursor and OpenClaw: turn a paid UGC campaign brief into a checklist and a true-for-you script, edit what you film, post with the ad label to your own TikTok, Reels and Shorts, and track payouts. Never generates a person. Free, MIT.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A memory for Claude Code that stays correct. One working reference, one keeper agent, every fact tagged with its source.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Editor de Reels por template para o Claude Code (macOS): corta pausas e erros, legenda animada, tela verde, tela dividida, yap, efeitos e prévia com storyboard.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Build interview-ready projects. A phase-by-phase methodology, real worked examples, and importable Claude skills for picking an idea, naming risks, adversarial testing, and writing an honest case study.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A model-agnostic skill that helps any AI make posters that don't look AI-generated
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A Claude Code skill that turns a frontend change into a review page stakeholders can comment on: captioned screenshots of every screen and state, pins, notes, and a resolve and reopen flow, without running the app.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Make paper-collage ("Vox-style") explainer videos and kinetic lyric videos with no API keys and no paid services: torn colour paper, scissor-cut photo stickers, tape, halftone dots and words slapped on in the beat, while a camera travels across one big scrapbook wall. Uses Remotion plus free local Python tools (rembg cut-outs, librosa beat detection, optional faster-whisper timing). Use this skill whenever the user wants a collage, cut-paper, scrapbook, zine, editorial or Vox-like explainer, a lyric or lyrical video, a kinetic-typography music video, or a "video from my song / my script / my photos" in that look, in any language (Hindi, English, Hinglish, Urdu, ...), even if they never say "collage" or "Remotion".
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
CTF 逆向知识库:14 份方法论技能 + 65 篇可检索条目,纯 Markdown,可被任意 AI 工具加载
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Recursive Language Model (RLM) skill pack for multi-file codebase analysis, featuring workflows for doc generation, refactoring plans, and security audits with shared corpus helpers. Pairs directly with the kamalsoft/vscode-rlm VS Code extension for customizable agent execution across repositories of any size.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
A Claude skill for making animated short films where every frame is drawn in code: stick figures, ink hatching, a cinematic camera and synced sound, rendered to MP4.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Agent skills that make AI coding agents do data science correctly: EDA reports, logged data cleaning and leakage checks, with tested Python helpers
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Agent skills for coding workflows.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Mine repeated DeepSeek Harness prompts into reviewable SKILL.md drafts - deterministic TF-IDF clustering, zero-token mining, never promoted without human approval.
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.
Static text analysis only — does not execute any code and can miss novel or contextual attacks. Not a safety guarantee. Learn more
Spellbook as a Herdr layout: write agent skills with Claude Code beside you
i
This paste-in prompt relies on your agent having real shell/filesystem access to clone the repo and place it itself — it works for agentic CLI/IDE tools like Claude Code, Codex CLI, Gemini CLI, and Cursor's agent mode.
It does not work in non-agentic chat interfaces (plain ChatGPT or Gemini web chat without a persistent sandboxed filesystem) — there's no way for those to actually perform the install.