all publishers

learnprompt

@learnprompt source repo

116 published skills · page 1 of 2

  1. ▌
    Seedance Horror Suspense · learnprompt bundle
    Every shot carries its own timecode and shows one visible change on a body. The dread comes from the chain — a look, veins, a bite, the next person — and the ending seals a door without settling anything. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Horror and suspense; 中文触发词: 恐怖悬疑短片, 恐怖, 悬疑, 惊悚), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  2. ▌
    Seedance Fashion Lookbook · learnprompt bundle
    One person, one look, a handful of places. A head-to-toe appearance lock carries the whole clip, and each scene gets one location, one gesture and one kind of light. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Fashion lookbook and portrait film; 中文触发词: 时尚 lookbook 与人像写真片, 时尚, 穿搭, 人像, 写真), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  3. ▌
    Seedance Travel City Walk · learnprompt bundle
    One traveller moves through a place scene by scene, each scene carrying its own timecode, its own location and one short line. The polish is bought with film grain and golden-hour light. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Cinematic travel vlog montage; 中文触发词: 电影感旅行漫游, 旅拍, 城市漫游, 旅行), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  4. ▌
    Seedance Epic Fantasy Scifi · learnprompt bundle
    Monsters, dragons, world reveals. Each entity gets its own definition block, the shots are cut by timecode, and scale is bought with reference objects and low angles rather than words like massive. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Epic fantasy and sci-fi spectacle; 中文触发词: 奇幻科幻大场面, 奇幻, 科幻, 巨龙, 怪兽, 史诗), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  5. ▌
    Seedance Game UI Livestream · learnprompt bundle
    The screen itself is the shot: a fake gameplay capture, livestream or desktop recording. It holds up when the overlay layer is pinned to fixed positions and its numbers and banners change in step with the action. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Gameplay capture with HUD and stream overlay; 中文触发词: 游戏实机录屏与直播叠层, 游戏录屏, 实机, 直播, HUD, UI 动效), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  6. ▌
    Seedance Production Workflow · learnprompt bundle
    Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt.
    129 repo stars
  7. ▌
    Seedance Retro Dv Home Video · learnprompt bundle
    The period feel comes from camera defects and one tiny everyday incident. Write the camcorder's autofocus hunting, exposure shifts and handheld shake as an explicit list, keep the story small, and the clip reads as a real old tape. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Early-2000s DV home video; 中文触发词: 早年 DV 家庭录像, DV, 家庭录像, VHS, 复古, 年代感), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  8. ▌
    Seedance Storyboard Grid To Video · learnprompt bundle
    Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has to connect the panels. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Storyboard grid to video; 中文触发词: 分镜网格转视频, 分镜图, 九宫格, 故事板), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  9. ▌
    Seedance Food Asmr · learnprompt bundle
    Cooking close-ups, mukbang and eating vlogs. They work when every beat shows one visible change in the food and one matching sound, and the dish stays the same dish from first frame to last. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Food close-ups and eating ASMR; 中文触发词: 美食特写与吃播 ASMR, 美食, 吃播, ASMR, 烹饪), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  10. ▌
    Seedance 3d Cartoon · learnprompt bundle
    One small anthropomorphic character carries the whole film. Spell out its looks part by part, write the style as render settings you can measure, and cut the timeline so each block holds a single action goal. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short; 中文触发词: 3D 卡通角色短片, 3D 卡通, 皮克斯, 黏土, 卡通角色), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  11. ▌
    Seedance Pet Animal · learnprompt bundle
    The animal is the lead and a phone is the only camera. Lock the count to exactly one, keep the animal behaving like an animal, and let the payoff come from it closing in on the lens. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Pets and animals as the lead; 中文触发词: 宠物动物当主角, 宠物, 猫, 狗, 动物), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  12. ▌
    Seedance Car Vehicle · learnprompt bundle
    The machine has to stay one machine while the camera does all the work. Lock the vehicle part by part, then fill the runtime with a numbered cut list that moves the camera every second. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Cars and vehicles at speed; 中文触发词: 汽车与载具速度片, 汽车, 赛车, 摩托, 载具), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  13. ▌
    Seedance Meme Comedy · learnprompt bundle
    A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Twist-ending comedy skit; 中文触发词: 反转结尾搞笑短片, 搞笑, 反转, 梗, 沙雕), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  14. ▌
    Seedance Sports Extreme · learnprompt bundle
    The clip lives or dies on the action loop. Write every link from run-up to landing in order, name the physics you want by part, and spend the negative list on flying, hovering and teleporting. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Sports and extreme stunts; 中文触发词: 体育与极限运动, 体育, 极限运动, 跑酷, 滑板), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
    129 repo stars
  15. ▌
    Carl Motion · learnprompt bundle
    29 motion-graphics styles (paper collage, synthwave, ink wash, woodcut, point cloud, claymation, risograph, glassmorphism, blueprint, pixel game, particles, HUD and more), each with a tested prompt, known failure points and a status; 20 ship the engine that rendered an 8-second example, plus a delivery gate that checks the clip. Use when the user wants an animated clip, explainer or motion graphic in a named visual style, asks which style fits a topic, wants to restyle an animation, or says carl-motion / 动效画风 / 画风盘点 / 用某某画风做动画.
    129 repo stars
  16. ▌
    Seedance Prompt Library · learnprompt bundle
    Verified prompt templates and structures for Seedance 2.5 / 2.0 video generation, distilled from the highest-performing published cases on goodcase.ai. Use when the user asks to write, revise, or review a Seedance video prompt, or asks how to prompt Seedance for a specific kind of shot (narrative short, ad/commercial, UGC talk-to-camera, dialogue with lip-sync, action, product reveal, and similar). Also use when the user names Seedance, 即梦视频, or Seedance 2.5/2.0 directly.
    129 repo stars
  17. ▌
    Learnprompt Single Mdx 2 · learnprompt bundle
    Create or rewrite exactly one LearnPrompt Starlight MDX tutorial to the repository's golden-sample standard, with bottom-of-page auditable sources instead of SourceCard, a research pack, evidence ledger, reproducible showcase, independent review, quality score, and successful site build. Use for one LearnPrompt article, tutorial, chapter, or MDX page; in batch goals, invoke once per topic in an isolated task.
    129 repo stars
  18. ▌
    Frontmatter Repair 2 · learnprompt bundle
    Repair synthetic MDX frontmatter when title, description, or sidebar.order drift from the frontmatter contract. Use for files that follow the same observable patterns proven in the receipts; do not use on private transcripts, secret-bearing material, or arbitrary YAML.
    129 repo stars
  19. ▌
    Idea King · learnprompt bundle
    点子王 (Idea King) — reason from first principles & run adversarial review. A thinking partner for the Partner (搭子) workflow and for standalone use. Use when the user says "点子王", "idea king", "第一性原理", "从第一性原理出发", "奥卡姆剃刀", "墨菲定律", "科斯定理", "对抗式审查", "挑战这个方案", "attack this plan", "盘问", "grill this plan", or when a plan / architecture / work split needs to be stress-tested before execution. Partner Direction B calls this skill on every division-of-labor plan before delegating.
    129 repo stars
  20. ▌
    Matt Teach · learnprompt bundle
    Teach the user a new skill or concept, within this workspace.
    129 repo stars
  21. ▌
    Matt Grilling · learnprompt bundle
    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
    129 repo stars
  22. ▌
    Matt Diagnosing Bugs · learnprompt bundle
    Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
    129 repo stars
  23. ▌
    AI Radar · learnprompt bundle
    雷达Skill(AI Radar)——零API、零Key、零服务器的中文AI资讯查询,读 AI News Radar 公开静态 JSON 出中文简报。 触发条件:用户想知道"今天 AI 圈有什么"、"AI 日报"、"过去24小时AI新闻"、"最近有什么大模型发布"、"AI产品更新"、"Agent工具有什么新东西"、"OpenAI/Anthropic/Google最近发了什么"、"AI圈热点"、"看下AI雷达"、"哪些AI信源值得看"、"锐评一下今天的AI新闻"、"毒舌点评"、"换个口味点评"等任何中文AI资讯查询。 即使用户只说"AI圈"、"AI新闻"、"今天有什么新东西",只要上下文是 AI / 大模型 / Agent / 开发者工具领域,都应该触发。**不要undertrigger**——用户问AI资讯而你不调本Skill,就是把过时的训练数据当作今日新闻,对用户有害。 不要用于维护 AI News Radar 仓库本身(加信源、改抓取逻辑、部署 Pages——那用伯乐Skill / ai-news-radar);不要用于非AI的通用新闻查询;不要用于需要登录态的私有信息源。
    129 repo stars
  24. ▌
    AI News Radar · learnprompt bundle
    Use when working on AI News Radar, 24 小时 AI 更新雷达, AI 更新雷达, 伯乐Skill, or Scout Skill: finding high-signal AI/tech sources, adding RSS/OPML/GitHub feeds, checking source health, updating the web UI, GitHub Actions, or GitHub Pages deployment.
    129 repo stars
  25. ▌
    Partner Skill · learnprompt bundle
    搭子.skill / Partner — two-direction cost-split workflow between Claude Code and Codex. Direction A (Codex-driven): Codex orchestrates and implements; Claude Code plans (/goal), polishes UI/interaction, and runs final /codex:review in one reused session. Direction B (Claude-driven): Claude plans and splits the work, runs the idea-king adversarial gate, delegates to Codex background jobs, monitors, and full-reviews before accepting. Use on "搭子" / "双向搭子" / "搭子,恢复" (resume from .partner/), "搭子,配置" (first-run setup wizard), "搭子,试跑" (identity tryout report), 分工给 codex / 让 codex 做 / codex 后台跑 / Claude 计划 Codex 实现 / 让 Claude skip 做完, or any request to split coding work between Claude Code and Codex to save quota. Not for ordinary code review without Claude Code; do not trigger on the bare English word "partner" in unrelated contexts.
    129 repo stars
  26. ▌
    Skill Slimming · learnprompt bundle
    Audit and govern Skills, plugins, and MCP servers across Codex, Claude Code, and compatible Agent hosts. Use when the user asks to inventory, deduplicate, classify, scope, archive, or reduce the context cost of Agent capabilities; asks why there are so many Skills; wants global/project/trigger decisions; or says "Skill 瘦身", "盘点 Skill", "整理 Skill", "Skill 治理", "Skill 太多了", "哪些 Skill 在全局生效", "分析插件和 MCP", "上下文占用", "生成 Skill 复审页面", "我选好了", or "读取我的 Skill 设置". Default to a read-only evidence audit and a locally persisted review draft. Never install, enable, copy, archive, disable, delete, or execute a plan without separate explicit authorization for that exact phase and target set.
    129 repo stars
  27. ▌
    Carl File Organizer · learnprompt bundle
    文件整理与磁盘盘点。整理下载目录或任意散乱文件夹时,先只读扫出方案,逐项写人话说明,用户在网页上点头才动,动过的能撤。整机盘点时只读扫出空间去向,按绿黄红三色分级,绿的可清,黄的你看一眼,红的别动。用户说「整理下载目录」「收拾一下 Downloads」「下载文件夹太乱了」「帮我归档文件」「整理一下这个文件夹」「磁盘满了」「看看存储」「C 盘满了」「清理一下磁盘」「看下电脑空间」「organize my downloads」「tidy this folder」「clean up my downloads」「disk is full」「storage analysis」「free up space」时使用。全程只读,任何移动、进废纸篓或删除都由用户在页面上点按钮并二次确认,Agent 永远不自己动文件。
    129 repo stars
  28. ▌
    Wechat Article Video Download · learnprompt bundle
    Download a specified video from a public WeChat Official Account article and verify the saved MP4. Use when the user provides an mp.weixin.qq.com article URL and asks to save, extract, grab, or download the first or Nth embedded article video. Do not use for Channels livestreams, login-only media, DRM, encrypted streams, or requests to bypass access controls.
    129 repo stars
  29. ▌
    Kairos Lite · learnprompt bundle
    Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.
    129 repo stars
  30. ▌
    Dream Memory · learnprompt bundle
    Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
    129 repo stars
  31. ▌
    Memory Extractor · learnprompt bundle
    Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
    129 repo stars
  32. ▌
    Swarm Coordinator · learnprompt bundle
    Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.
    129 repo stars
  33. ▌
    Verification Gate · learnprompt bundle
    Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
    129 repo stars
  34. ▌
    Structured Context Compressor · learnprompt bundle
    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.
    129 repo stars
  35. ▌
    Learnprompt Single Mdx · learnprompt bundle
    Create or rewrite exactly one LearnPrompt Starlight MDX tutorial to the repository's golden-sample standard, with bottom-of-page auditable sources instead of SourceCard, a research pack, evidence ledger, reproducible showcase, independent review, quality score, and successful site build. Use for one LearnPrompt article, tutorial, chapter, or MDX page; in batch goals, invoke once per topic in an isolated task.
    129 repo stars
  36. ▌
    Link To Obsidian · learnprompt
    Save a shared web link as a clean Obsidian note. Use when the user gives a URL and asks to save, clip, or archive it into their Obsidian vault as a markdown note with title, source, and summary.
    129 repo stars
  37. ▌
    Release Brief · learnprompt
    从一个 issue 和一段 diff 生成结构化发布摘要,固化“读 issue → 读 diff → 归类改动 → 评估风险 → 写验证步骤”的重复工作流。
    129 repo stars
  38. ▌
    Frontmatter Repair · learnprompt bundle
    Repair synthetic MDX frontmatter when title, description, or sidebar.order drift from the frontmatter contract. Use for files that follow the same observable patterns proven in the receipts; do not use on private transcripts, secret-bearing material, or arbitrary YAML.
    129 repo stars
  39. ▌
    Receipt Renamer · learnprompt bundle
    Prepare a dry-run rename plan for a batch of receipt PDFs. Use when the user wants repository-style receipt filenames normalized under the local naming policy without renaming files yet.
    129 repo stars
  40. ▌
    Release Feed API · learnprompt bundle
    Read a read-only release feed over HTTP, enforce an auditable request contract, and write redacted JSON and Markdown reports. Use when the task is to inspect releases from a REST endpoint without mutating upstream state.
    129 repo stars
  41. ▌
    Docs Migration Pipeline · learnprompt bundle
    Migrate three legacy Markdown docs into Starlight-compatible migration candidates inside an isolated temp repo. Use when you need stage receipts, crash recovery, resume validation, or deterministic candidate packaging without touching real user docs.
    129 repo stars
  42. ▌
    Release Readiness Checklist · learnprompt bundle
    Inspect a small npm CLI release candidate and produce a row-by-row release-readiness checklist report with evidence, pass rules, severity, N/A policy, and a final gate. Use when the task is to review a release candidate without publishing it.
    129 repo stars
  43. ▌
    Observable Receipt Distiller · learnprompt bundle
    Distill a candidate skill from observable repair receipts, then prove it on holdout fixtures. Use when you have repeated accepted patches, corrections, and validator results, but do not have permission to use private transcripts or hidden chain-of-thought.
    129 repo stars
  44. ▌
    Karpathy LLM Wiki · learnprompt
    Build and maintain an LLM-powered personal knowledge base or wiki. Use this skill when the user wants to organize research notes, build a second brain, set up an Obsidian vault with LLM compilation, ingest papers or articles automatically, or mentions "personal knowledge base", "LLM wiki", "second brain", "knowledge management", "ingest papers", "obsidian + LLM". Based on Karpathy Gist and 59k-like post.
    129 repo stars
  45. ▌
    Karpathy Idea Files · learnprompt
    Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement. Use this skill when the user wants to capture a new idea quickly, needs to write a project spec for an agent to implement, wants to share a concept without building it first, or says "write up this idea", "create a spec", "gist this", "idea file", "agent can implement this", "brief for this project". Based on Karpathy 27k-like LLM Wiki Gist post and GitHub repo.
    129 repo stars
  46. ▌
    Karpathy Minimalism · learnprompt
    Apply Karpathy-style minimalism and anti-dependency principles to code and system design. Use this skill when the user wants to reduce dependencies, avoid supply chain risks, rewrite something in pure Python or minimal code, audit a project for bloat, design agent-native CLI tools, or says "too many dependencies", "minimize deps", "pure python", "yoink this", "vibe code this", "no frameworks", "agent-native design". Based on 28k-like litellm attack post and 25k-like 243-line GPT post.
    129 repo stars
  47. ▌
    Karpathy Methodology · learnprompt bundle
    Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style thinking, needs guidance on agentic engineering, LLM knowledge bases, minimalist coding, understanding-first principles, or any of the 14 core methodologies distilled from his work. Also triggers on: "karpathy method", "karpathy approach", "karpathy way", "AK style", "like karpathy does", "karpathy principles", or when user asks how Karpathy would approach any programming or AI problem.
    129 repo stars
  48. ▌
    Karpathy Autoresearch · learnprompt
    Set up an autonomous research loop where an agent iterates on experiments, hypotheses, and code on git branches. Use this skill when the user wants to automate ML experiments, set up a research agent that self-improves, needs to run many variations of an experiment without manual intervention, or says "automate experiments", "agent research loop", "self-improving agent", "run hyperparameter search", "autoresearch". Based on Karpathy 28k-like AutoResearch post.
    129 repo stars
  49. ▌
    Karpathy LLM Simulator · learnprompt
    Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Use this skill when the user needs to make an important decision, wants to stress-test an idea, needs devil's advocate analysis, wants to avoid confirmation bias, or says "argue against this", "what are the counterarguments", "simulate experts", "debate this", "challenge my thinking". Based on Karpathy 31k-like post.
    129 repo stars
  50. ▌
    Karpathy Education First · learnprompt
    Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners. Use this skill when the user wants to explain a project to beginners, create a tutorial from code, write documentation that teaches (not just documents), make a concept accessible, or says "make this teachable", "explain like im a beginner", "nano project version", "teaching version", "explain from scratch", "blog post about this". Based on Karpathy 243-line GPT and Eureka Labs posts.
    129 repo stars
  51. ▌
    Karpathy Meta Reflection · learnprompt
    Run a structured reflection on how AI is reshaping your skills, career, and leverage. Use this skill for monthly career audits, skill atrophy reviews, understanding what's worth learning vs delegating to AI, or when the user says "career audit", "skills review", "what should I learn", "am I becoming obsolete", "AI impact on my work", "leverage review", "meta reflection". Based on Karpathy 56k-like programmer identity post.
    129 repo stars
  52. ▌
    Karpathy Vibe To Agentic · learnprompt
    Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). Use this skill when the user has a rough prototype and wants to level it up, needs to go from "it kind of works" to production-quality, wants to understand the difference between vibe coding and agentic coding, or says "polish this", "make this production-ready", "level up from prototype", "vibe coded this now what". Based on Karpathy posts 3 and 6.
    129 repo stars
  53. ▌
    Karpathy Output Evolution · learnprompt
    Upgrade LLM outputs from plain text to structured, rendered formats like HTML, Marp slides, or interactive dashboards. Use this skill when the user wants better-formatted output, needs to convert notes into a presentation, wants HTML output from an LLM, needs slides from a document, or says "make this prettier", "render this", "output as HTML", "make slides from this", "structured output", "Marp", "better format". Based on Karpathy 19k-like HTML output post.
    129 repo stars
  54. ▌
    Karpathy Agentic Engineering · learnprompt
    Apply Karpathy-style agentic engineering to any coding or building task. Use this skill when the user wants to set up an agent-driven workflow, needs to write a CLAUDE.md or AGENTS.md, wants to orchestrate agents with clear success criteria, or says things like "agent loop", "let the agent handle it", "agentic coding", "set up agent workflow". Includes the 7-step inner loop from Karpathy claude coding notes.
    129 repo stars
  55. ▌
    Karpathy Understanding First · learnprompt
    Apply the Karpathy understanding-first principle — verify what AI built, own your understanding, map the jagged capability landscape of LLMs. Use this skill when the user has used AI to build something and needs to verify it, wants to audit their own understanding, needs to know where LLMs are reliable vs unreliable, or says "verify this", "do I actually understand this", "what can I trust the AI on", "jagged capabilities", "understanding not outsourcing". Based on 46k-like quote post.
    129 repo stars
  56. ▌
    Karpathy Supply Chain Hygiene · learnprompt
    Apply rigorous supply chain security hygiene to software projects — audit dependencies, detect risks, minimize attack surface. Use this skill when the user wants to audit project dependencies, is concerned about supply chain attacks, wants to set up secure dependency management, needs to review a requirements.txt or package.json, or says "dependency audit", "supply chain risk", "check packages", "secure dependencies", "pin versions", "check pypi". Based on Karpathy 28k-like litellm supply chain post.
    129 repo stars
  57. ▌
    Karpathy Practice Environments · learnprompt
    Build practice environments and evaluation gyms where agents can try, fail, and learn from feedback. Use this skill when the user wants to set up automated evaluation for an agent, needs a sandbox for testing LLM capabilities, wants to build a practice gym for skills, needs an RL-style environment for agent improvement, or says "eval environment", "practice gym", "agent sandbox", "automated testing for agents", "RL environment", "agent eval loop". Based on Karpathy LLM Textbook and environments posts.
    129 repo stars
  58. ▌
    Karpathy System Prompt Learning · learnprompt
    Write explicit strategy into system prompts as a learning mechanism — making LLM behavior more predictable and teachable through prompt-as-textbook approach. Use this skill when the user wants to improve an agent or LLM's performance on a specific task through system prompts, needs to encode a strategy or workflow into a prompt, wants consistent LLM behavior, or says "improve system prompt", "encode this strategy", "prompt engineering", "make agent follow this workflow", "prompt as textbook". Based on Karpathy system prompt learning post.
    129 repo stars
  59. ▌
    Laoyeye · learnprompt bundle
    戒指老爷爷。你把卡住的事跟它说,它先问你,再指一条该用的提示语或 skill 并直接开跑。这是这个仓库全部 24 件的路由。
    129 repo stars
  60. ▌
    Eli5 · learnprompt bundle
    大图小字讲解法提示语原文。用户想快速看懂一个陌生主题、希望图多字少地讲清楚、提到 eli5 或完全不懂某个东西时使用。要图、要一个能打开的页面时用它,只要文字讲清楚就不用它。触发词包括 大图小字、eli5、当我什么都不懂、图文讲解、少量文字讲清楚、我完全不懂给我讲讲、生成一个讲解页面。产出一个大图配少量文字的 HTML 讲解页面。
    129 repo stars
  61. ▌
    Kaz Leader · learnprompt bundle
    把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研,再一次性提问(≤5 个),产出一份 ≤4000 字符、直接粘进 /goal 就能跑的任务书,含实测数字、白名单地界、防作弊验收和断点续跑。执行型与探索型(调研/选型/找方案)自动分流。
    129 repo stars
  62. ▌
    Parable · learnprompt bundle
    寓言故事提示语原文,帮你理解并记住一个概念,最后带两道检验题。用户看了几遍还是不懂、别人解释过还是没听懂、直接解释已经失败过时使用。触发词包括 用寓言讲讲、讲个故事帮我理解、给我打个比方、寓言、5 分钟搞懂、看了几遍还是不懂、别人解释过我没听懂、直接解释失败过。产出一则不点破概念的寓言,加概念解析,再加两道检验题。原始思路来自 Anthropic 的 Amanda Askell。
    129 repo stars
  63. ▌
    Fact Check · learnprompt bundle
    事实核查提示语原文。用户想核实一个说法、观点、结论、数据或方案是否成立时使用。触发词包括 事实核查、帮我核查、这是真的吗、查证一下、有没有幻觉、这个数据靠谱吗、审查这个观点、fact check。需要联网核查,产出五档可信度标注和推理链漏洞。
    129 repo stars
  64. ▌
    Johari Window · learnprompt bundle
    乔哈里视窗协作提示语原文。用户想设定 AI 的协作方式、抱怨回答不贴需求、嫌追问太多或不问就猜、希望先判断信息状态再回应时使用。触发词包括 乔哈里、视窗、开放区、盲区、隐藏区、未知区、协作模式、别猜我的需求、先搞清楚再答。整段挂在会话或任务开头,约束之后的全部协作。
    129 repo stars
  65. ▌
    Kaz Neat Freak · learnprompt bundle
    Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.
    129 repo stars
  66. ▌
    Expert Panel · learnprompt bundle
    专家会诊提示语原文。用户的问题需要多个互补专业视角配合、单一视角给不出好方案时使用。触发词包括 专家会诊、多个视角看看、找几个专家、多学科分析、组个专家团、让他们互相质疑。产出三种互补视角的分歧点和综合方案,含适用条件、最大风险、退出条件。
    129 repo stars
  67. ▌
    No Fluff Output · learnprompt bundle
    直给输出法提示语原文。用户抱怨 AI 说话啰嗦绕圈子、想要更直接可执行的回答、看长篇容易走神时使用。触发词包括 别废话、直接说重点、说结论、别绕弯子、有话直说、别来虚的、先说怎么做、拒绝废话、ADHD 友好、专注力不够。整段挂在会话开头,约束之后所有回答的结构,说恢复正常模式才关掉。
    129 repo stars
  68. ▌
    Carl Idea King · learnprompt bundle
    点子王 (Idea King) — reason from first principles & run adversarial review. A thinking partner for the Partner (搭子) workflow and for standalone use. Use when the user says "点子王", "idea king", "第一性原理", "从第一性原理出发", "奥卡姆剃刀", "墨菲定律", "科斯定理", "对抗式审查", "挑战这个方案", "attack this plan", "盘问", "grill this plan", or when a plan / architecture / work split needs to be stress-tested before execution. Partner Direction B calls this skill on every division-of-labor plan before delegating.
    129 repo stars
  69. ▌
    Socratic Inquiry · learnprompt bundle
    苏格拉底式问诊提示语原文。用户说不清自己到底想问什么、问题一团乱、想先把问题问清楚再动手时使用。触发词包括 苏格拉底、苏格拉底式提问、帮我问诊、帮我理清问题、我不知道该问什么、先别给建议、我到底想问什么。一次只问一个问题,最多六问,最后产出一个真正值得回答的新问题。
    129 repo stars
  70. ▌
    Memory Parable · learnprompt bundle
    记忆寓言提示语原文,重点是记住,理解交给别的,寓言讲完还会逐个隐喻对应,无聊的时候拿来消遣也合适。用户想用故事记住一个抽象或陌生的概念,或者只是无聊想让 AI 讲个有意思的东西时使用。触发词包括 记忆寓言、用故事帮我记、别让我背概念、研究生水平的概念、无聊的时候讲个故事、Amanda Askell 那个提示词。产出一则不点破概念的寓言,再解释概念和寓言里每个隐喻的对应关系。
    129 repo stars
  71. ▌
    First Principles · learnprompt bundle
    第一性原理提示语原文。用户的方案在反复打补丁、陷入路径依赖、想回到问题本质重新推导时使用。触发词包括 第一性原理、回到本质、从头推一遍、别打补丁了、推倒重来、这么做的根本原因是什么。产出原方案里只在修补表面的部分,加一条重新推导的新路径和验证第一步。适合你自己读自己想,不需要 Agent 代跑流程。要的是让人挑毛病、拆台,用 carl-idea-king。
    129 repo stars
  72. ▌
    Reverse Teardown · learnprompt bundle
    反向拆解提示语原文。用户看到一个优秀的产品、网页、方案、流程、数据看板或作品,想学会它为什么有效时使用。触发词包括 反向拆解、拆解这个、它为什么做得好、我想模仿、逆向拆解、拆解这个好范例、这个牛在哪。产出可复用规律加一份操作清单。只拆做得好的,项目黄了、上线炸了这种失败复盘不用它。
    129 repo stars
  73. ▌
    Two Layer Explain · learnprompt bundle
    双层解释法提示语原文。用户遇到听不懂的概念、名词、报错、技术栈,想要一次讲透时使用。触发词包括 双层解释、小白版、专业版、通俗讲一遍、把我当小白、这个概念是什么意思、讲讲什么是、贴着代码或文档问、这个报错什么意思、马上就要用。产出小白解释加专业解释,附术语对照表和自测题。
    129 repo stars
  74. ▌
    Life Design · learnprompt bundle
    人生设计术提示语原文。基于斯坦福人生设计方法,用户想看清现在的位置、分清重力问题和可设计的真问题、规划未来五年时使用。这是一次多轮深度对话,六到九个主问题,最后产出八千到一万两千字的个人人生设计蓝图和三个奥德赛计划。
    129 repo stars
  75. ▌
    Minimum Experiment · learnprompt bundle
    最小实验提示语原文。用户纠结的事情靠继续想已经不会更清楚、需要用现实反馈来验证时使用。触发词包括 最小实验、先试试、怎么验证、别空想了、跑个实验、小成本试错、七天验证、已经反复纠结过很多轮、想了很久还是选不出来。产出待验证假设、一个低成本可逆实验的完整设计,以及明天就能做的第一个动作。
    129 repo stars
  76. ▌
    Cross Domain Borrow · learnprompt bundle
    跨领域借解提示语原文。用户在本行业里想不出解法、需要从其他领域借鉴机制时使用。触发词包括 跨领域、别的行业怎么解决、换个视角、类比一下、借鉴其他领域、有没有类似的问题被解决过。产出至少三个远距离领域的同构案例和可迁移机制。
    129 repo stars
  77. ▌
    Steelman Both Sides · learnprompt bundle
    双向钢人论证提示语原文。用户在两个选项之间犹豫不决、需要做决策时使用。触发词包括 钢人、双向钢人、steelman、两个选项选哪个、帮我做个决定、正反两面都说最强理由、我该选 A 还是 B。产出两边的最强论证、真正分歧、关键变量,再问一个最可能改变结论的问题。
    129 repo stars
  78. ▌
    Hidden Talent · learnprompt bundle
    深度天赋挖掘提示语原文。用户想找到自己被忽视或压抑的天赋、怀疑自己没有天赋、想要一份个人天赋使用说明书时使用。这是一次半小时以上的多轮深度对话,一次只问一个问题,最多十个主问题,最后产出一万字左右的说明书。
    129 repo stars
  79. ▌
    Horizontal Vertical Analysis · learnprompt bundle
    横纵分析法提示语原文。用户想深度研究一个陌生的产品、公司、人物、技术、行业或事件时使用。触发词包括 横纵分析、深度研究、帮我搞懂这家公司、研究一下这个赛道、写份研究报告、纵向历史横向对比、deep research。建议搭配深度研究或联网能力跑,产出一万到三万字可追溯报告。
    129 repo stars
  80. ▌
    Goodcase · learnprompt bundle
    goodcase.ai(好案例)AI 爆款案例与 Prompt 查询 Skill。当用户想找"AI 爆款案例"、"好 case"、"这类图怎么做的"、"这种视频怎么生成的"、"找个 XX 的 prompt"、"有没有现成的提示词"、"Veo 案例"、"即梦案例"、"Midjourney 案例"、"Kling / 可灵案例"、"Seedance 案例"、"GPT Image 案例"、"AI 图像案例"、"AI 视频案例"、"AI 编程 UI 案例"、"AI 文案案例"、"爆款 prompt"、"复刻这个效果"、"这个效果的提示词"、"AI case"、"viral AI examples"、"AI prompt examples"、"how was this AI image/video made"、"find me a prompt for X" 等任何 AI 创作案例/提示词查询时使用。即使用户只说"有什么好玩的 AI 案例"、"给我找个能抄的 prompt"、"最近什么 AI 图很火",也应该触发本 Skill。也用于"用 goodcase 测一下 XX 模型"、"抽几个案例评测模型"、"新模型出了跑一下 goodcase 题"、"benchmark this model with goodcase" 等模型评测场景。Skill 直接 curl 公开 REST API 拉真实案例数据(含完整 Prompt、稳定分、成本档),不需要任何 API Key。**宁可多触发**——用户问 AI 创作案例而你凭训练数据编一个,等于给用户假案例假 Prompt,对用户有害。
    129 repo stars
  81. ▌
    Pov Vlog Presence · learnprompt bundle
    Apply the POV and vlog presence workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  82. ▌
    Web 3d Motion Hero · learnprompt bundle
    Apply the 3D and motion hero workflow derived from multiple published GoodCase examples. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  83. ▌
    Product Studio Visual · learnprompt bundle
    Apply the Product studio visual workflow derived from multiple published GoodCase examples. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  84. ▌
    Product Ad Shot Design · learnprompt bundle
    Apply the Product ad shot design workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  85. ▌
    Animation Style Consistency · learnprompt bundle
    Apply the Animation style and character consistency workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  86. ▌
    Character Style Consistency · learnprompt bundle
    Apply the Character and style consistency workflow derived from multiple published GoodCase examples. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  87. ▌
    Portfolio Story Architecture · learnprompt bundle
    Apply the Portfolio story architecture workflow derived from multiple published GoodCase examples. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  88. ▌
    Poster Information Hierarchy · learnprompt bundle
    Apply the Poster information hierarchy workflow derived from multiple published GoodCase examples. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  89. ▌
    Process Transformation Story · learnprompt bundle
    Apply the Process and transformation story workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  90. ▌
    Web 3d Motion Hero By 197q59i · learnprompt bundle
    Apply an evidence-derived 3D and motion hero workflow observed across published GoodCase examples by viktoroddy. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  91. ▌
    Action Continuity Choreography · learnprompt bundle
    Apply the Action continuity choreography workflow derived from multiple published GoodCase examples. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  92. ▌
    Editorial Portrait Composition · learnprompt bundle
    Apply the Editorial portrait composition workflow derived from multiple published GoodCase examples. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  93. ▌
    Product Commerce Conversion Page · learnprompt bundle
    Apply the Product and commerce conversion page workflow derived from multiple published GoodCase examples. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  94. ▌
    Product Ad Shot Design By 1ktgmlf · learnprompt bundle
    Apply an evidence-derived Product ad shot design workflow observed across published GoodCase examples by Synthia. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  95. ▌
    Landing Page Information Structure · learnprompt bundle
    Apply the Landing-page information structure workflow derived from multiple published GoodCase examples. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. Read the bundled Case evidence before producing an artifact.
    129 repo stars
  96. ▌
    Animation Style Consistency By 1diwzmp · learnprompt bundle
    Apply an evidence-derived Animation style and character consistency workflow observed across published GoodCase examples by NoorAI. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  97. ▌
    Character Style Consistency By 1ronuwr · learnprompt bundle
    Apply an evidence-derived Character and style consistency workflow observed across published GoodCase examples by のぞむ*AIイラスト. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  98. ▌
    Portfolio Story Architecture By 13qd91c · learnprompt bundle
    Apply an evidence-derived Portfolio story architecture workflow observed across published GoodCase examples by shushant_l. Use when planning, designing, or implementing a website in this interface pattern, including requests for 网页, 落地页, 作品集, 3D hero, SaaS, ecommerce, or UI structure. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  99. ▌
    Poster Information Hierarchy By 1feqfhp · learnprompt bundle
    Apply an evidence-derived Poster information hierarchy workflow observed across published GoodCase examples by 小小东. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars
  100. ▌
    Editorial Portrait Composition By S8wxu9 · learnprompt bundle
    Apply an evidence-derived Editorial portrait composition workflow observed across published GoodCase examples by Taaruk. Use when planning, writing, or refining an AI image prompt in this visual pattern, including requests for 图片提示词, 海报, 肖像, 产品图, or character consistency. This is an unofficial synthesis and must preserve source attribution.
    129 repo stars