GitHub user
Agent skills by LearnPrompt
- skills
- 44
- repositories
- 7
Repositories by LearnPrompt
- andrej-karpathy-skillsKarpathy-inspired Agent Skills collection106 stars · 15 skills
- awesome-seedance🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 600+ cases traced to original posts, 260+ cross-model retest runs with public verdicts, 25 copy-ready templates, 50+ installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.1.8k stars · 15 skills
- cc-harness-skillsPortable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.236 stars · 6 skills
- LearnPrompt永久免费开源的 AIGC 课程, 目前已支持Claude Code，Codex，Hermes，OpenClaw，Obsidian，Prompt Engineering, ChatGPT, Midjourney, Runway, Stable Diffusion, AI数字人，AI声音&音乐，开源大模型2.7k stars · 4 skills
- ai-news-radar24h AI/tech news radar with GitHub Actions, live web UI, and Scout Skill for AI sources.1.8k stars · 2 skills
- luban-skill鲁班 | Luban — 把'能用的Skill'打磨成'能被装、能传播、能验证、能进化'的公共资产。Agent skill-polishing workshop: 验料·访行·过尺·慢刨·回炉957 stars · 1 skill
- skillrush-townSkillrush Town: daily ClawHub Top100 snapshots and potential AI skill radar109 stars · 1 skill
Skills by LearnPrompt, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 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… | LearnPrompt/ | 2.7k | — | ~1.7k | Automated safety check: Pass | Unknown | 2 days ago |
| 2 | A skill your agent uses 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… | LearnPrompt/ | 1.8k | — | ~2.5k | Automated safety check: Notes | MIT | today |
| 3 | 3.Luban 鲁班（Luban）——Skill打磨工坊。把一个"能用的Skill"打磨成"能被理解、能被安装、能被传播、能被验证、能持续进化"的公共Skill资产。 | LearnPrompt/ | 957 | — | ~3.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 4 | 4.AI Radar 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。 | LearnPrompt/ | 1.8k | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 5 | Repair synthetic MDX frontmatter when title, description, or sidebar.order drift from the frontmatter contract. | LearnPrompt/ | 2.7k | — | ~212 | Automated safety check: Pass | Unknown | 2 days ago |
| 6 | 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. | LearnPrompt/ | 236 | — | ~477 | Automated safety check: Pass | MIT | 2 mo ago |
| 7 | Save a shared web link as a clean Obsidian note. An agent skill from LearnPrompt/LearnPrompt. | LearnPrompt/ | 2.7k | — | ~257 | Automated safety check: Pass | Unknown | 2 days ago |
| 8 | 淘金小镇 | Skillrush Town — 每日 ClawHub Top100 淘金雷达。消费侧触发：用户问「今天 ClawHub 有什么新 skill」「淘金小镇今天有什么」「最近什么 skill 在涨」「有什么潜力 skill 值得装」「ClawHub 榜单」「skill 下载榜 / 增速榜 / 新进榜」时，读取 data/latest.json（或 GitHub Pages… | LearnPrompt/ | 109 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 9 | Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. | LearnPrompt/ | 1.8k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 10 | 10.Kairos Lite 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. | LearnPrompt/ | 236 | — | ~334 | Automated safety check: Pass | MIT | 2 mo ago |
| 11 | Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts. | LearnPrompt/ | 236 | — | ~347 | Automated safety check: Pass | MIT | 2 mo ago |
| 12 | One small anthropomorphic character carries the whole film. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 13 | 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. | LearnPrompt/ | 236 | — | ~327 | Automated safety check: Pass | MIT | 2 mo ago |
| 14 | 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。 | LearnPrompt/ | 2.7k | — | ~179 | Automated safety check: Pass | Unknown | 2 days ago |
| 15 | Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style… | LearnPrompt/ | 106 | — | ~1.5k | Automated safety check: Pass | MIT | 2 mo ago |
| 16 | The machine has to stay one machine while the camera does all the work. | LearnPrompt/ | 1.8k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 17 | Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw… | LearnPrompt/ | 236 | — | ~346 | Automated safety check: Pass | MIT | 2 mo ago |
| 18 | Monsters, dragons, world reveals. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 19 | 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. | LearnPrompt/ | 236 | — | ~302 | Automated safety check: Pass | MIT | 2 mo ago |
| 20 | Apply Karpathy-style agentic engineering to any coding or building task. | LearnPrompt/ | 106 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 21 | One person, one look, a handful of places. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 22 | Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change. | LearnPrompt/ | 106 | — | ~1.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 23 | Cooking close-ups, mukbang and eating vlogs. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 24 | Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners. | LearnPrompt/ | 106 | — | ~1.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 25 | The screen itself is the shot: a fake gameplay capture, livestream or desktop recording. | LearnPrompt/ | 1.8k | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 26 | Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement. | LearnPrompt/ | 106 | — | ~1.5k | Automated safety check: Pass | MIT | 2 mo ago |
| 27 | Every shot carries its own timecode and shows one visible change on a body. | LearnPrompt/ | 1.8k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 28 | Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. | LearnPrompt/ | 106 | — | ~1.3k | Automated safety check: Pass | MIT | 2 mo ago |
| 29 | A short skit where every beat is laid down to serve one punchline. | LearnPrompt/ | 1.8k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 30 | Build and maintain an LLM-powered personal knowledge base or wiki. | LearnPrompt/ | 106 | — | ~1.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 31 | The animal is the lead and a phone is the only camera. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 32 | Run a structured reflection on how AI is reshaping your skills, career, and leverage. | LearnPrompt/ | 106 | — | ~1.5k | Automated safety check: Pass | MIT | 2 mo ago |
| 33 | Verified prompt templates and structures for Seedance 2.5 / 2.0 video generation, distilled from the highest-performing published cases on goodcase.ai. | LearnPrompt/ | 1.8k | — | ~1k | Automated safety check: Pass | MIT | today |
| 34 | Apply Karpathy-style minimalism and anti-dependency principles to code and system design. | LearnPrompt/ | 106 | — | ~1.6k | Automated safety check: Pass | MIT | 2 mo ago |
| 35 | The period feel comes from camera defects and one tiny everyday incident. | LearnPrompt/ | 1.8k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 36 | Upgrade LLM outputs from plain text to structured, rendered formats like HTML, Marp slides, or interactive dashboards. | LearnPrompt/ | 106 | — | ~1.5k | Automated safety check: Pass | MIT | 2 mo ago |
| 37 | The clip lives or dies on the action loop. An agent skill from LearnPrompt/awesome-seedance. | LearnPrompt/ | 1.8k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 38 | Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. | LearnPrompt/ | 1.8k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 39 | One traveller moves through a place scene by scene, each scene carrying its own timecode, its own location and one short line. | LearnPrompt/ | 1.8k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 40 | Build practice environments and evaluation gyms where agents can try, fail, and learn from feedback. | LearnPrompt/ | 106 | — | ~2.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 41 | Apply rigorous supply chain security hygiene to software projects — audit dependencies, detect risks, minimize attack surface. | LearnPrompt/ | 106 | — | ~1.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 42 | Write explicit strategy into system prompts as a learning mechanism — making LLM behavior more predictable and teachable through prompt-as-textbook approach. | LearnPrompt/ | 106 | — | ~1.9k | Automated safety check: Pass | MIT | 2 mo ago |
| 43 | Apply the Karpathy understanding-first principle — verify what AI built, own your understanding, map the jagged capability landscape of LLMs. | LearnPrompt/ | 106 | — | ~1.6k | Automated safety check: Pass | MIT | 2 mo ago |
| 44 | Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). | LearnPrompt/ | 106 | — | ~1.4k | Automated safety check: Pass | MIT | 2 mo ago |
Questions, answered from the data.
What is the best skill by LearnPrompt?
Learnprompt Single Mdx from LearnPrompt/LearnPrompt ranks first of the 44 skills by LearnPrompt listed here, with the highest score: its repository has 2.7k GitHub stars, its SKILL.md loads about 1.7k tokens and it passes the automated safety check with no findings. Next come AI News Radar and Luban.
Are LearnPrompt's skills official?
None yet. All 44 skills by LearnPrompt listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.