Search
AI & LLM Engineering · For marketers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity… | AgriciDaniel/ | 2.3k | 1 repo | ~3.3k | Automated safety check: Notes | MIT | 2 days ago |
| 2 | 口播稿,适用于 AI 技术科普、Agent/Skill/RAG、LLM 等底层原理讲解,以及面试题拆解、工具实测、热点普及。支持两种用法:给定主题从零产出口播稿、对已有口播稿进行优化。触发关键词包括:口播、口播稿、video script。 | itwanger/ | 18k | — | ~2.2k | Automated safety check: Pass | No licence | yesterday |
| 3 | Edits, updates, rewrites, or adds content on the ComfyUI template site pages. | Comfy-Org/ | 1.3k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 4 | 4.Bench mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette. | ddalcu/ | 1.8k | 1 repo | ~1.1k | Automated safety check: Pass | Unknown | today |
| 5 | Turn llmprobe reports into the charts a perf PR embeds (one line per arm across context size, every point labelled, machine and model in the caption) and host them so the PR body renders them. | ddalcu/ | 1.8k | — | ~594 | Automated safety check: Pass | Unknown | today |
| 6 | Agnes AI API 接入支持与问题排查 Skill。帮助新用户完成 Agnes AI API 的接入配置, 诊断和解决接入过程中遇到的认证、参数、响应、图像生成、视频生成等各类问题。 | lj1270998580-crypto/ | 305 | — | ~14k | Automated safety check: Notes | No licence | 18 days ago |
| 7 | Run local black-box voice tests against the physical Dotty robot by playing a TTS prompt through the workstation speakers while the C920 records video and room audio. | BrettKinny/ | 113 | — | ~866 | Automated safety check: Notes | MIT | 5 days ago |
| 8 | Audit and optimize frontmatter description fields across documentation pages to keep them concise and token-efficient. | lynx-family/ | 130 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review. | harryvondiesel-web/ | 133 | — | ~2.8k | Automated safety check: Pass | MIT | 4 days ago |
| 10 | 10.Geo Run Run a full GEO analysis — guides you through setup, brand research, query generation, execution, analysis, and reporting | onvoyage-ai/ | 384 | — | ~1.3k | Automated safety check: Notes | MIT | 7 mo ago |
| 11 | 11.Explore Run Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. | lllllllama/ | 497 | 1 repo | ~833 | Automated safety check: Pass | MIT | 18 days ago |
| 12 | A skill your agent uses when a FLUX 3 video must be built from supplied images or video. | black-forest-labs/ | 128 | — | ~827 | Automated safety check: Pass | MIT | 1 mo ago |
| 13 | Diagnose and fix video/image color OBJECTIVELY with the getimage (action:"analyzecolor") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a… | artokun/ | 803 | — | ~2.4k | Automated safety check: Pass | MIT | 6 days ago |
| 14 | 14.Music Generate full songs with vocals or instrumentals (ACE-Step) and sound effects or ambience (Stable Audio Open) on the user's GPU through Guaardvark's Audio Foundry. | guaardvark/ | 258 | — | ~710 | Automated safety check: Pass | MIT | today |
| 15 | 기업 분석 스킬. An agent skill from thesun4sky/jobstack. | thesun4sky/ | 156 | — | ~2.9k | Automated safety check: Notes | MIT | 1 mo ago |
| 16 | The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's… | oxbshw/ | 470 | — | ~599 | Automated safety check: Notes | MIT | 26 days ago |
| 17 | Design and run product experiments at a practical PM level — A/B tests, hypothesis tests, rollouts, feature flags, and reading results without pretending to be a statistician. | andreaskelm/ | 234 | — | ~2.3k | Automated safety check: Pass | Unknown | 2 days ago |
| 18 | Diagnose and draft Amazon Canada apparel advertising plans with lifecycle and seasonal timing, English/French search coverage, account evidence, profitability guardrails, and approval-ready… | xjli360/ | 251 | — | ~1.2k | Automated safety check: Pass | MIT | 13 days ago |
| 19 | A skill your agent uses when diagnosing a FLUX 3 brief before generation. | black-forest-labs/ | 128 | — | ~904 | Automated safety check: Pass | MIT | 1 mo ago |
| 20 | A skill your agent uses when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in… | aaron-he-zhu/ | 2.9k | 2 repos | ~3.5k | Automated safety check: Pass | Apache-2.0 | today |
| 21 | arkcli +deploy:普通创建推理接入点(Endpoint)的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里;但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外,必须改走 arkcli-infer-endpoint,不能由本 skill… | volcengine/ | 140 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 22 | Maintain the Phoenix llms.txt documentation index at docs/phoenix/llms.txt — the machine-readable docs map used by AI agents and the px docs fetch CLI. | Arize-ai/ | 12k | — | ~2.3k | Automated safety check: Pass | Unknown | yesterday |
| 23 | 23.Storytelling Build multi-shot narrative image, video, and audio workflows with genmedia. | fal-ai-community/ | 251 | — | ~1.4k | Automated safety check: Pass | No licence | 12 days ago |
| 24 | Transcribe local audio/video and Apple Voice Memos quickly with cached MLX Whisper models, including bad/low-quality audio. | mitsuhiko/ | 3.2k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 25 | Transcribe audio files to text via POST /audio/transcriptions. | veniceai/ | 144 | — | ~1.7k | Automated safety check: Pass | MIT | 5 days ago |
| 26 | Lingzao lightweight XHS keyword design Skill for Xiaohongshu SEO keywords, final 10 publishing keywords, keyword embedding, title, cover copy, opening lines, and keyword field checks. | atian-create/ | 296 | — | ~345 | Automated safety check: Pass | MIT-0 | 3 mo ago |
| 27 | 27.Flux 3 Video A skill your agent uses when routing a general FLUX 3 video request. | black-forest-labs/ | 128 | — | ~520 | Automated safety check: Pass | MIT | 1 mo ago |
| 28 | How to pick the owning team and the priority for an inbound support ticket, including what to do when a ticket spans two teams. | Kiln-AI/ | 5.2k | — | ~425 | Automated safety check: Pass | Unknown | 2 days ago |
| 29 | A skill your agent uses when the user asks to "design an employee advocacy program", "set up founder-led sharing", or "build a share kit for the team"; produces an advocacy program blueprint in two… | aaron-he-zhu/ | 2.9k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 30 | A skill your agent uses when the user asks to "check if our surfaces have drifted from the canon", "watch for competitor repositioning", or "define when we should reposition"; produces a drift… | aaron-he-zhu/ | 2.9k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 31 | arkcli 推理接入点管理与显式 raw CRUD 创建能力。正向触发:用户明确要求脚本化 / CI / 无护栏 / 原始 raw CRUD 创建 Endpoint 时,必须使用本 skill 的 arkcli infer endpoint create 路径,不能切到 arkcli-deploy;模型缺失或只有品牌/家族名时仍留在本 skill,先执行实时有界候选与 0/1/N… | volcengine/ | 140 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 32 | Transcribe speech to text using Apple's Speech framework. An agent skill from dpearson2699/swift-ios-skills. | dpearson2699/ | 1.2k | — | ~3.7k | Automated safety check: Pass | Unknown | 2 mo ago |
| 33 | 33.Tokenwise Measurement-driven model router for Claude Code. An agent skill from sickn33/agentic-awesome-skills. | sickn33/ | 47k | 1 repo | ~932 | Automated safety check: Pass | MIT | 2 days ago |
| 34 | Direct a three-phase MiniMax H3 first-person FPV flight: take off near the ground inside P1, complete one 360-degree orbit around P1's primary scene subject, then follow the verified P2 red route… | karuvanan/ | 131 | — | ~6.7k | Automated safety check: Pass | Unknown | 2 days ago |
| 35 | 35.Video A skill your agent uses when applies to any page embedding or hosting video content (YouTube, Vimeo, self-hosted). | thedaviddias/ | 74k | — | ~562 | Automated safety check: Pass | MIT | 5 days ago |
| 36 | arkcli 接入向导(workflow):把某个模型接入到自己的应用/服务的端到端引导 —— 从'我想用某模型'到拿到可调用的 Endpoint(+ 可选示例代码)。当用户说'我想在我的 app/服务里用豆包/某模型''怎么把方舟模型接进来''帮我接入 XX 模型''想正式用上某模型'这类不含 deploy/部署关键词、但本质是正式接入的意图时触发。已明确说'部署/创建… | volcengine/ | 140 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 37 | Design 15-45 second MiniMax H3 live-action arcade martial-arts movie scenes with two readable fighters, grounded striking and MMA ground-game choreography, non-repeating multi-Segment action and a… | karuvanan/ | 131 | — | ~12k | Automated safety check: Pass | Unknown | 2 days ago |
| 38 | 38.Stepfun Asr Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking. | daymade/ | 1.4k | — | ~3k | Automated safety check: Pass | MIT | yesterday |
| 39 | 39.Stepfun Tts Generates Chinese/Japanese speech with StepFun's Contextual TTS — default stepaudio-2.5-tts, stepaudio-3-tts for whisper/inline-() prosody. | daymade/ | 1.4k | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 40 | A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. | rampstackco/ | 945 | — | ~7.9k | Automated safety check: Pass | MIT | 4 days ago |
| 41 | Set up and run local web searches using Bright Data SERP API with the unfancy-search pipeline (query expansion, SERP retrieval, RRF reranking). | davila7/ | 33k | — | ~1.2k | Automated safety check: Notes | MIT | yesterday |
| 42 | Grant a user the runtime permissions an activated ITSM agent's actions need so the actions do not fail on permission errors. | forcedotcom/ | 1.1k | — | ~5.4k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 43 | Design high-speed cinematic wuxia blade fights with strict physical continuity, one-armed or asymmetric body mechanics, fixed weapon geometry, cumulative injury, weapon-driven causality, 15-second… | karuvanan/ | 131 | — | ~5.8k | Automated safety check: Pass | Unknown | 2 days ago |
| 44 | Converts one or more images into faithful text descriptions or OCR with the local 1.3B MiniCPM-V 4.6 GGUF model through llama.cpp, automatically preferring an available Vulkan GPU and falling back… | godot-fun/ | 183 | — | ~813 | Automated safety check: Pass | MIT | yesterday |
| 45 | 45.API Models Call nodetool.models from a code action: pick the best configured model for a capability, search for a model the user named, browse a provider's catalog, set a node's model property, or make one… | nodetool-ai/ | 560 | — | ~976 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 46 | 将 Anthropic 官方品牌颜色和字体应用于任何可能需要 Anthropic 视觉风格的作品。适用于品牌颜色或样式指南、视觉格式化或公司设计标准的场景。 | LeastBit/ | 590 | — | ~262 | Automated safety check: Pass | Apache-2.0 | 8 mo ago |
| 47 | Weekly, browser heavy. An agent skill from markfulton/ai-employees. | markfulton/ | 543 | — | ~15k | Automated safety check: Pass | MIT | yesterday |
| 48 | A skill your agent uses when authoring PolicyRuleDefinition and PolicyRuleDefinitionSet metadata XML for Salesforce Data Cloud governance policies, or when editing .policyRuleDefinition /… | forcedotcom/ | 1.1k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | yesterday |