yikart/AiToEarn

Agent skills in the GitHub repository yikart/AiToEarn, each with its code score out of 100.

Let's use AI to Earn!

Repository score

67 / 100 C

Skills

48

Verified

0

Average skill score

63

GitHub stars

27,617

License

MIT

Open yikart/AiToEarn on GitHub

48 skills in this repository

1. diagnose

   Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" /…

   79B
2. tdd

   Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks…

   78B
3. impeccable

   Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend…

   76B
4. byted-mediakit-asr

   Extract speech subtitles from videos via MediaKit MCP. Only for full transcripts, use voice separation followed by Doubao ASR through call-maas-proxy on audio or video. Use for su…

   73B
5. byted-mediakit-audiogen

   Generate audio with Seed Audio through MediaKit MCP. Use for speech, narration, character dialogue, sound effects, ambience, and audio scenes from text, preset voices, reference a…

   73B
6. write-a-skill

   Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

   73B
7. image-edit

   Edit an existing image with deterministic pixel operations via image_edit — rotate, flip, crop (free/ratio/circle), resize, compress/format-convert, adjust brightness/saturation/c…

   71B
8. video-generation

   Generate, edit, or extend videos with Seedance models via list_video_generation_models and generate_video; optimizes prompts per model's conventions. Use when user asks to create,…

   70B
9. grill-with-docs

   Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. U…

   69C
10. analyzing-videos

    Analyzes video content and extracts highlights. Use when user wants to analyze video, extract highlights, create video summary, generate video keywords, understand video content,…

    68C
11. browser-operations

    Drive the user's Cloud Space browser - start or stop the space, navigate, click, type, and extract web content with natural-language actions. Use when the user asks to open a webs…

    68C
12. byted-asset-preparation

    Determine how to make media suitable for a planned use: retain it, extract components, separate mixed sound, remove unsuitable burned-in captions, adapt its format, or source repl…

    68C
13. byted-mediakit-media-understand

    Understand videos, audio and images with MediaKit MCP tools. Use for media summaries, visual event searches, dialogue analysis, sound descriptions, and timestamped evidence for ed…

    68C
14. prototype

    Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several rad…

    68C
15. translating-videos

    Translates videos including subtitles, voice cloning, and lip sync. Use when user wants to translate video, dub video to another language, convert video language, localize video c…

    68C
16. triage

    Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for a…

    68C
17. channel-publish

    Publish content to the user's bound Channel Accounts, schedule or change Publish At, cancel an unfinished Publish Task, or update already published content. Use when the user want…

    67C
18. extracting-thumbnails

    Extracts thumbnails from video URLs. Use when publishing video content that requires a cover image, when the user does not provide a cover/thumbnail, or before publishing to platf…

    67C
19. generating-drama-recaps

    Generates narrated recap videos from short drama clips using AI-powered narration and voice synthesis. Use when user wants to create drama summary, narrated recap, voice-over vide…

    67C
20. to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues,…

    67C
21. design-taste-frontend

    Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look template…

    66C
22. caveman

    Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode",…

    65C
23. byted-audio-continuity

    Check and repair audio continuity after trimming, splitting, reordering, or retiming audible clips, when cuts produce clicks, abrupt noise changes, or distracting gaps, or when so…

    64C
24. setup-matt-pocock-skills

    Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label voca…

    64C
25. byted-mediakit-cloudedit-basic

    Read this skill before using CloudEdit, a cloud-based video editor, to inspect, create, edit, or export video projects. Use it for importing media, trimming or combining clips, ad…

    63C
26. transferring-video-styles

    Converts live-action videos into artistic styles like comic, anime, manga, 3D cartoon. Use when user wants to transform video style, create anime version, apply artistic effects,…

    63C
27. image-creation

    Generate or edit raster images for social posts, product shots, covers, mockups, and variants. Use when the user asks to create, edit, restyle, adapt, or redesign images based on…

    62C
28. composing-videos

    Combines multiple videos/images into a single video with optional background audio. Use when user wants to merge clips, concatenate videos, create slideshow from images, stitch vi…

    61C
29. removing-subtitles

    Removes hardcoded subtitles from videos using AI inpainting. Use when user wants to remove subtitles, erase text from video, clean video from captions, delete burned-in subtitles,…

    61C
30. vercel-react-best-practices

    React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optim…

    61C
31. byted-mediakit-cloudedit-planner

    Turn editing intent and video, audio, or image sources into an evidence-backed, executable CloudEdit plan. Use whenever an edit needs decisions about selection, story, ordering, p…

    60C
32. managing-content

    Manages media files, drafts, and content organization. Use when user needs to upload media, create drafts, organize content, save to library, or manage media groups. 内容管理、媒体管理、保存媒…

    59C
33. crawling-social-media

    Downloads and extracts content from social media platforms. Use when user wants to crawl, download, or extract videos/content from Bilibili, YouTube, TikTok, Douyin, Instagram, Tw…

    58C
34. improve-codebase-architecture

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find ref…

    58C
35. editing-images

    Image editing using Sharp. Supports compositing (QR codes, logos, watermarks), resizing, cropping, rotating, flipping, brightness/contrast/saturation adjustment, blur, sharpen. 图片…

    57C
36. to-prd

    Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

    57C
37. byted-basic-working-principles

    Read before starting or continuing a video creation or editing task: reviewing source material, planning a script or storyboard, preparing visuals, assembling or revising a cut, a…

    56C
38. generating-images

    Generates images using AI models (Gemini). AI图像生成、文生图、生成图片。

    56C
39. generating-videos

    Generates videos using Grok. Supports text-to-video and image-to-video. AI视频生成、文生视频、图生视频。

    56C
40. grill-me

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan,…

    56C
41. editing-videos

    Video editing using Volcengine Track structure. Supports cutting, trimming, adding text, stickers, audio, filters, effects, transitions, multi-clip compositions, speed adjustment,…

    55C
42. imagegen-frontend-web

    Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY se…

    54D
43. 全域内容运营助手

    aitoearn帮你生成文章、短视频、图文与海报，一键分发抖音、快手、小红书、视频号、Facebook、TikTok 等海内外全平台，覆盖起号、涨粉、带货与变现全链路。

    54D
44. aitoearn-growth

    全域内容运营助手（AiToEarn）：生成文章、短视频、图文与海报，并一键分发到抖音、快手、小红书、微信视频号、Facebook、TikTok 等海内外全平台，覆盖起号、涨粉、带货与变现全链路。 当用户想要创作或发布内容、生成/编辑图片、生成/剪辑/续写视频、提取字幕或语音转写、生成配音与音效、多平台一键发布或定时发布、给内容做变现规划时使用此技能。 依赖…

    53D
45. karpathy-guidelines

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

    51D
46. aitoearn

    全域内容运营助手（AiToEarn）：生成文章、短视频、图文与海报，并一键分发到抖音、快手、小红书、微信视频号、Facebook、TikTok 等海内外全平台，覆盖起号、涨粉、带货与变现全链路。 当用户想要创作或发布内容、生成/编辑图片、生成/剪辑/续写视频、提取字幕或语音转写、生成配音与音效、多平台一键发布或定时发布、给内容做变现规划时使用此技能。 依赖…

    47D
47. zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the big…

    47D
48. handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    45D

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.