Communitygithub.com

NeverSight/learn-skills.dev

Operate the user's personal WeChat account through their self-hosted Wisdom service (BYOC) — check login status, list contacts/conversations, read and summarize history, search contacts, refresh the local history DB, and send messages only after explicit confirmation. Use when the user mentions 个人微信, 我的微信, WeChat personal chat, 微信聊天记录, 微信联系人, reading/summarizing WeChat messages, or sending a WeChat message.

learn-skills.dev 是什么?

learn-skills.dev is a Claude Code agent skill that operate the user's personal WeChat account through their self-hosted Wisdom service (BYOC) — check login status, list contacts/conversations, read and summarize history, search contacts, refresh the local history DB, and send messages only after explicit confirmation. Use when the user mentions 个人微信, 我的微信, WeChat personal chat, 微信聊天记录, 微信联系人, reading/summarizing WeChat messages, or sending a WeChat message.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/acedatacloud/skills/personal-wechat

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Personal WeChat via Wisdom

Use the user's self-hosted Wisdom service to operate their personal WeChat account. Wisdom runs on a Windows host with WeChat Desktop logged in and exposes an HTTP API.

Credentials are injected by the personalwechat BYOC connector:

  • PERSONALWECHAT_BASE_URL — Wisdom server base URL, e.g. http://82.156.126.14:8000.
  • PERSONALWECHAT_API_TOKEN — Wisdom API_TOKEN. Secret — never echo, print, or log it.

The helper sends the token as Authorization: Bearer ...; it never puts the token in the URL. For queued UI operations such as search and send, the helper submits the task and waits for /api/tasks/{id} before printing the final result.

This is the user's real personal WeChat account. Read operations can run directly. Sending messages or files must be dry-run first, then performed only after the user explicitly approves the exact target and content.

CLI

The skill ships a stdlib-only helper:

WX=$SKILL_DIR/scripts/personal_wechat.py

Verify Connection First

Always start with status when the user asks to use WeChat:

python3 $WX status

Expected healthy shape:

{"auth":{"logged_in":true,"wechat_running":true,"page":"logged_in"}}

If logged_in=false, tell the user to open the Wisdom web UI / RDP and scan the WeChat QR code. If the API returns 401, ask the user to reconnect the Personal WeChat connector with the current Wisdom API token.

Read Workflows

Current Account

python3 $WX account

Contacts

python3 $WX contacts --limit 50

Recent Conversations

Use the normal conversations endpoint first; it prefers WeChat DB when ready and falls back to Wisdom's app DB.

python3 $WX conversations --limit 20

For decrypted local WeChat history sessions:

python3 $WX conversations --history --limit 20

Messages in a Conversation

First list conversations, then use the id as conversation_id:

python3 $WX messages "34642176898@chatroom" --limit 50 --order asc

Historical Messages

Read from Wisdom's decrypted WeChat local databases:

python3 $WX history --limit 50
python3 $WX history --talker "34642176898@chatroom" --limit 50
python3 $WX history --limit 20 --offset 20

Raw SQL, Read-Only Only

Wisdom permits only SELECT and PRAGMA:

python3 $WX sql MicroMsg.db 'SELECT count(*) AS cnt FROM Session'

Use raw SQL only for diagnostics or targeted metadata queries. Do not dump large message tables unless the user explicitly asks.

Refresh History DB

If history looks stale, refresh the decrypted DB snapshot:

python3 $WX refresh-history

Search

python3 $WX search "Alice"

Search drives the WeChat UI, so it may be slower than local DB history reads.

Sending Messages — GATED

send dry-runs by default. It never sends unless --confirm is present, or unless an AceDataCloud scheduled task pre-authorized this Skill and you use --unattended-confirm.

python3 $WX send "Alice" "今晚 8 点开会吗?"
# -> {"dry_run": true, ...}

Show the dry-run output to the user and ask for explicit approval of the exact recipient and text. Only then run:

python3 $WX send "Alice" "今晚 8 点开会吗?" --confirm

Never add --confirm in the first attempt. Never infer consent from vague text. The user must clearly approve sending this exact message.

Scheduled-task unattended confirmation

When running inside an AceDataCloud scheduled task, the platform may pre-authorize specific Skills for unattended execution. If all of these are true:

  • AICHAT_UNATTENDED_MODE=true
  • AICHAT_ACTIVE_SKILL is personal-wechat or acedatacloud/personal-wechat
  • AICHAT_ACTIVE_SKILL appears in AICHAT_UNATTENDED_ALLOWED_SKILLS

then the user has pre-authorized this Skill for that scheduled task. In that case, use:

python3 $WX send "Alice" "今晚 8 点开会吗?" --unattended-confirm

If the helper returns unattended_confirmation_denied, do not retry with --confirm; report the dry-run and explain that the task needs this Skill to be selected in its unattended authorization settings.

Safety Rules

  • Never print PERSONALWECHAT_API_TOKEN.
  • Treat PERSONALWECHAT_BASE_URL + API_TOKEN as full remote control of the user's WeChat.
  • For normal chat write/send operations: dry-run first, ask for explicit approval, then re-run with --confirm.
  • For scheduled-task unattended writes: use --unattended-confirm only when the platform env says this Skill is pre-authorized.
  • Do not call logout/restart endpoints from the skill unless the user explicitly asks to repair the Wisdom service.
  • If Wisdom returns 503 for history, run python3 $WX refresh-history once, then retry the read.
  • If the server is unreachable, ask the user to check the Windows host / security group / port 8000.

Endpoint Mapping

The helper wraps these Wisdom endpoints:

  • GET /api/status
  • GET /api/auth/status
  • GET /api/account
  • GET /api/contacts?version=2.0
  • GET /api/conversations
  • GET /api/conversations/history
  • GET /api/messages
  • GET /api/messages/history
  • POST /api/messages/history/query
  • POST /api/messages/history/refresh
  • POST /api/search
  • POST /api/messages/send (only after --confirm or verified --unattended-confirm)

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

相关技能