twitter-to-binance-square
Auto-mirror Twitter/X content to Binance Square, or publish a new Square post directly. Supports text posts, up to 4 images, one video, and #tags. Use for requests like "mirror tweets to Binance Square", "post this image to Square", "publish this video to Square", or "run the Binance Square MCP server".
What this skill does
# Twitter to Binance Square Use the scripts in this skill directory. The scripts own Binance Square upload, status polling, video cover extraction, and publish behavior. ## Credentials - Tweet mirroring requires `TWITTER_TOKEN`. - `TWITTER_TOKEN` must be a valid 6551 Twitter API token supplied by the user's environment. - Square publishing requires `BINANCE_SQUARE_OPENAPI_KEY`; `SQUARE_API_KEY` is accepted only for backward compatibility. - Never pass the Square key as a command-line argument or MCP tool parameter. - Never print the full key. ## Supported Publish Shapes | Shape | Binance body fields | |---|---| | Text | `contentType=1`, `bodyTextOnly` | | Images | `contentType=1`, `bodyTextOnly`, `imageList` | | Video | `contentType=3`, `fileTicket`, `cover`, `videoTimeSeconds`, `isPublish=true` | | Tags | normalized `#tags` appended into `bodyTextOnly` | Images and video are mutually exclusive. Image posts support max 4 images. Video posts support exactly 1 video. ## Automation Script Run from this directory: ```bash python scripts/auto_mirror.py --mode account --accounts VitalikButerin --tags Crypto,Web3 --once --dry-run ``` Effective CLI parameters: | Parameter | Effect | |---|---| | `--config`, `-c` | Load JSON config. | | `--mode` | `account`, `search`, or `hashtag`. | | `--accounts` | Comma-separated Twitter usernames for account mode. | | `--keywords` | Search keywords for search mode. | | `--hashtag` | Hashtag for hashtag mode, without `#`. | | `--interval` | Poll interval in seconds. | | `--min-likes` | Minimum likes threshold. | | `--min-retweets` | Minimum retweets threshold. | | `--max-posts` | Max posts per cycle. | | `--include-replies` | Include replies in account mode. | | `--include-retweets` | Include retweets in account mode. | | `--tags` | Comma-separated tags appended as `#tags`. | | `--image` | Image path or URL to attach; repeat or comma-separate, max 4. | | `--video` | One video path or URL to attach. | | `--video-duration` | Video duration in seconds; if omitted, `ffprobe` is used. | | `--video-cover` | Image path or URL used as video cover; if omitted, `ffmpeg` extracts the first frame. | | `--no-tweet-images` | Ignore images found on source tweets. | | `--no-tweet-videos` | Ignore videos found on source tweets. | | `--dry-run` | Preview request body without posting or uploading. | | `--once` | Run one cycle and exit. | | `--state-file` | State file for posted tweet IDs and post log. | The JSON config uses `mirror_config.example.json` as the source of truth. ## MCP Server Run: ```bash python scripts/mcp_server.py ``` MCP tool: `publish_square_post` | Parameter | Effect | |---|---| | `text` | Required post text. | | `tags` | Optional list of tags. Items may include or omit `#`. | | `images` | Optional list of local image paths or image URLs, max 4. | | `video` | Optional local video path or video URL. | | `video_duration_seconds` | Optional positive duration; if omitted, `ffprobe` is used. | | `video_cover` | Optional local image path or URL for video cover; if omitted, `ffmpeg` extracts the first frame. | | `dry_run` | Return request body without upload or publish. | Do not pass both `images` and `video`. ## Agent Rules 1. Use `dry_run` before first live publishing when practical. 2. Only attach media explicitly provided by the user or present on the source tweet. 3. Do not rewrite user text unless the user asks. 4. Preserve existing `#tags` and `$symbols`; append configured tags only once. 5. Treat `220009` as the daily Square OpenAPI limit. ## Verification Boundary Local dry-run verifies parameter wiring and request-body construction. Live Square publishing was verified on 2026-05-23 with a temporary OpenAPI key for image+tags and video+tags posts. Live Twitter account fetching was verified with a valid 6551 `TWITTER_TOKEN`. Twitter image URL publishing was also verified end to end: a direct `pbs.twimg.com/media/...` source image was uploaded and published as a Square-hosted `public.bnbstatic.com` image. Tweet image extraction must prefer direct `pbs.twimg.com/media/...` image URLs over `x.com/.../photo/...` page URLs.
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.