13916236077/ximalaya-dedao-transcripts

Codex Skill for turning Ximalaya audio links into Dedao Brain transcripts

Compatible avec~Claude CodeCodex CLI~Cursor
npx skills add 13916236077/ximalaya-dedao-transcripts

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Ximalaya Dedao Transcripts

Overview

Use this skill to turn public Ximalaya audio links into Dedao Brain note transcripts. Prefer the bundled scripts for all fragile steps: Ximalaya manifest extraction, Dedao token refresh, local-audio upload/note creation, original transcript retrieval, and Markdown export.

Do not paste long transcript text into chat. Save user-facing transcript deliverables under the current workspace outputs/ directory.

Workflow

  1. Create a working directory:
mkdir -p work/ximalaya_dedao outputs/ximalaya_dedao
  1. Prepare Dedao auth files. Read existing token files if the user has them in the workspace. Never print tokens in chat or logs.
node <skill>/scripts/dedao_refresh_token.mjs \
  --refresh-token-file work/dedao_current_refresh_token.txt \
  --token-file work/dedao_current_token.txt \
  --out-refresh-token-file work/dedao_current_refresh_token.txt \
  --response-file work/ximalaya_dedao/dedao_refresh_response.json
  1. Build a Ximalaya manifest:
node <skill>/scripts/ximalaya_manifest.mjs \
  --url "https://xima.tv/..." \
  --out work/ximalaya_dedao/manifest.json

If the manifest reports complete: false, read references/ximalaya-manifest.md and fix the missing pages before creating Dedao notes. Do not silently process an incomplete album.

  1. Create Dedao local-audio notes:
node <skill>/scripts/ximalaya_to_dedao_batch.mjs create \
  --manifest work/ximalaya_dedao/manifest.json \
  --token-file work/dedao_current_token.txt \
  --refresh-token-file work/dedao_current_refresh_token.txt \
  --out-refresh-token-file work/dedao_current_refresh_token.txt \
  --out-dir outputs/ximalaya_dedao
  1. Pull original transcript JSON for every note:
node <skill>/scripts/ximalaya_to_dedao_batch.mjs originals \
  --manifest work/ximalaya_dedao/manifest.json \
  --token-file work/dedao_current_token.txt \
  --refresh-token-file work/dedao_current_refresh_token.txt \
  --out-refresh-token-file work/dedao_current_refresh_token.txt \
  --out-dir outputs/ximalaya_dedao
  1. Export Markdown deliverables:
node <skill>/scripts/export_transcripts.mjs \
  --manifest work/ximalaya_dedao/manifest.json \
  --notes outputs/ximalaya_dedao/note_ids.json \
  --originals outputs/ximalaya_dedao/originals \
  --out-dir outputs/ximalaya_dedao_transcripts
  1. Verify before final response:
node -e "const fs=require('fs'); const idx=JSON.parse(fs.readFileSync('outputs/ximalaya_dedao_transcripts/index.json','utf8')); console.log(idx.episode_count, idx.total_text_char_count, idx.missing_files||0)"
find outputs/ximalaya_dedao_transcripts/episodes -maxdepth 1 -name 'p*.md' | wc -l

Quality Gates

  • Compare manifest episode count, note ID count, original JSON count, and exported Markdown file count.
  • Inspect empty or tiny originals/pNN.json files before exporting.
  • If Ximalaya DNS or Dedao API calls fail inside the sandbox, rerun the same important command with network escalation.
  • For Ximalaya .m4a audio, Dedao may reject type=m4a; pass --upload-type mp3 while uploading the downloaded bytes. This matched the verified local-audio flow.
  • If stream_on_local_audio times out after writing a note ID, keep the note ID and fetch original by note ID.

References

  • Read references/dedao-local-audio.md when Dedao upload, signing, token refresh, note creation, or original retrieval fails.
  • Read references/ximalaya-manifest.md when a Ximalaya album/track link does not produce a complete manifest.

Skills associés

minimax-ai/vision-analysis

Analyze, describe, and extract information from images using the MiniMax vision MCP tool. Use when: user shares an image file path or URL (any message containing .jpg, .jpeg, .png, .gif, .webp, .bmp, or .svg file extension) or uses any of these words/phrases near an image: "analyze", "analyse", "describe", "explain", "understand", "look at", "review", "extract text", "OCR", "what is in", "what's in", "read this image", "see this image", "tell me about", "explain this", "interpret this", in connection with an image, screenshot, diagram, chart, mockup, wireframe, or photo. Also triggers for: UI mockup review, wireframe analysis, design critique, data extraction from charts, object detection, person/animal/activity identification. Triggers: any message with an image file extension (jpg, jpeg, png, gif, webp, bmp, svg), or any request to analyze/describ/understand/review/extract text from an image, screenshot, diagram, chart, photo, mockup, or wireframe.

community

Lifecycle-Innovations-Limited/claude-ops

Business operating system for Claude Code — 25 skills, 13 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS monitoring, revenue (Stripe+RevenueCat), e-commerce (Shopify), marketing (Klaviyo/Meta/GA4), voice (Bland/ElevenLabs), APM (Datadog/NewRelic/OTEL), YOLO mode.

community

Agents365-ai/ccc-skill

Cell-cell communication analysis skill for AI coding agents — LIANA+, CellPhoneDB, CellChat, NicheNet, COMMOT

community

jackquelinunpredictable827/mkhlab

Power OpenClaw with 60 Arabic AI skills, dialect support, and local-first privacy on any model

community

yhlai0911/codex-skill-workshop

Agent skill repository for yhlai0911/codex-skill-workshop.

community

DmitriiPetukhov/codex-skill-marketplace

Agent skill repository for DmitriiPetukhov/codex-skill-marketplace.

community