wadackel/dotfiles/gdocs-to-md
Claude Code and agent skill by wadackel/dotfiles
- community
Checking that the SKILL.md file is still in the repository.
Convert a Google Docs document to GitHub Flavored Markdown via Docs API. Fetches document structure as JSON via gws docs, then converts with a Bun script. Use when asked to "convert Google Docs to Markdown", "Google DocsをMarkdownに変換して", "docsをmdにして", "MarkdownにExportして", or when a Google Docs URL is provided with intent to produce a .md file.
Install
npx vskill@latest install wadackel/dotfiles/gdocs-to-mdSKILL.md
The same SKILL.md was published earlier as wadackel/dotfiles/gdocs-to-md.
Google Docs to Markdown
Convert a Google Docs document to GitHub Flavored Markdown. Fetches the document via gws docs documents get (Google Docs API), then converts the JSON structure to GFM using a Bun script.
Prerequisites
- gws CLI — for Google Docs API access. See the gws-shared skill for auth setup.
- jq — for JSON parsing.
- Bun — for running the conversion script.
- Google Docs API must be enabled for your GCP project.
Quick Start
Accepts either a full Google Docs URL or a raw document ID. If called with no argument, you will be prompted.
Output is written to the current working directory.
Workflow
Step 0 — Confirm output location
Display the current working directory to the user before writing any files:
Step 1 — Parse $ARGUMENTS
- Full URL: extract the document ID using the pattern
/d/([a-zA-Z0-9_-]+)/ - Raw ID: use as-is (alphanumeric string, typically 30+ characters)
- No argument: ask through the current agent's user-confirmation mechanism for the URL or document ID; in text-only runtimes, ask the question, end the turn, and wait for the user's next response before continuing
Step 2 — Create isolated temp file
Step 3 — Fetch document JSON
Validate after fetch:
- Check
jq -e '.body' "$TMP_JSON" > /dev/nullpasses — confirms a valid document response - Extract title:
TITLE=$(jq -r '.title' "$TMP_JSON") - Check
$TITLEis non-empty
If validation fails: print the raw content of $TMP_JSON and "temp file preserved at: $TMP_JSON", then stop.
On gws failure: print the error and "temp file at: $TMP_JSON". If the error is an auth/permission issue, suggest running gws auth login. If the error mentions Docs API not enabled, direct user to enable it in GCP Console. Do not proceed to conversion.
Step 4 — Convert with the Bun script
On conversion failure: print the error and "JSON preserved at: $TMP_JSON", then stop.
Step 5 — Cleanup (success only)
Only clean up after successful conversion. On failure, preserve $TMP_JSON for debugging.
Step 6 — Report result
Verify the output file exists, then report absolute paths. Do not read the full file content into context.
Output
| File | Description | |
|---|---|---|
<title>.md | GitHub Flavored Markdown, no hard line-wrapping |
Written to the current working directory.
Additional Resources
- For flag explanations, error handling details, and known limitations, see workflow-details.md
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinghome/programs/agents/skills/gdocs-to-md/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/wadackel/dotfiles/gdocs-to-md)