gdocs-tab-writer
Skill1 starsChanged 6 days agoUnlicenseView on GitHub
Write structured content to a specific tab in a Google Doc using the gdocs batch CLI. Use when asked to write, append, or update content in a Google Doc tab, paste content into a doc, or populate an empty doc tab with formatted content.
In this repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ad-copy-writerSkill
- ae-inspect-describeSkill
- algorithmic-artSkill
- animation-directorSkill
- assembly-guideSkill
- brainstorming-and-ideatingSkill
- brainstorming-research-ideasSkill
- brainstormingSkill
- brief-to-tasksSkill
- canvas-designSkill
- cli-designSkill
- cli-output-hierarchySkill
- commit-messageSkill
- craft-uiSkill
- creative-directorSkill
- design-briefSkill
- design-flowSkill
- design-mock-auditSkill
- design-reviewSkill
- design-system-patternsSkill
- design-tokensSkill
- deslopifySkill
- diagnoseSkill
- diagramming-app-routesSkill
- doc-restructureSkill
- eval-criticSkill
- formatting-open-markdownsSkill
- frontend-designSkill
- frontend-slidesSkill
- gemini-apiSkill
- gif-creationSkill
- github_repo_researchSkill
- grill-meSkill
- grill-with-docsSkill
- hallmarkSkill
- handoffSkill
- html-presentationSkill
- humanizerSkill
- i-have-adhdSkill
- improve-codebase-architectureSkill
- information-architectureSkill
- install-skill-from-githubSkill
- markdown-output-hierarchySkill
- marketing-psychologySkill
- merge-latestSkill
- modern-web-performanceSkill
- motion-designSkill
- pdf-readerSkill
- pm-brainstormingSkill
- pm-discovery-brainstormSkill
- product-marketingSkill
- prototypeSkill
- pull-requestSkill
- ralph_loopSkill
- react-best-practicesSkill
- review-loopSkill
- sandbox-explainerSkill
- skill-creatorSkill
- skill-optSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Write structured, formatted content to a specific tab in a Google Doc.
- Very specific: line 34
Every object MUST have an "op" field.
- Very specific: line 93
All ops support optional styling: bold, italic, font_family, font_size, text_color, alignment, paragraph_bg_color.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
gdocs-tab-writer
Write structured, formatted content to a specific tab in a Google Doc.
Why This Skill Exists
Most gdocs write commands (write, import-md --update) do NOT support the
--tab flag. The only reliable way to write to a specific tab is:
GDOCS=/google/bin/releases/gemini-agents-gdocs/gdocs
$GDOCS batch DOC_ID -f batch.json --tab TAB_IDQuick Reference
Step 1: Find the tab ID
$GDOCS list-tabs DOC_IDStep 2: Build a batch JSON file
Every object MUST have an "op" field. The "level" field on headings MUST be
a string, not a number.
[
{"op": "heading", "text": "My Title", "level": "1"},
{"op": "append", "text": "\nSome body text.\n"},
{"op": "heading", "text": "Section", "level": "2"},
{"op": "append", "text": "\nMore content here.\n"},
{"op": "bullet-list", "text": "First point"},
{"op": "bullet-list", "text": "Second point"},
{"op": "numbered-list", "text": "Step one"},
{"op": "numbered-list", "text": "Step two"},
{"op": "insert-table", "table_data": [["Col A", "Col B"], ["val1", "val2"]], "table_header_bg_color": "#e8f0fe", "table_header_bold": true}
]Step 3: Execute the batch
$GDOCS batch DOC_ID -f /path/to/batch.json --tab TAB_IDTo replace all existing content in the tab:
$GDOCS batch DOC_ID -f /path/to/batch.json --tab TAB_ID --replace-allGotchas (Things That Do NOT Work)
| Approach | Why It Fails |
| `import-md --update DOC_ID --tab | --tab flag not supported |
| : TAB_ID` : : | |
| `write DOC_ID --file f.md --tab | --tab flag not supported |
| : TAB_ID` : : | |
append DOC_ID "text" --tab TAB_ID | Works but text is an inline arg — too |
| : : short for large content : | |
codemind replace_paragraph MCP | Can't find markdown comment markers |
| : tool : (invisible in Docs) : | |
Batch JSON with "level": 1 | Parser error — must be "level": "1" |
| : (number) : (string) : | |
Batch JSON without "op" field | unknown batch op "" error |
Available Ops
| Op | Required Fields | Description |
heading | text, level | Heading (level "1"-"6", "TITLE", |
| : : : "SUBTITLE") : | ||
append | text | Append styled text paragraph |
bullet-list | text | Bullet list item |
numbered-list | text | Numbered list item |
insert-table | table_data | Table with optional styling |
horizontal-rule | — | Visual separator |
rich-text | runs | Multi-style paragraph |
link | text, url | Hyperlinked text |
All ops support optional styling: bold, italic, font_family, font_size,
text_color, alignment, paragraph_bg_color.
Full Workflow Example
GDOCS=/google/bin/releases/gemini-agents-gdocs/gdocs
DOC_ID="1GwoW3rTCg0_tuW5VWK7bKUJ0o3s5M7pqYWF7Yb4flZw"
# 1. List tabs to find the target
$GDOCS list-tabs $DOC_ID
# 2. Save batch JSON to a scratch file
# (use write_to_file to create /path/to/batch.json)
# 3. Write to the tab
$GDOCS batch $DOC_ID -f /path/to/batch.json --tab t.8mtzp4dajt86
# 4. Verify
$GDOCS read $DOC_ID --tab t.8mtzp4dajt86Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

