Google Comment Responder

View saved version →

---
name: google-comment-responder
description: Reusable workflow for responding to existing document comment threads. Use when Codex needs to scan comments on one or more documents, filter by configurable markers such as `AGENT:`, draft concise replies, post replies only to eligible existing threads, resolve threads only when asked, avoid deleting comments, and verify writeback. Works as a generic workflow for Google Drive comments or any connector/API that exposes comment threads, authors, status, replies, and pagination.
---

# Google Comment Responder

## Overview

Use this skill to run a configurable comment responder without embedding any person-, company-, document-, or project-specific IDs. Treat all targets, author filters, markers, evidence sources, and write rules as per-run configuration gathered from the user request, local instructions, or an explicit config file.

Treat eligible comments as another input surface for Codex. Once a thread passes the configured eligibility filters, interpret the latest eligible comment as the user's request and execute it with the same resources and instruction hierarchy available in an ordinary Codex prompt: user request, local instruction files such as `AGENTS.md`, memory, configured skills, connected apps/tools, documents, repositories, prior notes, and any explicit resources. Do not limit the answer to the target document unless the request or policy says to.

## Required Configuration

Before reading or writing comments, identify these settings:

- Target files: stable file IDs, URLs, or exact paths. Prefer stable IDs over names when available.
- Comment tool: the connector/API that can list, reply to, resolve, or read back comments.
- Eligibility marker: labels such as `AGENT:`, `BOT:`, `REVIEW:`, or another requested string.
- Author filter: if no author name is provided, try to infer it from all available resources before asking. Use connector metadata such as `author.me: true`, a `whoami` result, the authenticated profile/email, document comment authors, local instructions, explicit config, or other provided context. If the author is still unknown or ambiguous, ask before replying. The user or config can adjust this later, including allowing multiple authors.
- Status filter: usually unresolved and non-deleted threads only.
- Skip markers: phrases such as `do not respond`, `ignore`, or any user-specified exclusion.
- Evidence sources: all available resources that would normally be available for the same Codex prompt, including documents, attachments, repositories, memory, local instructions such as `AGENTS.md`, configured skills/tools, prior notes, and current comments. For factual asks, prefer live primary sources and use memory or prior notes as leads rather than final evidence when verification is practical.
- Surrounding context: nearby document text around each comment anchor, quote, slide, cell, or section.
- Write policy: draft-only, post replies, resolve after replying, or report-only.
- Output format: counts, replied thread IDs, skipped reasons, and unresolved blockers.

If a required setting is missing and a reasonable default would risk writing the wrong comment, ask one concise question before posting.

## Generic Config Shape

Use this shape when the user asks to save or describe a reusable responder:

```yaml
targets:
  - id: "<stable-file-id-or-url>"
    type: "<doc|sheet|slide|file|other>"
    label: "<human-readable-label>"
eligibility:
  marker: "AGENT:"
  author_filter:
    default: "running_user"
    infer_if_missing: true
    allowed_authors: []
    ask_if_unknown: true
    allow_multiple_authors: true
  unresolved_only: true
  non_deleted_only: true
  skip_markers:
    - "do not respond"
    - "ignore"
write_policy:
  mode: "draft-then-post"
  reply_to_existing_threads_only: true
  allow_resolve: false
  allow_delete: false
pagination:
  page_size: 100
  require_exhaustive_scan: true
verification:
  reread_after_write: true
  report_thread_ids: true
c

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 1 — file references are metadata, not package contents.