What makes Review Responder notable?

1.3K downloads. Trust evidence available

How should Review Responder be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Review Responder

Use this skill when an operator is actively running the Google Business Profile review-response workflow for one of their configured client accounts. Specific triggers: 'check for new reviews,' 'run the review check for [client],' 'new review came in for [client],' 'draft a reply to the [reviewer] r

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

2.1.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 2.1.1release · observed Sep 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17f63svb641q2stekk1cmcdn183k4rq:google-review-responder

Install using `clawhub skill install s17f63svb641q2stekk1cmcdn183k4rq:google-review-responder` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/chris/google-review-responder before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chris-google-review-responder/snapshot"

Documentation

CLAWHUB

141,830 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: review-responder
version: 2.0.1
description: "Use this skill when an operator is actively running the Google Business Profile review-response workflow for one of their configured client accounts. Specific triggers: 'check for new reviews,' 'run the review check for [client],' 'new review came in for [client],' 'draft a reply to the [reviewer] review,' 'approve the draft for [reviewer/client],' 'post the reply for [review id],' 'show pending review approvals,' 'show me the pending reviews,' or 'apply the [medical/legal/restaurant/retail/general] industry profile to this draft.' Do NOT trigger on: general questions about how to handle reviews, casual mentions of Google reviews, marketing strategy chat, requests to write a review (versus reply to one), or any workflow where no configured client exists. Covers: scheduled checks against Google Business Profile API for configured clients, star-rating-matched draft replies with industry-aware drafting constraints (medical/HIPAA-aware, legal, restaurant, retail), and an approval gate across Telegram, email, webhook, or in-chat channels. Drafts are NEVER auto-posted; operator approval is required before any reply is published. See Privacy and Data Handling for credential and posting scope."
metadata:
openclaw:
emoji: ⭐
---

# Review Responder

Automatically monitors Google Business Profile reviews across one or more client accounts, drafts professional responses tuned to star rating and industry, and routes drafts to a configurable approval channel before posting. Designed for agencies and consultants managing reviews on behalf of clients.

## Trigger

This skill activates during scheduled review checks (heartbeat) and when an operator responds to a pending review approval message.

---

## Configuration

All paths and channels are read from a single config file: `review-responder.config.json` in the skill's data directory. If it doesn't exist, create one from this template on first run:

```json
{
"script_path": "~/review-responder/gbp_reviews.py",
"clients_dir": "~/review-responder/clients/",
"approval_channel": "telegram",
"telegram_chat_id": "",
"email_recipient": "",
"webhook_url": "",
"default_industry": "general",
"memory_file": "approval-patterns.json"
}
```

### Configuration fields

- **script_path**: Absolute path to the `gbp_reviews.py` CLI. Defaults to `~/review-responder/gbp_reviews.py` but can live anywhere.
- **clients_dir**: Directory containing per-client config files. Each client gets its own subdirectory or JSON entry.
- **approval_channel**: One of `telegram`, `email`, `webhook`, or `chat`. Determines where draft replies are sent for approval. See Approval Channels below.
- **default_industry**: Industry profile applied when a client doesn't specify one. See Industry Compliance Profiles below.
- **memory_file**: Where to log approval patterns for the learning layer.

### Per-client overrides

Each client in `clients_dir` can override `industry`, `approv

README.md

# Review Responder

An [OpenClaw](https://openclaw.ai) skill that monitors Google Business Profile reviews, drafts professional responses, and routes them to a configurable approval channel before posting.

Built for consultants and agencies managing reviews across multiple client locations and industries.

**Current version: 2.0.1**

## What's new in 2.0.1

- Added a **Privacy and Data Handling** section to SKILL.md that honestly describes the skill's real network calls (Google Business Profile API), credential storage (operator-owned OAuth credentials per client), and the no-auto-post guardrail
- Added a **Permissions and Privacy** section to this README so operators see scope, credential handling, and the HIPAA-aware (not HIPAA-certified) boundary before installing
- Reworded the `medical` industry profile from "HIPAA-safe" to "HIPAA-aware drafting" to accurately describe what the skill enforces (drafting constraints) versus what it does not provide (workflow certification)
- Narrowed the activation triggers in `description` to require an active, configured-client workflow, with a "do NOT trigger" guard for casual reviews chat and review-writing requests

## What's new in 2.0.0

- **Configurable script paths and channels** via a single `review-responder.config.json` file
- **Channel-agnostic approval flow**: Telegram, email, webhook, or in-thread chat
- **Industry compliance profiles**: medical (HIPAA-aware drafting), legal, restaurant, retail, and general
- **Operator pattern learning**: logs approval decisions per client and surfaces patterns (e.g., "you usually shorten 5-star replies for this client")
- **Per-client overrides** for industry, approval channel, and tone notes

See [CHANGELOG.md](CHANGELOG.md) for the full release history.

## How It Works

1. On each scheduled check, OpenClaw enumerates configured clients and looks for new unanswered reviews
2. For each new review, the agent applies the client's industry profile and drafts a tone-matched response
3. The draft is sent to the configured approval channel (Telegram, email, webhook, or chat)
4. The operator replies "OK" to post it, sends edits to revise it, or "skip" to ignore it
5. Decisions are logged so the agent can learn the operator's preferences over time

No reviews are ever posted without explicit operator approval.

## What's Included

- `SKILL.md` — Agent behavior instructions (configuration, approval flow, industry profiles, pattern learning)
- `HEARTBEAT.md` — Periodic check instructions for OpenClaw's heartbeat system
- `gbp_reviews.py` — Main script for checking reviews and posting replies
- `get_client_token.py` — One-time OAuth helper for onboarding clients locally
- `oauth_server.py` — Web-based OAuth flow for remote client onboarding
- `clients/_template.json` — Config template for adding new clients
- `SETUP.md` — Full setup and per-client onboarding guide

## Quick Start

1. Set up a Google Cloud project with the Business Profile API enabled (details in `SETUP

_meta.json

{
  "ownerId": "kn77r9qjvh6fy4aja2km8bzgvd83khv9",
  "slug": "google-review-responder",
  "version": "2.1.1",
  "publishedAt": 1790621086156
}

CHANGELOG.md

# Changelog

All notable changes to this skill will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this skill adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [2.0.1] — 2026-06-08

### Added
- **Privacy and Data Handling** section in SKILL.md describing the real network surface (Google Business Profile API v4, Google OAuth token endpoint, configured approval channel), credential storage (operator-owned OAuth credentials per client in `clients_dir`), and hard guardrails (no auto-posting, no PHI in public replies, no credential leakage, no bulk export)
- **Permissions and Privacy** section in README.md so operators see the full network surface, credential storage posture, hard guardrails, and the compliance scope (HIPAA-aware drafting, NOT a HIPAA-certified workflow) before installing

### Changed
- Reworded the `medical` industry profile from "HIPAA-safe" to "HIPAA-aware drafting" to accurately describe the constraint (avoids PHI in public reply text) without implying a regulatory certification this skill cannot provide. CHANGELOG references to "HIPAA-safe" updated in the 2.0.0 entry's description of this profile for consistency
- Narrowed the activation triggers in the `description` frontmatter to require an explicit configured-client workflow (named client, named reviewer, specific approval/post action), with a "do NOT trigger" guardrail for casual review chat, review-writing requests, and marketing-strategy questions
- Unquoted the `version` field in frontmatter (matches updated ClawHub CLI semver requirements)

## [2.0.0] — 2026-05-12

### Added
- Configuration file (`review-responder.config.json`) for centralizing script paths, clients directory, approval channel, default industry, and memory file location
- Per-client configuration overrides for industry, approval channel, and tone notes
- Channel-agnostic approval flow with four supported channels: Telegram, email, webhook, and in-thread chat
- Industry compliance profiles for medical (HIPAA-safe), legal, restaurant, retail, and general business types
- Operator pattern learning layer that logs each approval decision (approved-as-is, edited with diff summary, skipped) per client and surfaces patterns over time
- Periodic insight surfacing to the operator (e.g., "you usually shorten 5-star replies for this client by ~10 words")

### Changed
- **BREAKING**: Hardcoded script paths (`~/review-responder/gbp_reviews.py`) replaced with a configurable `script_path` field
- **BREAKING**: Telegram is no longer the assumed approval channel; `approval_channel` must be set explicitly in config
- HIPAA section promoted from a sub-block under Response Guidelines into a top-level `Industry Compliance Profiles` section with peer profiles for other industries
- SKILL.md now has proper YAML frontmatter (`name`, `version`, `description`, `metadata.openclaw.emoji`)

### Removed
- MIT LICENSE file (license now managed at

HEARTBEAT.md

# Heartbeat: Review Responder

## On Every Heartbeat

1. Check for new unanswered Google Business reviews for each active client.
   Run for each client configured in `~/review-responder/clients/`:
   ```
   python3 ~/review-responder/gbp_reviews.py check --client <client_id>
   ```

2. If the script finds new reviews, read the output carefully. For each new review:
   - Draft a response following the guidelines in the Review Responder skill (SKILL.md)
   - Send the draft to the operator via Telegram for approval
   - Use the message format specified in SKILL.md

3. If no new reviews are found for any client, reply HEARTBEAT_OK.

## Important
- Do NOT auto-post replies. Every response requires operator approval via Telegram.
- If the script errors (missing config, API failure), report the error via Telegram so the operator can investigate.
- Check `python3 ~/review-responder/gbp_reviews.py pending` to see if there are stale pending reviews that haven't been addressed. If any are older than 48 hours, send a reminder.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.