Human Approval Gate for Agents
Human Approval Gate for Agents
Agent Skills🔌 MCP-ready
Health
80/100
▲ 0
📋 0 copies
Trigger Phrase
Use the Human Approval Gate for Agents skill
Prompt
289 words# QUALITY GATE: Human Approval Gate for Agents
## Purpose
Force an explicit approval checkpoint before an agent sends messages, spends money, deletes data, posts publicly, or changes production systems.
## When to Use
Use this when the user needs to: Force an explicit approval checkpoint before an agent sends messages, spends money, deletes data, posts publicly, or changes production systems. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Proposed action
- Affected system
- Impact level
- Recipient or audience
- Rollback option
## Workflow
1. Classify the action as low, medium, high, or irreversible risk
2. Summarise what will happen in plain English
3. List data that will be exposed or changed
4. Require approval wording for medium or higher risk
5. Block execution if approval is missing or ambiguous
## Output Format
Approval card with risk rating, action summary, required confirmation, and block/pass result.
## Quality Rules
- Ground every claim in supplied inputs or clearly mark it as an assumption.
- Prefer specific fields, examples, and decision points over generic advice.
- Include a test command and pass criteria so the skill can be evaluated.
- Keep the output usable by a human first and automation-ready second.
## Guardrails
- Do not send emails, publish posts, contact leads, change calendars, spend money, delete data, or alter production systems without explicit human approval.
- Do not invent facts, private details, legal claims, prices, or external data.
- For web or profile research, use current sources and separate evidence from inference.
- For connected tools, use the minimum permission needed and log the action taken.
## Test Command
Run this skill on a simple example for Human Approval Gate for Agents and return the expected output structure plus any missing inputs.
## Purpose
Force an explicit approval checkpoint before an agent sends messages, spends money, deletes data, posts publicly, or changes production systems.
## When to Use
Use this when the user needs to: Force an explicit approval checkpoint before an agent sends messages, spends money, deletes data, posts publicly, or changes production systems. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Proposed action
- Affected system
- Impact level
- Recipient or audience
- Rollback option
## Workflow
1. Classify the action as low, medium, high, or irreversible risk
2. Summarise what will happen in plain English
3. List data that will be exposed or changed
4. Require approval wording for medium or higher risk
5. Block execution if approval is missing or ambiguous
## Output Format
Approval card with risk rating, action summary, required confirmation, and block/pass result.
## Quality Rules
- Ground every claim in supplied inputs or clearly mark it as an assumption.
- Prefer specific fields, examples, and decision points over generic advice.
- Include a test command and pass criteria so the skill can be evaluated.
- Keep the output usable by a human first and automation-ready second.
## Guardrails
- Do not send emails, publish posts, contact leads, change calendars, spend money, delete data, or alter production systems without explicit human approval.
- Do not invent facts, private details, legal claims, prices, or external data.
- For web or profile research, use current sources and separate evidence from inference.
- For connected tools, use the minimum permission needed and log the action taken.
## Test Command
Run this skill on a simple example for Human Approval Gate for Agents and return the expected output structure plus any missing inputs.
Before & After
❌ Without this prompt
Make me an automation for human approval gate for agents.
✅ With this prompt
Use the Human Approval Gate for Agents skill. Inputs: goal, systems, data fields, approval owner, and definition of done. Return the workflow, tests, guardrails, and approval checkpoint.
Install Instructions
Copy the body into Prompt Hub as a quality-gate. For Agent Skills, save as SKILL.md or paste into the target agent/project. For n8n/Make/Voiceflow, use this as the build blueprint before importing any third-party JSON.
Test It
Test command:
Run Human Approval Gate for Agents with a tiny dummy case and verify it returns the declared output format, missing-input warnings, guardrails, and pass criteria.
Expected output:
Approval card with risk rating, action summary, required confirmation, and block/pass result.
Pass criteria:
- Passes when the output is specific, complete, safe, testable, approval-aware where needed, and immediately usable with light editing.
⚠️ Guardrails
- Human approval is required before external sends, publishing, destructive changes, spending money, calendar booking, CRM updates that change customer status, or production system changes. Use least-privilege tool access.
📁 Context File Tip
Source context: Sabrina Ramonov describes agents.sabrina.dev as a free library of AI agents and automations, including n8n and Make templates. Related source: https://arxiv.org/abs/2510.26328. Agent-skill structure context: https://agentskills.io/home. Security context: https://arxiv.org/abs/2510.26328.
⚡ Automation
Agent Skills
🔌 MCP-compatible