Source-Grounded Answer Gate
Source-Grounded Answer Gate
Agent Skills🔌 MCP-ready
Health
80/100
▲ 0
📋 0 copies
Trigger Phrase
Use the Source-Grounded Answer Gate skill
Prompt
262 words# QUALITY GATE: Source-Grounded Answer Gate
## Purpose
Check whether an answer includes unsupported factual claims, stale data, weak citations, or hidden assumptions.
## When to Use
Use this when the user needs to: Check whether an answer includes unsupported factual claims, stale data, weak citations, or hidden assumptions. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Answer to review
- Original question
- Sources used
- Freshness requirement
## Workflow
1. Identify the five most important factual claims
2. Verify each against a cited source or mark unsupported
3. Check whether any source is stale or irrelevant
4. Separate speculation from evidence
5. Return a fix list before publication
## Output Format
Citation audit table with claim, source, status, issue, and fix.
## 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 Source-Grounded Answer Gate and return the expected output structure plus any missing inputs.
## Purpose
Check whether an answer includes unsupported factual claims, stale data, weak citations, or hidden assumptions.
## When to Use
Use this when the user needs to: Check whether an answer includes unsupported factual claims, stale data, weak citations, or hidden assumptions. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Answer to review
- Original question
- Sources used
- Freshness requirement
## Workflow
1. Identify the five most important factual claims
2. Verify each against a cited source or mark unsupported
3. Check whether any source is stale or irrelevant
4. Separate speculation from evidence
5. Return a fix list before publication
## Output Format
Citation audit table with claim, source, status, issue, and fix.
## 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 Source-Grounded Answer Gate and return the expected output structure plus any missing inputs.
Before & After
❌ Without this prompt
Make me an automation for source-grounded answer gate.
✅ With this prompt
Use the Source-Grounded Answer Gate 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 Source-Grounded Answer Gate with a tiny dummy case and verify it returns the declared output format, missing-input warnings, guardrails, and pass criteria.
Expected output:
Citation audit table with claim, source, status, issue, and fix.
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://trigger.dev/blog/skills. Agent-skill structure context: https://agentskills.io/home. Security context: https://arxiv.org/abs/2510.26328.
⚡ Automation
Agent Skills
🔌 MCP-compatible