Retrieval-Led Research Skill
Retrieval-Led Research Skill
Agent Skills🔌 MCP-ready
Health
80/100
▲ 0
📋 0 copies
Trigger Phrase
Use the Retrieval-Led Research Skill skill
Prompt
270 words# SKILL: Retrieval-Led Research Skill
## Purpose
Make agents ground research in retrieved sources instead of memory, especially for current, niche, legal, financial, technical, or market claims.
## When to Use
Use this when the user needs to: Make agents ground research in retrieved sources instead of memory, especially for current, niche, legal, financial, technical, or market claims. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Research question
- Required source type
- Date sensitivity
- Citation format
- Decision to support
## Workflow
1. Classify whether freshness is required
2. Search for primary or authoritative sources first
3. Compare source dates and conflicts
4. Separate facts from inference
5. Return citations beside the claims they support
## Output Format
A cited research brief with source quality notes and confidence level.
## 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 Retrieval-Led Research Skill and return the expected output structure plus any missing inputs.
## Purpose
Make agents ground research in retrieved sources instead of memory, especially for current, niche, legal, financial, technical, or market claims.
## When to Use
Use this when the user needs to: Make agents ground research in retrieved sources instead of memory, especially for current, niche, legal, financial, technical, or market claims. It is designed for repeatable agent or automation work, not one-off fluffy prompting.
## Inputs Required
- Research question
- Required source type
- Date sensitivity
- Citation format
- Decision to support
## Workflow
1. Classify whether freshness is required
2. Search for primary or authoritative sources first
3. Compare source dates and conflicts
4. Separate facts from inference
5. Return citations beside the claims they support
## Output Format
A cited research brief with source quality notes and confidence level.
## 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 Retrieval-Led Research Skill and return the expected output structure plus any missing inputs.
Before & After
❌ Without this prompt
Make me an automation for retrieval-led research skill.
✅ With this prompt
Use the Retrieval-Led Research Skill 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 skill. 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 Retrieval-Led Research Skill with a tiny dummy case and verify it returns the declared output format, missing-input warnings, guardrails, and pass criteria.
Expected output:
A cited research brief with source quality notes and confidence level.
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