playbooks

home / skills / omer-metin / skills-for-antigravity / research

research skill

/skills/research

This skill helps you accelerate research and information gathering by leveraging AI tools for market and academic insights.

npx playbooks add skill omer-metin/skills-for-antigravity --skill research

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
1.2 KB
---
name: research-ai-tools
description: Master the AI tools that accelerate research and information gathering. From market research to academic analysis, find insights faster and make better decisions. Use when "research, find information, academic papers, market research, competitive intelligence, fact check, research, information, analysis, academic, market-research" mentioned. 
---

# Research Ai Tools

## Identity



## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill helps you master AI tools that accelerate research and information gathering across academic, market, and competitive contexts. It focuses on practical workflows, recommended tools, and patterns to obtain reliable insights faster. The skill enforces grounding in the provided reference files to ensure consistent creation, diagnosis, and validation of outputs.

How this skill works

The skill inspects three canonical reference files: references/patterns.md for how to construct research outputs, references/sharp_edges.md to diagnose common failure modes and risk factors, and references/validations.md to run objective checks against constraints. It produces stepwise workflows, tool recommendations, and validation reports that align with those references. When a requested task conflicts with the references, the skill corrects the request and proposes compliant alternatives.

When to use it

  • Gathering and summarizing academic literature or patents efficiently
  • Conducting market research or competitive intelligence briefs
  • Fact-checking claims and tracing source credibility
  • Designing reproducible research workflows and data collection plans
  • Validating research outputs against predefined constraints and standards

Best practices

  • Always consult references/patterns.md before designing outputs to follow established patterns
  • Use references/sharp_edges.md to anticipate and explain risks, biases, and failure modes
  • Run automated checks from references/validations.md to validate inputs and final results
  • Prioritize primary sources and document provenance for each key claim
  • Iterate: produce an initial evidence map, validate, and then refine conclusions

Example use cases

  • Create a 1-page market scan: tool list, key metrics, and validated sources following patterns.md
  • Summarize 10 academic papers into an evidence table and flag potential reproducibility issues using sharp_edges.md
  • Run a competitive intelligence checklist and produce a validated sensitivity analysis per validations.md
  • Fact-check a public claim by tracing citations, scoring source reliability, and delivering a provenance summary

FAQ

What does the skill require to produce validated outputs?

It requires access to the three reference files so it can apply patterns, diagnose risks, and run validations; without them it will request those files or refuse non-compliant tasks.

Can it recommend specific AI tools?

Yes — recommendations are paired with patterns and validation steps so you can adopt tools while maintaining reproducibility and risk awareness.