Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).
Scanned 5/30/2026
Install to Claude Code
npx -y skills add aiskillstore/marketplace --skill infinite-gratitude --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Infinite Gratitude?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aiskillstore-infinite-gratitude)More formats (shields.io, HTML) on the badges page.
---
name: infinite-gratitude
description: Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).
risk: safe
source: https://github.com/sstklen/infinite-gratitude
---
# Infinite Gratitude
> **Source**: [sstklen/infinite-gratitude](https://github.com/sstklen/infinite-gratitude)
## Description
A multi-agent research skill designed for parallel research execution. It orchestrates 10 agents to conduct deep research, battle-tested with real case studies.
## When to Use
Use this skill when you need to perform extensive, parallelized research on a topic, leveraging multiple agents to gather and synthesize information more efficiently than a single linear process.
## How to Use
This is an external skill. Please refer to the [official repository](https://github.com/sstklen/infinite-gratitude) for installation and usage instructions.
```bash
git clone https://github.com/sstklen/infinite-gratitude
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...