Aeon Deep Research
- 14 installs
- 1.2k repo stars
- Updated August 1, 2026
- bankrbot/skills
aeon-deep-research is a Claude skill that produces analyst-grade, multi-source research memos with source-classed claims and a mandatory adversarial section.
About
aeon-deep-research is a skill for exhaustive multi-source research where every claim is tagged with its source class (primary, expert, secondary, market signal) and confidence. It requires an adversarial counterpoint section that names contradicting sources rather than averaging them, plus an open-questions list. Use it when the cost of being wrong exceeds an hour of research.
- Exhaustive multi-source research with claims tagged by source class and confidence
- Mandatory adversarial counterpoint section that names contradicting sources rather than averaging them
- Modes for full research, a brief top-5, or a contrarian dissent-biased take
Aeon Deep Research by the numbers
- 14 all-time installs (skills.sh)
- Ranked #1,417 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
aeon-deep-research capabilities & compatibility
No API keys stated; pulls from primary, expert, secondary and market sources.
- Capabilities
- deep research · adversarial analysis · source attribution
- Use cases
- research · web search
- Pricing
- Free
What aeon-deep-research says it does
Contradicting sources are named, not averaged. "Source A says X; source B says not-X; reconciliation: ..."
Adversarial section is mandatory. No skip on quiet days.
npx skills add https://github.com/bankrbot/skills --skill aeon-deep-researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 14 |
|---|---|
| repo stars | ★ 1.2k |
| Last updated | August 1, 2026 |
| Repository | bankrbot/skills ↗ |
What it does
Run analyst-grade multi-source research on a topic with attributed claims, a mandatory adversarial section and open questions.
Who is it for?
Due diligence and memos where being wrong is costly.
Skip if: Quick one-line summaries where an hour of research is overkill.
When should I use this skill?
You need deep research, DD, a memo, or a contrarian take on a topic.
What you get
A memo with a thesis, source-tagged findings, a named adversarial counterpoint and open questions.
- A memo: thesis, tagged findings, adversarial section, open questions, deduplicated sources
By the numbers
- 4 source classes (primary/expert/secondary/market)
- Brief mode returns top 5 findings
Files
aeon-deep-research
For when a one-line summary won't cut it. Pulls from primary sources first (filings, contracts, official docs), expert sources second (named researchers, audit reports), secondary third (media, newsletters), market signal last (price action, prediction markets) — and tags every claim with its source class.
Inputs
| Param | Description |
|---|---|
topic | Plain-English topic. Required. |
mode | research (default), brief (top 5 findings only), contrarian (bias toward dissent). |
Output structure
1. Thesis — one paragraph. 2. Findings — bullets, each tagged [primary] / [expert] / [secondary] / [market] and [established] / [likely] / [contested]. 3. Adversarial section — the sharpest counter-argument, sourced. Mandatory. If the consensus is genuinely right, explain why the dissent is weak. 4. Open questions — what would change the conclusion, and what data would resolve it. 5. Sources — deduplicated, primary first.
Rules
- Contradicting sources are named, not averaged. "Source A says X; source B says not-X; reconciliation: ..."
- Linked-tweet-citing-thread-citing-press-release is not Primary.
- Adversarial section is mandatory. No skip on quiet days.
- Open questions force honesty about what isn't known.
{
"schemaVersion": 1,
"slug": "aeon-deep-research",
"provider": "Aeon",
"providerUrl": "https://github.com/aaronjmars/aeon",
"logo": null,
"demo": {
"title": "deep-research.sh",
"language": "bash",
"code": "# Full memo on a topic\naeon-deep-research topic=\"L2 sequencer decentralization in 2026\"\n\n# Top 5 findings only\naeon-deep-research topic=\"EigenLayer restaking risks\" mode=brief\n\n# Bias toward dissent\naeon-deep-research topic=\"Polymarket vs Kalshi\" mode=contrarian"
},
"setup": [
"Install: `install the aeon-deep-research skill from https://github.com/BankrBot/skills/tree/main/aeon-deep-research`",
"Configure LLM + search provider keys in the agent runtime",
"Pick a mode: `research` (default), `brief`, or `contrarian`",
"Source: https://github.com/BankrBot/skills/tree/main/aeon-deep-research"
],
"install": {
"type": "bankr",
"repoPath": "aeon-deep-research",
"command": "install the aeon-deep-research skill from https://github.com/BankrBot/skills/tree/main/aeon-deep-research"
}
}
Related skills
Agent BrowserGive their coding agent reliable, high-fidelity control over any website or Electron desktop app.591k39.6k
Lark ApprovalLet their AI coding agent create, read, update, and approve items in Lark (Feishu) approval workflows without leaving the coding environment.494kLark EventHandle Feishu/Lark bot events, webhooks, and subscription callbacks in agent-driven backend code.493kLark Workflow Meeting SummaryAutomatically generate structured meeting summaries and action items from Lark/Feishu calls without manual note-taking.492kLark Workflow Standup ReportAutomatically generate and post daily standup reports in Lark/Feishu from their workflow and activity data.492k
Twitter AutomationAutomate X/Twitter posts, scheduling, and engagement via X API integration441k669FAQ
How does it handle conflicting sources?
Contradicting sources are named, not averaged: source A says X, source B says not-X, with an explicit reconciliation.
Is the adversarial section optional?
No. The adversarial section is mandatory and cannot be skipped even on quiet days.