autonomous-research SKILL.md skillA

autonomous-research from getedgehq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add getedgehq/skills/autonomous-research@git:20260929.978c99e

Pins git:20260929.978c99e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
getedgehq/skills
Path
autonomous-research/SKILL.md
Versions recorded
2
Latest version
git:20260929.978c99e, committed Sep 29, 2026
First version recorded
Sep 17, 2026
Size
32,675 bytes
Repository stars
5
License
Apache-2.0

An 18-agent pipeline that turns one topic line into a drafted.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Autonomous Research

Turns one topic line into a finished paper with a real literature base.

Ported from OpenDraft (github.com/federicodeponte/opendraft, MIT), which runs this
as a hosted engine. Here the engine is you: eighteen stages and one evidence
stage, each a prompt in `agents/`, plus the scripts that do the parts a language
model must not do by hand.

**You are the model.** No key, no service, no account. The only network calls are
Crossref, OpenAlex and DataCite, all open endpoints.

## The one command

```
Write a paper on <topic>
```

Everything below follows from that. Do not ask the user to run the stages
themselves; run them.

## Ask four things first

Before stage 5, if the user has not already said, ask for:

1. **Target venue**, or "none, general academic".
2. **Total word limit.**
3. **Citation style**, one of the six in `references/citation-styles.md`.
4. **Document type**, one of the types in `references/paper-types.md`.

These are four questions in one message, not an interview, and they are the only
questions the pipeline asks. Everything else it decides.

Ask because the cost of guessing lands at the end and cannot be paid there. A
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add getedgehq/skills/autonomous-research@sha256:56f886f221c9dd01

The line at the top of this page pins the label git:20260929.978c99e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rizr2zixd7jvoyq5.svg)](https://markdownregistry.com/a/art_rizr2zixd7jvoyq5)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 17, 2026 and Sep 29, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
git:20260929.978c99e latest2026-09-29 978c99e 32,675 BA view · diff
git:20260917.e0419832026-09-17 e041983 29,139 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (32675 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

getedgehq/skills · 5 stars · license Apache-2.0 · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rizr2zixd7jvoyq5
GET https://markdownregistry.com/api/v1/resolve?ref=getedgehq/skills/autonomous-research
GET https://markdownregistry.com/api/v1/blob/56f886f221c9dd01669abbfd3d06bb28eea2b6d3259ad441923d880e5adaf169

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from getedgehq/skills

abel-sell-the-alpha SKILL.md skill
getedgehq/skills · abel-sell-the-alpha/SKILL.md · Build an account-specific enterprise sales brief using Jen Abel's buyer-advantage method. Use for founder-led…
git:20261002.d5668a9 · audit A · 5 stars
agent-governance-gap-analysis SKILL.md skill
getedgehq/skills · agent-governance-gap-analysis/SKILL.md · Score an organisation's AI agent governance against 25 technical checks across 7 dimensions — agent inventory…
git:20260928.4a8b17a · audit A · 5 stars
agent-infra-fixer SKILL.md skill
getedgehq/skills · agent-infra-fixer/SKILL.md · Fix the agent's own environment when skill-miner surfaces infra-class failures - broken or over-broad hooks…
git:20260929.d19e06d · audit A · 5 stars
agent-receipt SKILL.md skill
getedgehq/skills · agent-receipt/SKILL.md · Create a compact, evidence-backed proof-of-work receipt for a completed AI agent run. Use when the user wants to…
git:20260920.deb764a · audit A · 5 stars
agent-skills-gap SKILL.md skill
getedgehq/skills · agent-skills-gap/SKILL.md · Analyze Claude or Codex session logs or pasted prompts to identify evidenced strengths, weak task categories, a…
git:20260920.a474e57 · audit A · 5 stars
ai-dna SKILL.md skill
getedgehq/skills · ai-dna/SKILL.md · Turn your own local ChatGPT, Claude Code, and Codex conversation history into a 4:5 AI DNA helix still and 12-second…
git:20260929.4160913 · audit A · 5 stars
ai-festival-poster SKILL.md skill
getedgehq/skills · ai-festival-poster/SKILL.md · Turn someone's real AI usage into a desert festival lineup poster, painted in Python. Scans local Claude Code and Codex…
git:20260924.9d39be8 · audit A · 5 stars
ai-team SKILL.md skill
getedgehq/skills · ai-team/SKILL.md · Set up a small AI team in Claude Code or Codex: a Chief of Staff that routes work on a board, role agents (product…
git:20261009.f111569 · audit A · 5 stars
albro-founder-brand SKILL.md skill
getedgehq/skills · albro-founder-brand/SKILL.md · Build a buyer-focused founder narrative, content plan, distribution routine, and revenue hook using Scott Albro's…
git:20261002.d5668a9 · audit A · 5 stars
anatomy SKILL.md skill
getedgehq/skills · anatomy/SKILL.md · Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical…
git:20261022.d91e25b · audit A · 5 stars
andy-raskin-strategic-narrative SKILL.md skill
getedgehq/skills · andy-raskin-strategic-narrative/SKILL.md · Build or review a buyer-centered strategic narrative using Andy Raskin's public method. Use for sales or investor deck…
git:20261002.d5668a9 · audit A · 5 stars
ar-aging-and-cash-application SKILL.md skill
getedgehq/skills · ar-aging-and-cash-application/SKILL.md · Build an accounts receivable aging report and apply incoming cash to invoices. Covers aging buckets, due dates from…
git:20261005.43cc1a8 · audit A · 5 stars

Every file in getedgehq/skills

Other files named autonomous-research

autonomous-research SKILL.md skill
eli-w-king/autonomous-output-skills · autonomous-research/SKILL.md · Autonomous: Research. User research, unattended: UserTesting think-out-loud tests and Outset AI-moderated interviews…
git:20261104.faacb66 · audit A · 3 stars

Browse by kind, by grade A, or by owner.