autoresearch SKILL.md skillA
autoresearch from air-gapped/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add air-gapped/skills/autoresearch@git:20261027.75d87c7Pins git:20261027.75d87c7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- air-gapped/skills
- Path
.claude/skills/autoresearch/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261027.112d221, committed Oct 27, 2026
- First version recorded
- Aug 20, 2026
- Size
- 23,524 bytes
- Repository stars
- 5
- License
- MIT
Autonomous experiment loops that hill-climb a measurable metric — apply one change, measure, keep it only if the number improved, revert if not, repeat unattended. Also deep multi-perspective research producing a saved report, and research-then-optimize when no metric exists yet.
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
# Autoresearch An autonomous agent that finds improvements through measured experiments or deep research. Based on Karpathy's autoresearch pattern: separate what the human controls (strategy) from what the agent controls (execution), then let the agent iterate indefinitely with objective verification. ## Choosing a Mode | Mode | Command | When to use | |------|---------|-------------| | **Optimize** | `/autoresearch optimize` | There is code/config/prompt + a way to measure quality. Find improvements autonomously. | | **Research** | `/autoresearch research` | Deep, multi-source research on a topic with synthesis. | | **Improve** | `/autoresearch improve` | Improve something without a clear starting point. Research best practices first, then apply via the optimize loop. | When no mode is specified, infer from context: metric or benchmark mentioned → Optimize. Question or topic exploration → Research. Wants something "better" without a defined measure → Improve. --- ## Mode 1: Optimize (Experiment Loop) The core Karpathy pattern. A hill-climbing ratchet where only measurable improvements accumulate. ### Step 1: Configure the Experiment …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/autoresearch@sha256:933513370e3502aeThe line at the top of this page pins the label git:20261027.75d87c7, 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.
[](https://markdownregistry.com/a/art_25nqo6ha4vdwyeom)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 20, 2026 and Oct 27, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.112d221 latest | 2026-10-27 | 112d221 | 23,524 B | A | view · diff |
| git:20261027.75d87c7 | 2026-10-27 | 75d87c7 | 23,205 B | A | view · diff |
| git:20260822.e2384e1 | 2026-08-22 | e2384e1 | 22,902 B | A | view · diff |
| git:20260822.51de0a2 | 2026-08-22 | 51de0a2 | 22,895 B | A | view · diff |
| git:20260822.0c13ec8 | 2026-08-22 | 0c13ec8 | 22,635 B | A | view · diff |
| git:20260822.6a710a7 | 2026-08-22 | 6a710a7 | 21,952 B | A | view · diff |
| git:20260820.284d125 | 2026-08-20 | 284d125 | 21,584 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (23524 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
air-gapped/skills · 5 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_25nqo6ha4vdwyeom GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/autoresearch GET https://markdownregistry.com/api/v1/blob/933513370e3502aeff5d77442c063cc154386c2f4054e245e9239f3fab58db7a
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 air-gapped/skills
Every file in air-gapped/skills