autoresearch SKILL.md skillA

autoresearch from mxyhi/ok-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mxyhi/ok-skills/autoresearch@v2.2.2

Pins v2.2.2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mxyhi/ok-skills
Path
autoresearch/SKILL.md
Versions recorded
5
Latest version
v2.2.2, committed Aug 15, 2026
First version recorded
May 24, 2026
Size
7,962 bytes
Repository stars
500
License
Apache-2.0

Autonomous iteration loop: modify, verify, keep/discard against any metric.

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 — Autonomous Goal-directed Iteration

## Safety Invariants (all subcommands)
- Never push, publish, or deploy without explicit user approval.
- Bounded by default. Override with `Iterations: unlimited`.
- All results logged to `autoresearch/{subcommand}-{YYMMDD}-{HHMM}/` directory.
- Chain handoff via `handoff.json`. Evals reads `*-results.tsv`.

## Dispatch (bare `$autoresearch`)

Parse the invocation in this order:

| Condition | Mode |
|---|---|
| `Metric:` or `Verify:` present | **Classic** — existing metric loop, unchanged |
| Free-form natural-language goal, no metric/verify | **Orchestrator** — see Orchestrator section |
| Nothing | **Setup wizard** — interactive config builder |
| `--classic` flag | Force Classic regardless of goal text |
| `--auto` flag | Force Orchestrator regardless of goal text |

Print a banner on every invocation: `[autoresearch] mode: classic | orchestrator | wizard`.

## Subcommands

| Command | Does | Default Iterations |
|---|---|---|
| `$autoresearch` | Iterate against a metric: modify → verify → keep/discard | 25 |
| `$autoresearch plan` | Convert a goal into validated Scope, Metric, Verify config | N/A |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mxyhi/ok-skills/autoresearch@sha256:93ee4758dee086eb

The line at the top of this page pins the label v2.2.2, 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_h7o4xlipkxtyrd47.svg)](https://markdownregistry.com/a/art_h7o4xlipkxtyrd47)

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

Versions

The registry has recorded 5 versions of this file, between May 24, 2026 and Aug 15, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
v2.2.2 latest2026-08-15 7a42862 7,962 BA view · diff
v2.2.12026-06-23 544e6ff 7,828 BA view · diff
v2.1.42026-06-19 4f06aed 2,281 BA view · diff
v2.1.32026-06-17 d75986b 2,168 BA view · diff
v2.1.02026-05-24 ee9f00b 2,160 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 (7962 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

mxyhi/ok-skills · 500 stars · license Apache-2.0 · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h7o4xlipkxtyrd47
GET https://markdownregistry.com/api/v1/resolve?ref=mxyhi/ok-skills/autoresearch
GET https://markdownregistry.com/api/v1/blob/93ee4758dee086eb72485deab662e50668aec4d23f0a13c8bc04b07eab356572

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 mxyhi/ok-skills

AGENTS.md AGENTS.md file
mxyhi/ok-skills · AGENTS.md
git:20260925.7de4640 · audit A · 500 stars
agent-browser SKILL.md skill
mxyhi/ok-skills · agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260831.972d952 · audit A · 500 stars
ai-elements SKILL.md skill
mxyhi/ok-skills · ai-elements/SKILL.md · Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and…
git:20260314.07e5678 · audit A · 500 stars
ax SKILL.md skill
mxyhi/ok-skills · ax/SKILL.md · Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or…
git:20260731.b493166 · audit A · 500 stars
better-icons SKILL.md skill
mxyhi/ok-skills · better-icons/SKILL.md · Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving…
git:20260415.87a17fa · audit A · 500 stars
bopomofo-rescue SKILL.md skill
mxyhi/ok-skills · bopomofo-rescue/SKILL.md · Detect and recover text that was accidentally typed with the Taiwanese Bopomofo / Zhuyin (注音) keyboard while the input…
git:20261018.2c986bf · audit A · 500 stars
browser-trace SKILL.md skill
mxyhi/ok-skills · browser-trace/SKILL.md · Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then…
git:20260517.ccd356a · audit A · 500 stars
codebase-design SKILL.md skill
mxyhi/ok-skills · codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
git:20260831.e7f2564 · audit A · 500 stars
deep-research SKILL.md skill
mxyhi/ok-skills · deep-research/SKILL.md · Professional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic…
v6.0.0 · audit A · 500 stars
diagnosing-bugs SKILL.md skill
mxyhi/ok-skills · diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20261009.b4e20e9 · audit A · 500 stars
domain-modeling SKILL.md skill
mxyhi/ok-skills · domain-modeling/SKILL.md · Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md…
git:20260930.4ade426 · audit A · 500 stars
exa-search SKILL.md skill
mxyhi/ok-skills · exa-search/SKILL.md · Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas…
git:20260905.9d9dd2c · audit A · 500 stars

Every file in mxyhi/ok-skills

Other files named autoresearch

autoresearch SKILL.md skill
github/awesome-copilot · skills/autoresearch/SKILL.md · Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable…
git:20260318.05f4d67 · audit A · 40,226 stars
autoresearch SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/autoresearch/SKILL.md · Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop…
git:20260419.5c5835a · audit A · 40,148 stars
autoresearch SKILL.md skill
orchestra-research/ai-research-skills · 0-autoresearch-skill/SKILL.md · Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid…
v1.0.0 · audit A · 13,718 stars
autoresearch SKILL.md skill
ericosiu/ai-marketing-skills · autoresearch/SKILL.md · Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated…
git:20260404.0076d34 · audit A · 3,676 stars
autoresearch SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/autoresearch/SKILL.md · Goal-directed research missions that interleave web research with data experimentation and end on a structured…
git:20260823.9983f32 · audit A · 3,016 stars
autoresearch SKILL.md skill
naveedharri/benai-skills · plugins/autoresearch/skills/autoresearch/SKILL.md · Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation…
git:20260916.a3b1e15 · audit A · 71 stars
autoresearch SKILL.md skill
naveedharri/benai-skills · plugins/all-skills/skills/autoresearch/SKILL.md · Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation…
git:20260916.a3b1e15 · audit A · 71 stars
autoresearch SKILL.md skill
adriannoes/awesome-agentic-ai · cursor-claude-codex/skills/autoresearch/SKILL.md · Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating…
git:20260926.71e9bd2 · audit A · 69 stars

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