Home / naveedharri / benai-skills · plugins/autoresearch/skills/autoresearch/SKILL.md · GitHub

autoresearch skillA

autoresearch is agent-read markdown (skill) from naveedharri/benai-skills: Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's autoresearch..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# AutoResearch — Autonomous Optimization Loop

USE WHEN the user runs `/autoresearch`, says "autoresearch", "optimize this prompt", "improve this overnight", "run an optimization loop", "iterate on this", "auto-improve", or wants to autonomously refine a file against measurable criteria.

---

## Architecture: Separation of Roles

This skill supports two mutually exclusive evaluation modes. Both maintain four-way separation.

### Deterministic Mode (default) — Four-Way Separation

| Role | Who | Knows Eval Code? | Knows Prompt History? |
|------|-----|-----------------|----------------------|
| **Main Agent** | You (optimizer) | **NO** — reads metric number only | Yes — reads logs, plans changes |
| **Eval Agent** | `autoresearch-eval-agent` sub-agent | Yes — writes eval.py | No |
| **Test Runner** | `autoresearch-test-runner` sub-agent | **NO** — fresh context | **NO** |
| **Judge Script** | `eval.py` (deterministic Python) | IS the eval | No |

Metric: `pass_rate`. Best for tasks with clear, mechanical quality checks (word count, format, keywords, structure).

### AI Judge Mode (opt-in) — Four-Way Separation

| Role | Who | Knows Rubric? | Knows Prompt History? |
…

Read the whole file at its exact version.

How to install

Latest version
mdr add naveedharri/benai-skills/autoresearch@git:20260916.a3b1e15
Exact content
mdr add naveedharri/benai-skills/autoresearch@sha256:6722f11a72301365

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qsu3sjl3idkl5v66.svg)](https://markdownregistry.com/a/art_qsu3sjl3idkl5v66)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260916.a3b1e15 latest2026-09-16 a3b1e15 22,432 BA view · diff
git:20260407.4ef8f012026-04-07 4ef8f01 22,401 BA view · diff
git:20260402.19955422026-04-02 1995542 19,671 BA view · diff
git:20260402.848e70e2026-04-02 848e70e 19,011 BA view · diff
git:20260401.c80bab12026-04-01 c80bab1 13,896 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (22432 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

naveedharri/benai-skills · 65 stars · license MIT · pushed 2026-09-16 · branch develop

API

GET https://markdownregistry.com/api/v1/artifacts/art_qsu3sjl3idkl5v66
GET https://markdownregistry.com/api/v1/resolve?ref=naveedharri/benai-skills/autoresearch
GET https://markdownregistry.com/api/v1/blob/6722f11a72301365a36997ab879f1cbe60aefec668167fef7756f69750eddb98

Your agent 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.

More from naveedharri/benai-skills

CLAUDE.md claude
naveedharri/benai-skills · CLAUDE.md
git:20260911.3860544 · audit A · 65 stars
AGENTS.md@benai-landing agents
naveedharri/benai-skills · benai-landing/AGENTS.md
git:20260322.0d3e4c3 · audit A · 65 stars
CLAUDE.md@benai-landing claude
naveedharri/benai-skills · benai-landing/CLAUDE.md
git:20260322.0d3e4c3 · audit B · 65 stars
ads-audit skill
naveedharri/benai-skills · plugins/ads/skills/ads-audit/SKILL.md · Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn…
git:20260223.63345e4 · audit A · 65 stars
ads-budget skill
naveedharri/benai-skills · plugins/ads/skills/ads-budget/SKILL.md · Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy…
git:20260223.63345e4 · audit A · 65 stars
ads-competitor skill
naveedharri/benai-skills · plugins/ads/skills/ads-competitor/SKILL.md · Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy…
git:20260223.63345e4 · audit A · 65 stars
ads-creative skill
naveedharri/benai-skills · plugins/ads/skills/ads-creative/SKILL.md · Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms…
git:20260223.450945f · audit A · 65 stars
ads-google skill
naveedharri/benai-skills · plugins/ads/skills/ads-google/SKILL.md · Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74…
git:20260223.63345e4 · audit A · 65 stars
ads-landing skill
naveedharri/benai-skills · plugins/ads/skills/ads-landing/SKILL.md · Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience…
git:20260223.63345e4 · audit A · 65 stars
ads-linkedin skill
naveedharri/benai-skills · plugins/ads/skills/ads-linkedin/SKILL.md · LinkedIn Ads deep analysis for B2B advertising. Evaluates 25 checks across technical setup, audience targeting…
git:20260223.63345e4 · audit A · 65 stars
ads-meta skill
naveedharri/benai-skills · plugins/ads/skills/ads-meta/SKILL.md · Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 46 checks across Pixel/CAPI health…
git:20260223.63345e4 · audit A · 65 stars
ads-microsoft skill
naveedharri/benai-skills · plugins/ads/skills/ads-microsoft/SKILL.md · Microsoft/Bing Ads deep analysis covering search, Performance Max, Audience Network, and Copilot integration. Evaluates…
git:20260223.63345e4 · audit A · 65 stars

Every file in naveedharri/benai-skills

Other files named autoresearch

autoresearch 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 · 39,312 stars
autoresearch 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 · 39,368 stars
autoresearch 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 · 3,565 stars
autoresearch 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 · 2,847 stars
autoresearch skill
mxyhi/ok-skills · autoresearch/SKILL.md · Autonomous iteration loop: modify, verify, keep/discard against any metric
v2.2.2 · audit A · 490 stars
autoresearch 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:20260627.94fdd8b · audit A · 65 stars
autoresearch skill
akillness/jeo-skills · .agent-skills/autoresearch/SKILL.md · Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded…
v1.2.0 · audit B · 47 stars
autoresearch skill
tdimino/claude-code-minoan · skills/core-development/autoresearch/SKILL.md · Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up…
git:20260330.e8b27c0 · audit A · 41 stars

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