autoresearch SKILL.md skillA

autoresearch from yichen-zju/claude-for-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yichen-zju/claude-for-research/autoresearch@git:20261008.414312a

Pins git:20261008.414312a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yichen-zju/claude-for-research
Path
skills/autoresearch/SKILL.md
Versions recorded
5
Latest version
git:20261008.414312a, committed Oct 8, 2026
First version recorded
Sep 30, 2026
Size
9,741 bytes
Repository stars
10
License
none declared

Autonomous experiment loop with evidence-driven move selection — scales from parameter tuning (directional search) to architecture innovation (structural changes), with git ledger, guard, noise-aware keep/discard, and trend-analysis stop advice. Use when the user asks to optimize a research metric, run an experiment loop, tune hyperparameters, explore architectural changes, or improve model performance iteratively.

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

自主实验循环。单策略表覆盖两种尺度:**参数级微调**(改大改小/换参数)和**架构级创新**(结构性改动)。

分工:本 skill 负责**运行**循环。两种入口:
- **完整任务包**(锁定评估 + 开放文件 + program.md,可交付的自驱包)→ 缺失时
  用 `experiment-forge` 锻造;
- **最小就地契约**(主控按"裸库直接迭代"路由到本 skill 时)→ **不造包**:
  就地生成/接受最小运行契约即可开跑——评测命令 + 指标名/单位/方向 +
  循环边界(maxIterations/timeout)写进 `autoresearch.md` 即算契约成立,
  不强制 program.md 与开放文件结构。

Session files: `autoresearch.md`, `autoresearch.sh`, `autoresearch.jsonl`, `results.tsv`, `run-<N>.log`.

**契约单一来源**:results.tsv 表头、循环边界、crash/revert、Guard、min_delta、日志命名的权威定义在 `experiment-forge/references/contract.md`。本文件与契约冲突时以契约为准。

## 两种运行模式

| | 交互式(默认) | 无人值守(`claude -p` / program.md 驱动) |
|---|---|---|
| 停止建议 | 只是建议,用户决定 | 不停止;停滞 → 强制"升级"选步 |
| 硬停止 | maxIterations / 用户打断 | maxIterations / timeout |
| 问用户 | 环境选择、计划确认、停滞建议 | 不问(NEVER STOP) |

**被 research-orchestrator 调用时**:视为无人值守 —— Step 1 的续跑/新开询问与 Step 2/3 的交互闸门(AskUserQuestion 环境选择、计划确认)**全部跳过**:orchestrator 的 BOOTSTRAP 双闸门 + state 文件即上游授权,scope/预算/环境/恢复意图以 research-state.yaml 为准。环境沿用调用方已确认的选择或任务包 program.md 的约定;若没有任何已确认配置且无法交互,报 `blocked` 而不是擅自假设。orchestrator 的 Gate 已经做过确认,这里不再二次确认。

## Step 0: 前置检查
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yichen-zju/claude-for-research/autoresearch@sha256:2163a09a64c547c0

The line at the top of this page pins the label git:20261008.414312a, 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_2pnmxwf355apqo4l.svg)](https://markdownregistry.com/a/art_2pnmxwf355apqo4l)

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

Versions

The registry has recorded 5 versions of this file, between Sep 30, 2026 and Oct 8, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261008.414312a latest2026-10-08 414312a 9,741 BA view · diff
git:20261007.f635cde2026-10-07 f635cde 9,370 BA view · diff
git:20261003.cd1abb42026-10-03 cd1abb4 9,168 BA view · diff
git:20261003.0767d992026-10-03 0767d99 8,181 BA view · diff
git:20260930.9b33ccf2026-09-30 9b33ccf 7,079 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 (9741 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

yichen-zju/claude-for-research · 10 stars · license none declared · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2pnmxwf355apqo4l
GET https://markdownregistry.com/api/v1/resolve?ref=yichen-zju/claude-for-research/autoresearch
GET https://markdownregistry.com/api/v1/blob/2163a09a64c547c0a838c7c94d8e37459316bb062ced2b19bbdfedf6bfcf46c5

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 yichen-zju/claude-for-research

CLAUDE.md CLAUDE.md file
yichen-zju/claude-for-research · CLAUDE.md
git:20260930.9b33ccf · audit A · 10 stars
CLAUDE.md@claude CLAUDE.md file
yichen-zju/claude-for-research · claude/CLAUDE.md
git:20261014.9f2a5e0 · audit A · 10 stars
evolving-ai-agents SKILL.md skill
yichen-zju/claude-for-research · claude/skills/a-evolve/SKILL.md · Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution…
v1.0.0 · audit A · 10 stars
academic-plotting SKILL.md skill
yichen-zju/claude-for-research · claude/skills/academic-plotting/SKILL.md · Generates publication-quality figures for ML papers from research context. Given a paper section or description…
v1.0.0 · audit A · 10 stars
academic-research-suite SKILL.md skill
yichen-zju/claude-for-research · claude/skills/academic-research-suite/SKILL.md · Claude-native Academic Research Skills suite (ported from the Codex adapter) for deep research, academic paper writing…
v0.1.14 · audit A · 10 stars
huggingface-accelerate SKILL.md skill
yichen-zju/claude-for-research · claude/skills/accelerate/SKILL.md · Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for…
v1.0.0 · audit A · 10 stars
ai-use-disclosure SKILL.md skill
yichen-zju/claude-for-research · claude/skills/ai-use-disclosure/SKILL.md · Generate venue-specific AI-use disclosure statements for manuscript submission (ICLR, NeurIPS, ICML, Nature, Science…
git:20261014.9f2a5e0 · audit A · 10 stars
alpha-research SKILL.md skill
yichen-zju/claude-for-research · claude/skills/alpha-research/SKILL.md · Search, read, and query research papers via the alphaxiv MCP server (2.5M+ arXiv papers). Use when the user asks about…
git:20261014.9f2a5e0 · audit A · 10 stars
alphafold2 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/alphafold2/SKILL.md · Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer…
git:20261014.9f2a5e0 · audit A · 10 stars
anti-defensive-writing-en SKILL.md skill
yichen-zju/claude-for-research · claude/skills/anti-defensive-writing-en/SKILL.md · Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments…
git:20261014.9f2a5e0 · audit A · 10 stars
anti-defensive-writing SKILL.md skill
yichen-zju/claude-for-research · claude/skills/anti-defensive-writing/SKILL.md · 论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会, 而不是项目总结、实验日志或自我审查报告:识别这项工作最值得发表的价值,围绕它建立…
git:20261014.9f2a5e0 · audit A · 10 stars
autoresearch SKILL.md skill
yichen-zju/claude-for-research · claude/skills/autoresearch/SKILL.md · Autonomous experiment loop with evidence-driven move selection — scales from parameter tuning (directional search) to…
git:20261014.9f2a5e0 · audit A · 10 stars

Every file in yichen-zju/claude-for-research

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
mxyhi/ok-skills · autoresearch/SKILL.md · Autonomous iteration loop: modify, verify, keep/discard against any metric
v2.2.2 · audit A · 504 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

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