autoresearch SKILL.md skillA

autoresearch from yeachan-heo/gajae-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yeachan-heo/gajae-code/autoresearch@git:20260823.9983f32

Pins git:20260823.9983f32 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yeachan-heo/gajae-code
Path
packages/coding-agent/src/defaults/gjc/skills/autoresearch/SKILL.md
Versions recorded
5
Latest version
git:20260823.9983f32, committed Aug 23, 2026
First version recorded
Aug 23, 2026
Size
14,554 bytes
Repository stars
3,048
License
MIT

Goal-directed research missions that interleave web research with data experimentation and end on a structured best-effort verdict.

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 Workflow

Use when the user asks for `autoresearch`, or gives a bounded research goal whose deliverable is a defensible verdict rather than code ("find out", "investigate", "benchmark and draw a conclusion").

## Usage

```
/skill:autoresearch "<research goal>"
/skill:autoresearch --spec .gjc/_session-{sessionid}/specs/deep-interview-<slug>.md
```

Invoke this workflow as `/skill:autoresearch`; the durable state behind it is driven by the `gjc autoresearch` runtime command.

## Purpose

`autoresearch` runs one goal-directed research mission: it interleaves web research with data/environment experimentation and ends on a single structured, best-effort verdict. The verdict receipt carries a structured `status`, `evidence[]`, `caveats[]`, and the `evaluator` identity that issued it. The mission is research, NOT implementation: its durable outputs are findings, evidence, run records, and a verdict — never product code.

All mission state persists per session under `.gjc/_session-{sessionid}/autoresearch/` and survives across `gjc autoresearch` invocations. The global `~/.gjc/autoresearch` store is never written.

## Always-used command examples
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yeachan-heo/gajae-code/autoresearch@sha256:babcb5bea9cfad59

The line at the top of this page pins the label git:20260823.9983f32, 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_vawu75isrvzogjdt.svg)](https://markdownregistry.com/a/art_vawu75isrvzogjdt)

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

Versions

The registry has recorded 5 versions of this file, all committed on Aug 23, 2026.

versioncommittedcommitsizeaudit
git:20260823.9983f32 latest2026-08-23 9983f32 14,554 BA view · diff
git:20260823.a9977ce2026-08-23 a9977ce 14,512 BA view · diff
git:20260823.df6c7dd2026-08-23 df6c7dd 14,281 BA view · diff
git:20260823.74974272026-08-23 7497427 14,007 BA view · diff
git:20260823.3910bc62026-08-23 3910bc6 11,991 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 (14554 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

yeachan-heo/gajae-code · 3,048 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vawu75isrvzogjdt
GET https://markdownregistry.com/api/v1/resolve?ref=yeachan-heo/gajae-code/autoresearch
GET https://markdownregistry.com/api/v1/blob/babcb5bea9cfad5985364ff2be56884b4da42b3496d25bc20d688612e44d13fa

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 yeachan-heo/gajae-code

AGENTS.md AGENTS.md file
yeachan-heo/gajae-code · AGENTS.md
git:20261019.e502489 · audit A · 3,048 stars
deep-interview SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating before explicit execution approval
git:20261002.66fedd0 · audit A · 3,048 stars
ralplan SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/ralplan/SKILL.md · Consensus planning entrypoint that auto-gates vague ultragoal requests before execution
git:20261002.66fedd0 · audit A · 3,048 stars
ultragoal SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/src/defaults/gjc/skills/ultragoal/SKILL.md · Create and execute durable repo-native multi-goal plans over GJC goal mode artifacts.
git:20260925.0c57473 · audit A · 3,048 stars
DESIGN.md@packages/coding-agent/src/modes DESIGN.md file
yeachan-heo/gajae-code · packages/coding-agent/src/modes/DESIGN.md
git:20261015.6dd9f11 · audit A · 3,048 stars
executor-design SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/combined-pack/subskills/executor-design/SKILL.md · Adds combined pack design guidance for executor prompts.
git:20260605.e17540f · audit A · 3,048 stars
ralplan-design SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/combined-pack/subskills/ralplan-design/SKILL.md · Adds combined pack design guidance for ralplan planning.
git:20260605.e17540f · audit A · 3,048 stars
one SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-arg/subskills/one/SKILL.md · First duplicate arg.
git:20260605.e17540f · audit B · 3,048 stars
two SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-arg/subskills/two/SKILL.md · Second duplicate arg.
git:20260605.e17540f · audit B · 3,048 stars
one SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-parent-phase/subskills/one/SKILL.md · First duplicate phase.
git:20260605.e17540f · audit B · 3,048 stars
two SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/duplicate-parent-phase/subskills/two/SKILL.md · Second duplicate phase.
git:20260605.e17540f · audit B · 3,048 stars
reviewer SKILL.md skill
yeachan-heo/gajae-code · packages/coding-agent/test/fixtures/gjc-plugins/invalid-parent/subskills/reviewer/SKILL.md · Invalid reviewer parent.
git:20260605.e17540f · audit B · 3,048 stars

Every file in yeachan-heo/gajae-code

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 · 40,629 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:20261020.b80c7a2 · audit A · 40,492 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 · 14,233 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 · 3,761 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 · 509 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 · 92 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 · 78 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 · 78 stars

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