SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

codex-autoresearchleo-lilinxiao/codex-autoresearch

Lets Codex run a self-directed "research, improve, research again" loop, so multi-round iteration that would otherwise n…

No ratings yet Rate this skill
Stars2.8k
Forks130
Watchers2.8k
Open Issues1

InstallOne-line install

Installable

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add leo-lilinxiao/codex-autoresearch

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

Where it runs

This skill has to be installed inside the client above before you can use it.

OverviewOverview

Key Features

Lets Codex run a self-directed "research, improve, research again" loop, so multi-round iteration that would otherwise need constant human prompting completes automatically. Key capabilities include: 1. Autonomous iteration loop: the skill drives Codex through consecutive task rounds, each building on the previous result without manual round-by-round instructions; 2. Self-directed research flow: research tasks are broken into repeatable steps so Codex explores, verifies and converges on a result on its own; 3. Codex CLI integration: delivered as a Codex skill that plugs into the Codex CLI workflow, triggering autonomous research loops directly from the command line.

Use Cases

Code improvement, plan investigation and experiment validation that need multiple trial rounds to reach a satisfactory result; unattended automation where an agent keeps running tasks with less repeated human prompting.

Target Roles

AI / Algorithm Engineer, Full-stack / Indie Developer, Backend Developer, DevOps / Operations Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID376
Data sourceGitHub
Repositoryleo-lilinxiao/codex-autoresearch
CategoryAI & Agent Development / Autonomous Agents & Automation Workflows
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1184866064
Node IDR_kgDORp-fEA
Rank#344 (position within the source ranking)
Site-wide popularity rank#413 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k2026-09-292026-10-112026-09-29 · 2,7222026-10-11 · 2,844
  • Now2,844
  • Previous point · 09-29 2,722
  • vs previous point +122
  • 2 data points 12 days
0501001502026-09-292026-10-112026-09-29 · 1302026-10-11 · 130
  • Now130
  • Previous point · 09-29 130
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-03-18 02:20:038 months ago
Data last updated2026-10-26 11:56:4321 days ago
Last commit2026-09-12 14:07:512 months ago

CommitLatest commit

Committed by leo-lilinxiao. Update Category: Refactoring & Structural Improvements. Commit details: Simplify skill guidance and experiment controls. This update restructures internal code for better maintainability, without behavior changes.

0f54c57 leo-lilinxiao 2026-09-12

Next stepsNext steps