skills.rest
AnXueHua
AnXueHuaCOMMUNITY
Explore all skills by this author →
GitHub

academic-orchestrator

Orchestrates iterative research loops within a Codex project repository using PowerShell scripts.

Updated Aug 23, 2026
Search Tags:#research#codex#orchestration#iteration#plan#loop
One-click install
npx skills add https://github.com/AnXueHua/auto-research --skill academic-orchestrator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: academic-orchestrator
Source: https://github.com/AnXueHua/auto-research/tree/main/skills/academic-orchestrator
Command: npx skills add https://github.com/AnXueHua/auto-research --skill academic-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codex, git, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Researchers often struggle to manage iterative experiment planning, execution, and review within a codebase, leading to fragmented state, missed insights, and repetitive manual steps.

Core Features & Use Cases

  • End‑to‑end loop orchestration: Initializes, drafts, executes, reviews, and iterates research plans stored in plan/ and temp/ directories.
  • Scientific rigor prompts: Provides PI‑style prompting and critique layers to keep hypotheses falsifiable and evidence‑driven.
  • Flexible continuation: Allows starting new loops or resuming existing ones, handling decisions such as accept, iterate, rollback, or archive.

Quick Start

Start a research loop in the current repository with the goal “test a new regularizer” and the identifier “regularizer_test”.

Frequently Asked Questions about academic-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate iterative research loops within a code repository?▼

Automating iterative research loops within a code repository is handled by orchestrating end-to-end experiment phases. The system initializes, drafts, executes, reviews, and iterates bounded experiments directly in your project directories during a Codex session.

What is the best way to keep research hypotheses falsifiable and evidence-driven during execution?▼

Keeping research hypotheses falsifiable and evidence-driven is achieved through built-in scientific rigor prompts. The orchestration loop applies PI-style prompting and critique layers to ensure your experiments maintain scientific standards.

Do I need PowerShell and Codex CLI to run repository-based experiment orchestration?▼

Yes, running repository-based experiment orchestration requires PowerShell scripting and a Codex CLI. Git is also optionally supported for state management to help track decisions like accept, iterate, rollback, or archive.

How do I resume an existing research plan after a bounded experiment pause?▼

Resuming an existing research plan after a bounded experiment pause is supported through flexible continuation. The orchestration loop allows starting new loops or resuming existing ones, handling decisions such as accept, iterate, rollback, or archive.

Where are research plans and temporary experiment states stored during a Codex session?▼

Research plans and temporary experiment states are stored in dedicated plan and temp directories within your project repository. This ensures your iterative execution state remains integrated directly in the codebase.

Related Skills

Explore More Education & Research Skills→
alansmelloalansmello

speckit-git-initialize

Initialize a Git repository with an initial commit in Bash or PowerShell.

Community
Intermediate
Wenwen555Wenwen555

experiment-bridge

Convert experiment plans into GPU-backed deployments and collect initial results.

Community
Advanced
skkeoriwskkeoriw

codex

Automate coding tasks with OpenAI Codex CLI in a git repository.

Community
Advanced
hachejhachej
45

autoresearch

Automate a bounded research, fix, and verification loop for project targets.

Community
Advanced