RW Research Skill is a structured research assistant that decomposes research tasks into verifiable, handoff-ready steps across 4 public entry points and 21 internal skills, backed by knowledge atoms, axioms, and behavior contracts.

Stars

136

7-day growth

No data

Forks

19

Open issues

1

License

Apache-2.0

Last updated

2026-07-23

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It offers a modular, skill-based approach validated across four models in cross-model tests, with a clear public content policy and degradation handling, making research workflows auditable and reproducible.

Who it is for

  • Researchers with specific tasks (e.g., literature, writing, review)
  • PhD students and academic writers
  • Systematic review practitioners
  • Research methodologists

Use cases

  • Convert a rough research idea into a well-formed research question
  • Extract figures and evidence from papers while verifying key claims
  • Audit a study's method, statistics, and conclusions for weaknesses
  • Handle reviewer comments with targeted revisions and audit trails

Strengths

  • Organizes 21 specialized skills under 4 intuitive entry points
  • Cross-model validation shows +40.6 percentage point improvement over baseline on 8 synthetic tasks
  • Includes 540 knowledge atoms, 170 axioms, and 143 case/anti-case examples
  • Explicit degradation registry and public content policy ensure reliability and transparency

Considerations

  • Cross-model results are limited to the specific test tasks and model versions (v0.7.1), not proven for real research outcomes
  • Relies on Codex and Claude CLI with logged-in accounts; no API key is configured
  • Internal skills require explicit opt-in for installation and may not be discoverable by default

README quick start

安装

Description

Twelve standalone research workflow skills for questions, literature, evidence, design, writing, and submission.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482