RepoAlerts

wrencanfly/research-loop-skills

AI skill

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 9 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 9 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A set of seven portable Markdown skills that guide AI agents through bounded research: framing a question, mapping evidence to claims, choosing discriminating tests, executing checks, verifying conclusions and synthesizing a decision. Includes a zero-dependency Python checker…

Who it's for

Developers and researchers who use AI coding agents for evidence-based research and want traceable claims and reproducible checks

How to use it

Install

git clone https://github.com/wrencanfly/research-loop-skills.git

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up wrencanfly/research-loop-skills in my project. Follow its README: https://github.com/wrencanfly/research-loop-skills. Explain each step and check it is safe before running anything.

Star curve

49From 0 to 48 stars between 8 Nov 2026 and 17 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![wrencanfly/research-loop-skills on RepoAlerts](https://repoalerts.com/badge/wrencanfly/research-loop-skills.svg)](https://repoalerts.com/repo/wrencanfly/research-loop-skills?ref=badge)
Share on X

  • anthropics/single-agent-loop-kit

    A reference starter kit for moving a multi-agent system with a router and specialist subagents toward a single agent loop that loads skills and tools on demand. It audits subagents, scores changes on

    AI skillAI agentsPython · 561 stars · +26 this week · 33 days old

  • elayadesign/ai-design-skills

    A collection of design skills, each a self-contained folder of markdown rules for AI coding tools such as Claude Code, Cursor, Codex and Windsurf. Includes a landing-page design skill and a skill that

    AI skillAI agentsPython · 15,687 stars · +554 this week · 111 days old

  • ABLingss/awesome-agent-loops

    A curated directory of agent loop skills, workflow automation skills and cloud delivery recipes for DSH, Codex, Claude Code and compatible agents. Organized into sections covering DSH plugins, workflo

    ResourceAI agentsHTML · 108 stars · 12 days old

  • sno-ai/sno-station-skills

    A set of 31 tested skills that add team working habits to Claude Code and Codex. It provides cross-vendor peer review, automatic handoff when an agent's quota runs low, a one-page morning brief, work

    AI skillAI agentsShell · 865 stars · +1 this week · 47 days old

  • aicodeking/leanrea

    A single 8 KB agent skill file that gives AI coding agents routing rules and ready-to-run plain CLI commands for reverse engineering binaries, Electron apps and bundles, instead of an MCP server. It r

    AI skillAI agentsPython · 4,335 stars · +185 this week · 31 days old

  • udaysharmadev/Gravitas

    Portable Agent Skills and optional host hooks that make AI coding agents read files before editing, keep changes within declared scope, run validators, and require executed evidence before reporting c

    AI skillAI agentsPython · 490 stars · +36 this week · 70 days old