Labyrinth Exploration

Map and advance open-ended research programmes in mathematics, theoretical science and algorithms. Use for pushing bounds, attacking open conjectures, mapping what is still unknown, or independently refereeing and integrating research from agents or external models. Maintain proof tiers, provenance, frontier data and a dashboard. Not for a single self-contained proof, a one-off literature question or ordinary code review.

47 stars 4 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add nasqret/labyrinth-exploration --skill labyrinth-exploration

Manual install

git clone --depth 1 https://github.com/nasqret/labyrinth-exploration.git /tmp/labyrinth-exploration
mkdir -p ~/.claude/skills
cp -r /tmp/labyrinth-exploration/. ~/.claude/skills/labyrinth-exploration

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Labyrinth exploration

Treat a research programme as the exploration of a labyrinth. The job is to know
exactly where you are: which corridors are charted (proved), which are walled off
(impossible, refuted), which doors are visible but unentered (questions, conjectures),
and where it is still dark. Progress means changing the map. A refutation is progress: it
turns a hoped-for corridor into a wall and usually reveals a new door.

This skill describes the method and the artifacts. A small public example runs out of the
box: `examples/triangle-counts/` asks how many triangles a graph on n vertices can have, and
builds a complete map and dashboard in seconds.

## Client setup

Use the same method in **Codex or Claude Code**. In Codex, read `references/codex.md`
before the first setup or agent campaign. Resolve bundled resources relative to this
installed `SKILL.md`, not the working directory. Keep the installed skill separate from
the research project: write generated files, reports and project memory in the project.
Use the client's available tools and respect the user's scope and existing authorization.

| read | when |
|---|---|
| `references/codex.md` | on first use in Codex: tools, delegation, permissions and local publishing |
| `references/loop.md` | before the first iteration, and whenever an iteration stalls |
| `references/campaigns.md` | before launching more than two or three agents (attackers, referees, writers) |

Read the full skill on GitHub

Details

Skill name: labyrinth-exploration
Repository: nasqret/labyrinth-exploration
License: MIT
Repo updated: 9 October 2026

FAQ

What does the Labyrinth Exploration skill do?

How do I install the Labyrinth Exploration skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add nasqret/labyrinth-exploration --skill labyrinth-exploration. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Labyrinth Exploration popular?

It lives in nasqret/labyrinth-exploration, which has 47 GitHub stars and 4 forks.

Related skills

Synthetic Market Research

BayramAnnakov/synthetic-market-research

Fast, cheap market research using LLM-generated synthetic survey responses with Semantic Similarity Rating (SSR). Runs purchase intent, concept tests, and pricing research in minutes instead of weeks, at $0 per respondent. Based on PyMC Labs' validated methodology (90% correlation with real humans across 57 surveys). Triggers: synthetic research, market research, survey, purchase intent, concept test, consumer research, SSR, synthetic survey, product validation, pricing research, Likert scale.

Research & Science

Research Craft

nik1t7n/research-craft-skill

Use when planning, reviewing, or improving research work: choosing research problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading information inputs beyond shared reading lists, and reasoning backward from outcomes the researcher genuinely wants to exist.

Research & Science

Paper Workflow

brycewang-stanford/Paper-WorkFlow

将社科实证研究从 idea、proposal、数据或已有结果推进到可复现分析和完整论文 DOCX。支持研究设计、数据审计、估计、表图、写作与修订，以及按需准备投稿包；按证据完成阶段，不承诺显著结果或录用。触发：/paper-workflow、从想法到论文、从数据到 docx、推进已有实证稿件。

Research & Science

Paper Explainer

PompeiiChan/skills-ExplainPaper

AI论文解读工具。面向产品经理、运营等非技术背景但对AI感兴趣的读者，将晦涩的学术论文转化为图文并茂的通俗研报：讲清楚”这个技术解决什么问题、有多厉害、对业务意味着什么”，配以极简科技风插图，并输出莫兰迪风格的 HTML 单文件。

Research & Science

Remote GPU Trainer

Hanyuyuan6/remote-gpu-trainer

AutoDL/vast.ai/RunPod/Lambda/Paperspace远程GPU启动、调试、监控、续训、并行、停止及卡住/OOM/NaN/全零指标排查；可验证状态/selection-best checkpoint/拉回结果。释放实例销毁机器及数据盘，不等同关机。长期镜像/恢复→mirror-research-artifacts。

Research & Science

Genesis Architect

maioio/genesis-architect

Use when starting a new project. Genesis finds real production failures from similar GitHub repos, then builds a working MVP immediately - not just documents. Two modes: fast-mvp (5 min research cap, builds right after) and deep-research (full analysis). Success = user can run the project. Triggers on: "genesis init [vision]", "I want to build X", "scaffold", "new project", "set up project", "start building", "create a tool", "make a CLI", "bootstrap", "בנה פרויקט", "צור פרויקט", "התחל פרויקט".

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.