Research Craft

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.

50 stars 3 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add nik1t7n/research-craft-skill --skill research-craft
Manual install
git clone --depth 1 https://github.com/nik1t7n/research-craft-skill.git /tmp/research-craft-skill
mkdir -p ~/.claude/skills
cp -r /tmp/research-craft-skill/. ~/.claude/skills/research-craft

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

From the SKILL.md

# Research Craft

Use this as a research-quality checklist, not as motivational prose.

Source: https://x.com/itsreallyvivek/article/2064686372737454155

## Core Bias

The default failure mode is looking like a researcher instead of doing research.
Do not optimize for paper-shaped activity, trending topics, or impressive jargon.
Optimize for choosing better problems, getting better inputs, learning faster
from reality, and writing down the reasoning before memory edits it.

Two mistakes deserve special pressure:

1. Absorbed problems.
   - Common mistake: inheriting a problem from an advisor, a famous lab, a viral paper, or a group chat without owning the reasoning.
   - Why it fails: the researcher copies the conclusion but not the causal model. They do not know why the direction matters, what evidence would weaken it, or what would make the original lab abandon it.
   - Cost: fashionable problems are crowded, often compute-heavy, and usually already ahead of the independent researcher.

2. Shared inputs.
   - Common mistake: reading the same arXiv trends, summaries, and social threads as everyone else.
   - Why it fails: shared reading lists produce shared ideas at the same time, which makes the resulting insight low-value.
   - Cost: the agent produces consensus-shaped plans instead of original research paths.

## Workflow

1. Choose the problem instead of absorbing it.
   - Ask what outcome should exist in the world.
Read the full skill on GitHub

Details

Skill name
research-craft
Repository
nik1t7n/research-craft-skill
License
MIT
Repo updated
15 June 2026

FAQ

What does the Research Craft skill do?

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.

How do I install the Research Craft skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add nik1t7n/research-craft-skill --skill research-craft. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Research Craft popular?

It lives in nik1t7n/research-craft-skill, which has 50 GitHub stars and 3 forks.

Related skills

Labyrinth Exploration

47

nasqret/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.

Research & Science

Paper Explainer

47

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

Synthetic Market Research

43

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

Genesis Architect

48

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

Paper Workflow

45

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

Paperbanana

59

PlutoLei/paperbanana-skill

Use when user needs academic diagrams, methodology figures, statistical plots, or presentation slides from text descriptions or data files. Also use for evaluating generated figures against references.

Research & Science

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