Best reproducible research skills for Claude Code, Codex and other agents.

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.

K-Dense-AI/claude-scientific-writer

Prepares setup instructions and a named activation file for a user-managed software environment on an Open-Science SSH or Slurm compute host.

aipoch/open-science

Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.

xjtulyc/MedgeClaw

Experiment executor and monitor for academic research. An agent skill from Imbad0202/experiment-agent.

Imbad0202/experiment-agent

Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots.

aipoch/open-science

Read and critically analyze one academic paper from an arXiv URL/ID or a local PDF, producing a source-grounded Markdown report that can grow from a quick read into a reviewer-level deep review.

YSQ-boop/paper-lens

Scaffold a complete Bactopia Tool across all three tiers -- module, subworkflow, and workflow entry point under workflows/bactopia-tools/.

bactopia/bactopia

Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.

yushui2022/MathModel-Skill

Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.

Light0305/Light-skills

Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

K-Dense-AI/scientific-agent-skills

Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

lingzhi227/agent-research-skills

Review and revise academic papers with a senior-reviewer workflow.

M1n-n9/paper-lifecycle

Judge and reshape the story told by an entire paper figure deck.

aipoch/open-science

Independently verify Lean mathematical proofs in awards PRs, Erdős problems, or pinned source revisions.

TheJustinSunPrize/awards

Propagate the Bactopia and nf-bactopia versions declared in versions.yml into the hand-maintained files that carry a literal version (conf/testbase.config, CITATION.cff, bin/bactopia…

bactopia/bactopia

Teaches an agent to inspect Open-Science's JavaScript control REPL, check which host.* calls are allowed, and find project files, sessions and agent frames.

aipoch/open-science

A skill your agent uses when implementing, extending, auditing, or QAing LLM Chess data/cross-ref workflows: external eval source snapshots, conservative model mapping, runcrossref.py commands…

maxim-saplin/llm_chess

Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report.

xjtulyc/MedgeClaw

Regenerate nextflow.config and nextflowschema.json for Bactopia workflows by running bactopia-merge-schemas.

bactopia/bactopia

Runs a staged pipeline for mathematical modeling research and contest papers, from problem analysis and computation to paper writing, review rounds and submission checks.

WuXinbo-bo/Math-model-skills

Turns uploaded photos, voice notes, text or local files into standardized experiment logs in Markdown with YAML frontmatter, optionally through Feishu CLI and Obsidian.

Yuan1z0825/nature-skills

A skill your agent uses when reviewing mathematical validity, evidence, reproducibility, figures or a submission draft.

sweetcornna/mathodology

Refresh README benchmark results from a successful GitHub Actions Benchmark run, preserving data provenance and separate development, build, and memory tables.

rstackjs/build-tools-performance

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

pytorch/pytorch

Runs systematic, scoping or narrative literature reviews across PubMed, arXiv, bioRxiv and Semantic Scholar, with citation checks and Markdown or PDF output.

K-Dense-AI/scientific-agent-skills

Validate the get-started experience of Open Edge Platform (OEP) software components from the perspective of a first-time user.

open-edge-platform/edge-ai-suites

Runs reproducible math computations and counterexample searches with SymPy, NumPy and mpmath, logging evidence without presenting results as proofs.

tradecatlabs/vibe-coding-cn

Math modeling stage that turns an analysis report into reproducible code, validates the solutions, writes RESULTS_REPORT.md and produces data-driven PDF charts for the paper.

jihe520/MathModelAgent

Sets up and maintains AzureML-ready Python projects as uv workspaces with devcontainers, a Makefile and job YAML, so local runs match cloud jobs and experiments stay reproducible.

Kilo-Org/kilo-marketplace

Manage training checkpoints — export from the slime container to the host .ckpts/ directory with a runinfo.txt for full reproducibility.

cua-lite/cua-lite

Manages biological datasets with LaminDB: versioned artifacts, run lineage, ontology-based annotation, schema validation and links to workflow managers and ML tools.

davila7/claude-code-templates

Test quality assurance workflow for LeetCode problems - verifies reproducibility, fixes linting issues, and ensures test structure matches JSON templates.

wislertt/leetcode-py

Pipeline stage that turns a mathematical modeling report into runnable programs per sub-question, frozen numerical results and reviewable evidence files.

WuXinbo-bo/Math-model-skills

Compose one publication-grade multi-panel figure. An agent skill from aipoch/open-science.

aipoch/open-science

Critically review, score, compare, and rank one or more AI scientist outputs for biology, bioinformatics, computational life science, or adjacent research tasks.

BioTender-max/awesome-bio-agent-skills

This skill should be used when the user asks to "reproduce a paper", "implement paper code", "paper2code", "replicate research results", "run experiment from paper", "implement the algorithm from…

jerry609/PaperBot

Rules and reliable local tests for keeping Campfire's foss flavor F-Droid-compatible — a clean source scan (using scandelete, never scanignore) and a byte-for-byte reproducible build.

r0adkll/Campfire

Latch platform for bioinformatics workflows. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Review staleness of reference docs under .agents/docs/ using bactopia-docs --validate.

bactopia/bactopia

Turns papers, repositories, logs or notes into an Agent-Native Research Artifact with claims, concepts, configs, an exploration graph and grounded evidence.

Orchestra-Research/AI-Research-SKILLs

Drafts or audits data and code availability statements, dataset access routes, repository plans and FAIR metadata for Nature-style manuscripts.

Yuan1z0825/nature-skills

Diagnose Remotion implementation and render defects: font fallback, text jitter, local-frame timing, transition seams, wall-clock CSS, WebGL output and export reproducibility.

Remocn/remocn-studio

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote…

aipoch/open-science

Build the deterministic evidence ledger (artifactmanifest.json + claims.json) that every other Anti-Autoresearch auditor reads.

wanshuiyin/Anti-Autoresearch

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I.

tradermonty/claude-trading-skills

Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs.

BioTender-max/awesome-bio-agent-skills

Orchestrates a research paper from literature review through code, experiments, figures, tables, writing and review, with state passed between phases and checkpoints to resume.

lingzhi227/agent-research-skills

Orchestrates AI-assisted research across coding, figure production and writing, picking the right tool for each stage while keeping academic judgment with the researcher.

HKUSTDial/Supervisor-Skills