a-attia/scicomp-research-skills

Agent skills + workflow templates for scientific-computing research (papers and software). Forked from Master-cai/Research-Paper-Writing-Skills; restructured to the agents.md / OpenCode SKILL.md standard; adds a literature-survey skill (BibTeX + PDF + pdftotext + survey notes) and a paper-skeleton template. Multi-client, multi-machine.

This repository also configures its own agents. See what scicomp-research-skills tells them →

13Stars on the repository
8Mods indexed here, across every type
23d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

a-attia/scicomp-research-skills

Skill Claude Code

Use this skill at the start of any non-trivial session in this ecosystem -- the single biggest lever for reducing token / quota / context-window consumption and for keeping the agent productive across sessions. Make sure to load this whenever the work involves more than a few file reads, any PDF handling, multi-file…

not rated 13 changed 22d ago A SkillSpector: warn 210 tokens original MIT

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Author or revise any project document whose primary audience is a HUMAN -- README.md, PLAN.md, per-paper survey notes (notes/survey.md), bibliography collection logs (references/collectionlog.md), reviewer-response drafts, per-section research notes (notes/section.md), per-component implementation plans…

not rated 13 changed 22d ago A SkillSpector: warn 169 tokens original MIT

literature-survey

03

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Find, verify and maintain a literature-survey corpus for a research paper -- searching arXiv / OpenAlex / Crossref / zbMATH / OSTI / Semantic Scholar for candidates, then BibTeX entries, published-manuscript PDFs, text extractions for AI consumption, per-paper survey notes (30-50 lines each), and a collection log…

not rated 13 changed 22d ago A SkillSpector: warn 128 tokens original MIT

project-onboarding

04

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Use when adopting the scicomp-research-skills framework on an EXISTING project (paper, software library, analysis repo), or when about to do substantive work (drafting, refactoring, planning) in a directory with no AGENTS.md that looks like a research project (LaTeX sources, Python package, references/ + experiments/…

not rated 13 changed 22d ago A SkillSpector: warn 220 tokens original MIT

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or…

not rated 13 changed 22d ago A 68 tokens original MIT

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Use whenever a session will touch a scientific-computing codebase (numerical methods, PDE solvers, inverse problems, OED, UQ, scientific ML, or any code that produces numbers) in Python, Julia, C++, or other languages -- EVEN IF THE USER DOES NOT MENTION IT. Covers numerical correctness, testing, API design…

not rated 13 changed 22d ago A 236 tokens original MIT

a-attia/scicomp-research-skills

Skill Claude CodeCodex

Use when creating, revising or auditing a research talk or poster: conference and seminar talks, lab meetings, defenses, invited talks, funder or status briefings, posters. Applies to any toolchain (Beamer, Marp, PowerPoint, Keynote, reveal.js). Covers content and verification, not file mechanics: discovery of…

not rated 13 23d ago A 171 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: