Updated 2w ago
by koaeraser
ARMS
Autonomous Research Manuscript Skills — domain-agnostic pipeline for academic paper production with Claude Code
34 GitHub stars (34)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 13 skills (13 skills found in its SKILL.md files)
- 4 forks (4 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add koaeraser/ARMS
Asks which skills and agents to install. Just one: npx skills add koaeraser/ARMS --skill brief-expander — add -g for every project.
Claude Code
git clone https://github.com/koaeraser/ARMScp -r "ARMS/skills/brief-expander" ~/.claude/skills/
Copies the brief-expander skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add koaeraser/ARMS
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
brief-expander
Takes a minimal research idea (even one sentence) and expands it into a complete research brief that can drive the 10-skill pipeline. Performs web search, literature scanning, and field analysis to fill in problem statement, data assets, domain context, target venue, success criteria, comparators, adjacent fields, and evaluation design. Usage: /brief-expander "your research question or idea"
skills/brief-expander/SKILL.md on GitHub (opens in a new tab) -
critic-revisor
Autonomous adversarial critic-revisor loop on a LaTeX manuscript. Two parallel Opus reviews per round with differentiated angles (methodologist + applied/ contextual reader); reviewers can web-search within a per-round budget; Codex CLI applies the combined review; latexmk rebuilds the clean PDF; latexdiff produces a color-tracked PDF. Repeats until both reviewers say accept, no diff is produced,…
skills/critic-revisor/SKILL.md on GitHub (opens in a new tab) -
house-style
Exemplar-based house voice for LaTeX manuscripts: a reader-first standard judged against an approved exemplar, a house-voice rewrite that never changes meaning, numbers, citations, or defined terms, and advisory style metrics (sentence length, paragraph length, first-person plural, semicolons, numbers in prose) printed beside the exemplar's values. The exemplar can be replaced with your own via -…
skills/house-style/SKILL.md on GitHub (opens in a new tab) -
literature-lead
No description in the SKILL.md.
skills/literature-lead/SKILL.md on GitHub (opens in a new tab) -
methodology-architect
Methodology reasoning agent. Reads literature deeply, identifies combinations of existing ideas that address gaps, assesses societal impact, and produces a methodology specification. Can be invoked standalone (pre-brief) or by write-paper/auto-research when methodology revision is needed. Usage: /methodology-architect problem_statement.md [literature_dir/]
skills/methodology-architect/SKILL.md on GitHub (opens in a new tab) -
paper-critic
No description in the SKILL.md.
skills/paper-critic/SKILL.md on GitHub (opens in a new tab) -
paper-fixer
No description in the SKILL.md.
skills/paper-fixer/SKILL.md on GitHub (opens in a new tab) -
paper-grader
No description in the SKILL.md.
skills/paper-grader/SKILL.md on GitHub (opens in a new tab) -
paper-modeler
No description in the SKILL.md.
skills/paper-modeler/SKILL.md on GitHub (opens in a new tab) -
paper-writer
No description in the SKILL.md.
skills/paper-writer/SKILL.md on GitHub (opens in a new tab) -
research-pipeline
No description in the SKILL.md.
skills/research-pipeline/SKILL.md on GitHub (opens in a new tab) -
validate-method
No description in the SKILL.md.
skills/validate-method/SKILL.md on GitHub (opens in a new tab) -
write-manuscript
No description in the SKILL.md.
skills/write-manuscript/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs…