agentrigs
+ submit rig
~ / rigs / ai4s-research / ai4s-skills

ai4s-research/ai4s-skills

Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.

↗ GitHub ★ 235 mit updated 2mo ago collection Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~510 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ai4s-research/ai4s-skills/skills ./rig-ai4s-skills/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit ai4s-research/ai4s-skills/skills/ai4s-agent .claude/skills/ai4s-agent
$ npx degit ai4s-research/ai4s-skills/skills/experiment-suite .claude/skills/experiment-suite
$ npx degit ai4s-research/ai4s-skills/skills/integrity-auditor .claude/skills/integrity-auditor
$ npx degit ai4s-research/ai4s-skills/skills/literature-survey .claude/skills/literature-survey
$ npx degit ai4s-research/ai4s-skills/skills/mindmap-render .claude/skills/mindmap-render
$ npx degit ai4s-research/ai4s-skills/skills/paper-writer .claude/skills/paper-writer
$ npx degit ai4s-research/ai4s-skills/skills/research-explorer .claude/skills/research-explorer

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (7)

ai4s-agentexperiment-suiteintegrity-auditorliterature-surveymindmap-renderpaper-writerresearch-explorer

Similar rigs

ARAVINDAN20/Claude-Research-Paper-OS
Drop-in .claude/ config that turns Claude Code into an autonomous academic paper production system. 6 agents, 47+ skills, 5-phase pipeline from literature search to submission-ready manuscript.
★ 6 collection Claude CodeCodexCursor 55 skills 6 agents 6mo ago
Orchestrator 6.3k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
★ 141k project Claude CodeCodex 1 mcp 3 skills 9d ago
Pragmatist 4.2k tok ·
copied ✓