Is the AI4S Agent skill free?

Yes. The skill itself is free from ai4s-research/ai4s-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the AI4S Agent SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install AI4S Agent?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use AI4S Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

AI4S Agent

Meta-skill chaining explore, survey, experiment, and paper-writer for AI4S research

by ai4s-research · ai4s-research/ai4s-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 7ea2136

The meta-skill explicitly does no work of its own, it only orders four downstream skills, so a single-skill install leaves it broken; the honest install runs install.sh to bring in research-explorer, literature-survey, experiment-suite and paper-writer too. Its deterministic slug contract reproduced identical slugs across topics as specified, and the downstream literature-survey skill commendably forbids fabricated citations. Scored setup, not pass, because an honest end-to-end run (60-200 real web-fetched citations plus experiment execution and two LaTeX PDFs) is a multi-hour task not verifiable in context, so no baseline delta could be measured.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What AI4S Agent does

A pure-markdown meta-skill that orchestrates a four-stage AI-for-Science research pipeline (research-explorer, literature-survey, experiment-suite, paper-writer) end to end, sharing artifacts by a deterministic slug convention. Triggers when the user wants a whole research package on a topic; for a single stage it defers to the individual skill. Requires the full skill stack, LaTeX, and web access to actually run.

How to install AI4S Agent

git clone https://github.com/ai4s-research/ai4s-skills
mkdir -p ~/.claude/skills
cd ai4s-skills && SKILLS_DIR=~/.claude/skills ./install.sh   # installs the WHOLE stack; the meta-skill is non-functional without its 4 downstream skills

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger AI4S Agent

/ai4s-agent Meta-skill chaining explore, survey, experiment, and paper-writer for AI4S research

It also activates on plain-language prompts like these:

Run the full explore-survey-experiment-paper pipeline on this topic
Produce a literature survey and experiment suite for our new study
Generate a full paper draft starting from just our research topic

Frequently asked questions

Is the AI4S Agent skill free?: Yes. The skill itself is free from ai4s-research/ai4s-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does AI4S Agent work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. The meta-skill explicitly does no work of its own, it only orders four downstream skills, so a single-skill install leaves it broken; the honest install runs install.sh to bring in research-explorer, literature-survey, experiment-suite and paper-writer too. Its deterministic slug contract reproduced identical slugs across topics as specified, and the downstream literature-survey skill commendably forbids fabricated citations. Scored setup, not pass, because an honest end-to-end run (60-200 real web-fetched citations plus experiment execution and two LaTeX PDFs) is a multi-hour task not verifiable in context, so no baseline delta could be measured.
What is the AI4S Agent SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install AI4S Agent?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use AI4S Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.