Is the ResearchClaw skill free?

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

What is the ResearchClaw SkillProof Score?

7.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 2/5.

How do I install ResearchClaw?

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 ResearchClaw 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.

ResearchClaw

Sets up, runs, and debugs the AutoResearchClaw 23-stage autonomous paper-writing CLI pipeline.

by OthmanAdi · OthmanAdi/researchclaw-skill

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e794557

Real bundled hooks work as advertised (live-ran check-prereqs.sh, pre-config-write.sh, pre-delete-guard.sh -- accurate detection, real config backup, real delete block), but the skill's own headline install command 'pip3 install researchclaw' actually installs a deprecated, unrelated PyPI package (an inactive tool by a different author that tells you to switch to 'cr-cli') due to a namespace collision -- verified live against PyPI; the config file it generates (config.yaml via /researchclaw:config) also doesn't match what the real upstream CLI expects (config.arc.yaml via `researchclaw init`, confirmed against the live upstream README).

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

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 2/5

What ResearchClaw does

Wraps the third-party AutoResearchClaw CLI (Docker + LaTeX + your own LLM API key) with guided prerequisite checks, an interactive config wizard, pipeline run/resume/status commands, and pattern-matched failure diagnosis across its 23 stages and 3 human-approval gates. Triggers on 'ResearchClaw', autonomous research/paper generation, or pipeline setup and debugging requests.

How to install ResearchClaw

git clone https://github.com/OthmanAdi/researchclaw-skill
mkdir -p ~/.claude/skills
cp -r researchclaw-skill/skills/researchclaw ~/.claude/skills/researchclaw

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

Commands — how to trigger ResearchClaw

/researchclaw Sets up, runs, and debugs the AutoResearchClaw 23-stage autonomous paper-writing CLI pipeline.

It also activates on plain-language prompts like these:

Help me set up ResearchClaw so I can run the autonomous paper pipeline
My ResearchClaw pipeline run failed at stage 12, can you diagnose it?
Walk me through configuring ResearchClaw with my own LLM API key

Frequently asked questions

Is the ResearchClaw skill free?: Yes. The skill itself is free from OthmanAdi/researchclaw-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does ResearchClaw work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Real bundled hooks work as advertised (live-ran check-prereqs.sh, pre-config-write.sh, pre-delete-guard.sh -- accurate detection, real config backup, real delete block), but the skill's own headline install command 'pip3 install researchclaw' actually installs a deprecated, unrelated PyPI package (an inactive tool by a different author that tells you to switch to 'cr-cli') due to a namespace collision -- verified live against PyPI; the config file it generates (config.yaml via /researchclaw:config) also doesn't match what the real upstream CLI expects (config.arc.yaml via `researchclaw init`, confirmed against the live upstream README).
What is the ResearchClaw SkillProof Score?: 7.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 2/5.
How do I install ResearchClaw?: 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 ResearchClaw 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.