auto-review-loop
Autonomous multi-round research review loop.
Skill by AI4Scientist
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ai4scientist-auto-review-loop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/auto-review-loop
Tools it pre-approves 10
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(*),Read,Grep,Glob,Write,Edit,Agent,Skill,mcp__codex__codex,mcp__codex__codex-reply
What's inside
- Skill name
auto-review-loop- Description
- Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
- License
- unknown
- Allowed tools
- Bash(*),, Read,, Grep,, Glob,, Write,, Edit,, Agent,, Skill,, mcp__codex__codex,, mcp__codex__codex-reply
- Instructions
- 456 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
- Instructions call the network
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from AI4Scientist/nano-scientist
- 0.677score
paper-planning
EvoScientist
Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning…
SkillCFreshness: C★ 128Claude Code +9 - 0.667score
paper-navigator
EvoScientist
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search)…
SkillCFreshness: C★ 128Claude Code +9 - 0.603score
paper-writing
EvoScientist
Guides writing academic papers section by section using an 11-step workflow with LaTeX templates and counterintuitive writing tactics.
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
research-ideation
EvoScientist
End-to-end research ideation pipeline: literature grounding → multi-track idea generation (3 personas: innovator/pragmatist/critic) → iterative refinement →…
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
experiment-pipeline
EvoScientist
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2…
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
paper-rebuttal
EvoScientist
Guides writing effective rebuttals after receiving peer review feedback.
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
research-survey
EvoScientist
Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey →…
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
experiment-iterative-coder
EvoScientist
Iterative code refinement through plan → code → evaluate → refine cycles.
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
evo-memory
EvoScientist
Manages persistent research memory across ideation and experimentation cycles.
SkillDFreshness: D★ 128Claude Code +9 - 0.603score
paper-review
EvoScientist
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing.
SkillDFreshness: D★ 128Claude Code +9 - 0.561score
comm-lit-review
AI4Scientist
Communications-domain literature review with Claude-style knowledge-base-first retrieval.
SkillCFreshness: C★ 128Claude Code - 0.556score
ablation-planner
AI4Scientist
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
SkillCFreshness: C★ 128Claude Code +9
Signals
- Stars
- 128
- Forks
- 20
- Open issues
- 1
- Last commit (this folder)
- May 10, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/AI4Scientist/nano-scientist
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AI4Scientist
- 0.561score
comm-lit-review
AI4Scientist
Communications-domain literature review with Claude-style knowledge-base-first retrieval.
SkillCFreshness: C★ 128Claude Code - 0.556score
research-review
AI4Scientist
Get a deep critical review of research from GPT via Codex MCP.
SkillCFreshness: C★ 128Claude Code +9 - 0.556score
ablation-planner
AI4Scientist
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
SkillCFreshness: C★ 128Claude Code +9 - 0.556score
experiment-audit
AI4Scientist
Audit experiment integrity before claiming results.
SkillCFreshness: C★ 128Claude Code +9 - 0.556score
citation-audit
AI4Scientist
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports.
SkillCFreshness: C★ 128Claude Code - 0.556score
overleaf-sync
AI4Scientist
Two-way sync between a local paper directory and an Overleaf project via the Overleaf Git bridge (Premium feature).
SkillCFreshness: C★ 128Claude Code +9
Cite this page
auto-review-loop skill. Agent Mart. https://agentmart.dev/skills/ai4scientist-auto-review-loop (last updated 2026-10-24)