research-review
Skill17 starsChanged 3 months agoMITView on GitHub
Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
18 other projects use a version of this, 11 of them edited.
Adopted by
Most recently taken up by
- AfonsoZhang/auto-research-systemedited, first seen Nov 15, 2026
- WilliamEbong/CourseForgetheir own version, first seen Nov 8, 2026
- sjtuytc/ResearchMathAgentedited, first seen Oct 20, 2026
- charly-vibes/incitacionestheir own version, first seen Oct 14, 2026
- Yulivu/debuffer-skillsedited, first seen Oct 13, 2026
- yvesory/academic-research-suiteedited, first seen Oct 9, 2026
Used with
Projects with it also use resubmit-pipeline, experiment-bridge and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
raja21068Skillresubmit-pipeline
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Phase 0 physical isolation, Phase 0.5 health + anonymity check, Phase 1 audit (proof / claim / citation), Phase 2 microedits via auto-loop with edit-whitelist + citation-audit --soft-only, Phase 3 kill-argument adversarial gate, Phase 4 final compile + Overleaf push via /overleaf-sync. Use when user says \"resubmit pipeline\", \"重投流程\", \"port paper to <new venue>\", \"resubmit to <venue>\", \"tighten paper for resubmission\", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
Also in 5 projects that use this
raja21068Skillexperiment-bridge
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says \"实现实验\", \"implement experiments\", \"bridge\", \"从计划到跑实验\", \"deploy the plan\", or has an experiment plan ready to execute.
Also in 4 projects that use this
PostHogSkillexperiment-audit
Audit a PostHog A/B experiment for a customer — verify config, exposure, attribution, and metrics. Trigger phrases include \"audit [customer]'s experiment\", \"audit the [name] experiment\", \"check experiment setup for [customer]\", \"validate this A/B test\", or any request to review whether an experiment is correctly wired up. Assumes you already have MCP access to the customer's project (typically via the impersonation flow set up by the `impersonate-audit` wrapper that ships with this plugin).
Also in 4 projects that use this
rongaredeSkillsemantic-scholar
使用 Semantic Scholar API 检索和验证学术论文。支持并发多关键词搜索、批量 ID/DOI 查询、引用分析、批量补全摘要、统一 Markdown 导出。覆盖 2.14 亿+ 学术论文,无需 API Key 即可使用。触发词:论文检索、论文验证、Semantic Scholar、S2 搜索、查论文、补全摘要、导出MD
Also in 6 projects that use this
- +8 more from raja21068
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 11
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k61% same
- zjunlp/Mechanist★ 7548% same
- sjtuytc/ResearchMathAgent★ 3595% same
- catalsqlb-cmd/Prism-H★ 1677% same
- Yulivu/debuffer-skills★ 955% same
- yvesory/academic-research-suite★ 996% same
- Yusong-Enceladus/claude-skills★ 882% same
- raja21068/AutoResearch★ 278% same
- Shri-Phnx/claude-skills★ 250% same
- AfonsoZhang/auto-research-system★ 140% same
1 more not listed
Wrote their own version · 7
- advaitpaliwal/feynman★ 10ksame name
- companion-inc/feynman★ 10ksame name
- getcompanion-ai/feynman★ 10ksame name
- tsingyuai/scientify★ 2.2ksame name
- hisazumi/paper-review-skills★ 4same name
- charly-vibes/incitaciones★ 0same name
- WilliamEbong/CourseForge★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- ai4ai-model-optimizerSkill
- auto-discovery-loggerSkill
- cross-model-verifierSkill
- handoffSkill
- research-context-checkpointSkill
- analyze-resultsSkill
- auto-review-loopSkill
- collaborating-with-codexSkill
- idea-discoverySkill
- monitor-experimentSkill
- research-litSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 4 are common, 2 are distinctive, and 8 are very specific to this project.
4
Common
Most of the 16 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
When calling the reviewer, branch on REVIEWER_BACKEND:
- Very specific: line 30
Use mcp__codex__codex for new review threads.
- Very specific: line 31
Use mcp__codex__codex-reply for follow-up rounds (reuse threadId).
- Very specific: line 34
Use mcp__manual_review__review for new review threads with: prompt: [exact same prompt that would go to Codex] config: …
- Very specific: line 38
Use mcp__manual_review__review_reply for follow-up rounds with: threadId: [saved manual-review threadId] prompt: [follow-up prompt] config: …
- Common: line 62
Before calling the external reviewer, compile a comprehensive briefing:
- Common: line 63
Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
- Common: line 64
Read any memory/notes files for key findings and experiment history
- Very specific: line 105
Use the appropriate tool to continue the conversation.
- Common: line 148
Update project memory/notes with key review conclusions.
- Very specific: line 162
ALWAYS pin model: gpt-5.6-sol + config: {"model_reasoning_effort": "ultra"} for reviews (deep-audit tier.
- Distinctive: line 163
Put comprehensive context in the review brief.
- Distinctive: line 169
Document the threadId for potential future resumption
- Very specific: line 191
After each reviewer call (mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, or mcp__manual_review__review_reply), …
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Research Review via External Reviewer Backend (ultra reasoning)
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. It is verdict-bearing — it produces a cross-model review verdict, multi-round with reviewer thread continuity. An external timer re-fires the verdict on wall-clock time and breaks the reviewer's round-to-round memory: zero new signal, full token cost. Schedule the external wait that precedes it (work ready → then review once), not the verdict. Seeshared-references/external-cadence.md.
Get a multi-round critical review of research work from the selected external reviewer backend with maximum reasoning depth.
Constants
- REVIEWER_MODEL =
gpt-5.6-sol— Default model for the Codex backend, reasoning effortultra(deep-audit tier). Must be an OpenAI model (e.g.,gpt-5.6-sol,gpt-5.5,o3). Manual backend uses whatever model the user chooses. - REVIEWER_BACKEND =
codex— Default: Codex MCP (ultra). Override with— reviewer: oracle-profor Oracle MCP, or— reviewer: manualfor Manual Review MCP. If manual-review MCP is unavailable, stop and print the install command; do not fall back to Codex. Seeshared-references/reviewer-routing.md.
Reviewer Calling Convention
When calling the reviewer, branch on REVIEWER_BACKEND:
If REVIEWER_BACKEND = codex:
Use mcp__codex__codex for new review threads.
Use mcp__codex__codex-reply for follow-up rounds (reuse threadId).
If REVIEWER_BACKEND = manual:
Use mcp__manual_review__review for new review threads with:
prompt: [exact same prompt that would go to Codex]
config: {"model_reasoning_effort": "xhigh"}
Save the returned threadId.
Use mcp__manual_review__review_reply for follow-up rounds with:
threadId: [saved manual-review threadId]
prompt: [follow-up prompt]
config: {"model_reasoning_effort": "xhigh"}
Content fidelity: the manual reviewer should see the same substantive review brief Codex would read. If the manual UI supports file upload / attachment, reuse the same brief file; otherwise paste the brief contents inline because remote web UIs cannot read your local filesystem paths. Review tracing applies equally to both backends.
Context: $ARGUMENTS
Prerequisites
- Codex MCP Server configured in Claude Code:
claude mcp add codex -s user -- codex mcp-server - This gives Claude Code access to
mcp__codex__codexandmcp__codex__codex-replytools
Workflow
Step 1: Gather Research Context
Before calling the external reviewer, compile a comprehensive briefing:
- Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
- Read any memory/notes files for key findings and experiment history
- Identify: core claims, methodology, key results, known weaknesses
Step 2: Initial Review (Round 1)
Send a detailed prompt with ultra reasoning, using the selected backend. For
the codex backend, keep the MCP payload short: write the full briefing to
RESEARCH_REVIEW_REQUEST.md, then point Codex at that file.
For codex backend:
mcp__codex__codex:
model: gpt-5.6-sol
config: {"model_reasoning_effort": "ultra"}
prompt: |
Read the review brief at <absolute path to RESEARCH_REVIEW_REQUEST.md>.
Executor notes are not evidence beyond the files they cite, so verify the
referenced artifacts before judging.
Please act as a senior ML reviewer (NeurIPS/ICML level). Start from the
assumption that the work is broken somewhere — your job is to find where.
Be adversarial. Trust nothing the author tells you — verify everything
yourself. Identify:
1. Logical gaps or unjustified claims
2. Missing experiments that would strengthen the story
3. Narrative weaknesses
4. Whether the contribution is sufficient for a top venue
Please be brutally honest.The review brief should contain the full research context, the specific questions, and the primary artifact / raw-result paths the reviewer should inspect.
For manual backend: use mcp__manual_review__review with the same brief
contents. If the manual-review UI supports attachments, attach
RESEARCH_REVIEW_REQUEST.md; otherwise paste the brief inline. Save the
returned threadId.
Step 3: Iterative Dialogue (Rounds 2-N)
For codex backend: use mcp__codex__codex-reply with the returned threadId.
For manual backend: use mcp__manual_review__review_reply with the same threadId.
Use the appropriate tool to continue the conversation. For Codex follow-up
rounds, write an updated brief such as RESEARCH_REVIEW_ROUND_2.md and send
only the path:
mcp__codex__codex-reply:
threadId: [saved reviewer threadId from Step 2]
# replies inherit the thread's model/effort (gpt-5.6-sol ultra)
prompt: |
Read the updated review brief at <absolute path to
RESEARCH_REVIEW_ROUND_2.md>.
Focus on unresolved weaknesses and whether the revision actually fixed them.For manual follow-up rounds, attach that same updated brief if possible; otherwise paste it inline.
For each round:
- Respond to criticisms with evidence/counterarguments
- Ask targeted follow-ups on the most actionable points
- Request specific deliverables: experiment designs, paper outlines, claims matrices
Key follow-up patterns:
- "If we reframe X as Y, does that change your assessment?"
- "What's the minimum experiment to satisfy concern Z?"
- "Please design the minimal additional experiment package (highest acceptance lift per GPU week)"
- "Please write a mock NeurIPS/ICML review with scores"
- "Give me a results-to-claims matrix for possible experimental outcomes"
Step 4: Convergence
Stop iterating when:
- Both sides agree on the core claims and their evidence requirements
- A concrete experiment plan is established
- The narrative structure is settled
Step 5: Document Everything
Save the full interaction and conclusions to a review document in the project root:
- Round-by-round summary of criticisms and responses
- Final consensus on claims, narrative, and experiments
- Claims matrix (what claims are allowed under each possible outcome)
- Prioritized TODO list with estimated compute costs
- Paper outline if discussed
Update project memory/notes with key review conclusions.
Composed mode — if invoked with
— composed: <canonical-report-path>(an orchestrator like/idea-discoverypasses this), do not write a standalone review.mdin the project root. The raw conversation is already persisted to.aris/traces/…(see Review Tracing below — that audit copy is kept in every mode); fold the review conclusions (consensus, claims matrix, prioritized TODOs) into the orchestrator's canonical report and cite the trace path there. Default (no— composed:directive): behave exactly as above — write the standalone review document. Never infer composed mode from a report file merely existing. Full rules:shared-references/output-composition.md.
Key Rules
- ALWAYS pin
model: gpt-5.6-sol+config: {"model_reasoning_effort": "ultra"}for reviews (deep-audit tier; capability fallback perreviewer-routing.md, never belowxhigh) - Put comprehensive context in the review brief. Codex can read local files when you pass an absolute path; manual reviewers usually cannot, so attach or paste the same brief there.
- Be honest about weaknesses — hiding them leads to worse feedback
- Push back on criticisms you disagree with, but accept valid ones
- Focus on ACTIONABLE feedback — "what experiment would fix this?"
- Document the threadId for potential future resumption
- The review document should be self-contained (readable without the conversation)
Prompt Templates
For initial review:
"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS/ICML level)..."
For experiment design:
"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations."
For paper structure:
"Please turn this into a concrete paper outline with section-by-section claims and figure plan."
For claims matrix:
"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?"
For mock review:
"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept."
Review Tracing
After each reviewer call (mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, or mcp__manual_review__review_reply), save the trace following shared-references/review-tracing.md (Policy C — forensic; never silently skip). Use save_trace.sh (resolved per the chain in shared-references/integration-contract.md §2) or write files directly to .aris/traces/<skill>/<date>_run<NN>/. Respect the --- trace: parameter (default: full).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

