What makes Academic Paper Reviewer notable?

2.1K downloads. Trust evidence available

How should Academic Paper Reviewer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Academic Paper Reviewer

7-agent paper review system on Hermes Agent. 6 modes (full/re-review/quick/methodology-focus/guided/calibration). 5-panel review with editorial decision, rev... Skill: Academic Paper Reviewer Owner: andyrenxu7255 Summary: 7-agent paper review system on Hermes Agent. 6 modes (full/re-review/quick/methodology-focus/guided/calibration). 5-panel review with editorial decision, rev... Tags: academic:1.0.4, cc-by-nc:1.0.2, editorial:1.0.4, hermes:1.0.4, latest:1.0.4, manuscript:1.0.4, multi-agent:1.0.4, paper-review:1.0.4, peer-review:1.0.4, research:1.0.4, review:1.0.4 Version hi

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.1k

Updated

Oct 9, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.1K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.1K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.4release · observed May 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1721fhgyy0yf38f9gfpbjxrn984fcz0:academic-paper-reviewer

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-andyrenxu7255-academic-paper-reviewer/snapshot"

Documentation

CLAWHUB

152,043 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: academic-paper-reviewer
description: "7-agent paper review system on Hermes Agent. 6 modes (full/re-review/quick/methodology-focus/guided/calibration). 5-panel review with editorial decision, revision roadmap, and calibration metrics. Uses delegate_task for each reviewer. Triggers: review paper, peer review, manuscript review, check revisions, calibrate reviewer, 審稿, 同儕審查, 論文審查."
metadata:
  version: "1.0-hermes-1.0"
  last_updated: "2026-05-16"
  status: active
  adapted_from: "imbad0202/academic-research-skills"
  adapted_for: "Hermes Agent (deepseek-v4-pro)"
  task_type: open-ended
  license: "CC BY-NC 4.0"
  original_author: "Cheng-I Wu"
  original_license: "CC BY-NC 4.0"
  original_repo: "https://github.com/Imbad0202/academic-research-skills"
  copyright: "Copyright (c) 2026 Cheng-I Wu"
---
# Academic Paper Reviewer — 7-Agent Review System (Hermes Edition)

📄 **License:** [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) · Copyright (c) 2026 Cheng-I Wu  
🔗 **Original:** [Imbad0202/academic-research-skills](https://github.com/Imbad0202/academic-research-skills)  
🔄 **Adaptation:** Multi-agent review system implemented via `delegate_task` instead of Claude Code's internal agent system. All agent definitions, references, and quality standards preserved unchanged from original. **This adaptation is distributed under the same CC BY-NC 4.0 license.**

## Quick Start

```
Review this paper for journal submission
```

## Agent Team

| # | Agent | Role |
|---|-------|------|
| 1 | intake_agent | Receive paper, determine review type |
| 2 | methodology_reviewer | Method rigor assessment |
| 3 | evidence_reviewer | Evidence sufficiency & citation quality |
| 4 | argument_reviewer | Logical coherence & argument structure |
| 5 | domain_reviewer | Domain expertise & literature positioning |
| 6 | editor_in_chief | Aggregate reviews → editorial decision |
| 7 | revision_coach | Convert reviews → actionable roadmap |

## Hermes Execution

### Full Mode: 5-Panel Parallel Review
```
delegate_task(tasks=[
    {"goal": "Review manuscript methodology: design appropriateness, validity threats, replicability. Score 1-5.", "context": "Use agents/methodology_reviewer.md", "toolsets": ["file"]},
    {"goal": "Review evidence: citation quality, source credibility, evidence hierarchy alignment. Score 1-5.", "context": "Use agents/evidence_reviewer.md", "toolsets": ["file"]},
    {"goal": "Review argument: logical flow, claim-evidence alignment, counter-argument handling. Score 1-5.", "context": "Use agents/argument_reviewer.md", "toolsets": ["file"]},
    {"goal": "Review domain positioning: literature coverage, theoretical grounding, contribution significance. Score 1-5.", "context": "Use agents/domain_reviewer.md", "toolsets": ["file"]}
])
```

### Editorial Decision
```
delegate_task(goal="Aggregate all 4 reviewer reports. Apply weighted scoring (Method 30%, Evidence 25%, Argument 25%, Domain 20%). Issue editorial decision: Accept/Minor R

_meta.json

{
  "ownerId": "kn725tchg3gp72a78w22qa07p584f267",
  "slug": "academic-paper-reviewer",
  "version": "1.0.4",
  "publishedAt": 1779500956225
}

references/calibration_mode_protocol.md

# Calibration Mode Protocol

**Status**: v3.2
**Parent skill**: `academic-paper-reviewer`
**Mode name**: `calibration`
**Purpose**: Measure this reviewer's own false-negative rate (FNR), false-positive rate (FPR), and balanced accuracy against a user-supplied gold-standard set, then attach the resulting error profile as a confidence disclosure to subsequent reviews in the same session.

---

## Why this mode exists

A single LLM reviewer produces an absolute 0-100 rubric score, but that score is weakly interpretable without knowing the reviewer's error profile. Two reviewers could give the same paper a 65, yet one might systematically over-score weak methodology papers and the other might systematically under-score cross-disciplinary work. Absolute scores don't reveal this.

Lu et al. (2026, Nature 651:914-919) demonstrated in Table 1 that an LLM-based Automated Reviewer can approach human balanced accuracy (0.65 vs human 0.67-0.73 on 500 ICLR 2022 papers) while having a dramatically different error profile: FNR 0.17 vs human 0.52, at the cost of FPR 0.50 vs human 0.17-0.34. Human reviewers miss half of the papers that should be rejected; the Automated Reviewer misses very few but over-rejects more.

Translation for ARS: **our reviewer has an error profile too, and we do not currently measure it.** Calibration mode closes that gap. It does not try to make the reviewer perfect; it makes the reviewer's imperfections legible.

---

## Inputs

1. **Gold-standard set**: 5-20 papers the user has labelled with known outcomes. Minimum 5; recommended 10-15. Each entry:
- Paper file path or text
- Ground-truth label: `accept`, `reject`, or `borderline`
- Venue context (journal/conference, tier)
- Optional: human reviewer scores for comparison

2. **Domain specification**: the user's target field, used to seed `field_analyst_agent`. Calibration for "machine learning venues" is not valid for "qualitative education research" — error profiles are domain-specific.

3. **Session persistence**: the error profile is cached for the **current session only**. No cross-session caching, no `~/.ars_calibration_cache/` directory. Calibration is explicitly opt-in per the v3.2 design decision: the user decides when to spend tokens on calibration, and a new session starts fresh. If the user wants to reuse a profile across sessions, they re-run calibration or paste a prior Calibration Report as a session prompt.

---

## Process

### Phase 0: Intake

- Verify the set has at least one `accept` and one `reject` (otherwise FNR or FPR is undefined).
- If all labels are on one side, refuse to proceed and ask the user for at least one counter-example.
- Warn if n < 10: "Calibration with fewer than 10 papers produces wide confidence intervals. Results should be treated as directional, not conclusive."

### Phase 1: Run `full` mode on each gold paper, with ensembling

For each paper, run the standard `full` review pipeline **5 times** (ensembling, per Lu 2026 Methods A.1

references/changelog.md

# Changelog

| Version | Date | Changes |
|---------|------|---------|
| 1.4 | 2026-03-08 | Quality rubrics reference (0-100 scoring with 5 descriptors per dimension, weighted aggregation formula, decision mapping); Quick Mode Selection Guide; Dimension Scores upgraded from optional 1-5 to required 0-100 with rubric descriptors |
| 1.3 | 2026-03-05 | DA vs R3 role boundaries with explicit responsibility tables; CRITICAL finding criteria with concrete examples; Consensus classification (CONSENSUS-4/3/SPLIT/DA-CRITICAL); Confidence Score weighting rules; Asian & Regional Journals reference (TSSCI + Asia-Pacific + OA options) |
| 1.2 | 2026-03 | Added statistical reporting standards reference; enhanced methodology_reviewer_agent with statistical reporting adequacy sub-step |
| 1.1 | 2026-02 | Added Devil's Advocate Reviewer (7th agent), added re-review mode, expanded review team from 4 to 5 |
| 1.0 | 2026-02 | Initial version: 6 agents, 4 modes, 3-phase workflow |

references/editorial_decision_standards.md

# Editorial Decision Standards — Criteria for Editorial Decision Making

This document defines the explicit criteria for Accept / Minor Revision / Major Revision / Reject decisions, for use by `eic_agent` and `editorial_synthesizer_agent`.

---

## 1. Decision Categories

### Accept

**Definition**: The paper can be published without further review.

**Criteria**:
- Average score across all universal dimensions >= 4.0
- No dimension scores below 3.0
- At least 3/4 reviewers recommend Accept or Minor Revision
- No unresolved major academic issues

**Conditions**:
- May include minor copyediting suggestions
- May require final formatting adjustments
- Does not need to be sent for review again

**Typical scenarios**:
- Paper has undergone multiple revision rounds, all issues resolved
- Rare first-pass acceptance (< 5% of submissions at top-tier journals)

---

### Minor Revision

**Definition**: The paper is fundamentally acceptable and can be published after limited modifications; typically does not need to be sent for review again after revision.

**Criteria**:
- Average score across all universal dimensions >= 3.5
- No dimension scores below 2.5
- At least 3/4 reviewers recommend Accept or Minor Revision
- Issues can be resolved within 2-4 weeks
- Modifications do not involve restructuring core arguments or methods

**Typical revision items**:
- Supplementing a small number of references
- Clarifying certain methodology description details
- Improving clarity of argumentation
- Correcting citation format
- Adding discussion of limitations
- Adjusting conclusion wording (avoiding overclaiming)

**Response requirements**:
- Authors must respond to reviewer comments item by item
- After revision, reviewed by EIC (usually not sent for external review again)
- Revision deadline: 2-4 weeks

---

### Major Revision

**Definition**: The paper has potential but has significant issues, requiring substantial revision followed by re-review.

**Criteria**:
- Universal dimension average score between 2.5-3.4
- Some dimensions may score below 2.5 (but not fatal)
- At least 2/4 reviewers recommend Major Revision or better
- Issues are serious but fixable (not fundamental design flaws)
- Revision requires 6-8 weeks of work

**Typical revision items**:
- Re-analyzing data (additional analysis or correcting errors)
- Substantially rewriting literature review (missing key references)
- Supplementing additional data collection
- Reorganizing paper structure
- Correcting significant methodological flaws
- Strengthening theoretical framework application
- Adding robustness checks

**Response requirements**:
- Authors must write a detailed point-by-point response letter
- After revision, sent for re-review (may go back to original reviewers or new reviewers)
- Revision deadline: 6-8 weeks
- Typically a maximum of 2 rounds of Major Revision allowed

---

### Reject

**Definition**: The paper is not suitable for publication in this journal, even with revision.

**Criteria

Github ReposUpdated 8h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.