Back to resources

SKILL

peer-review

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/peer-review
Use with an agent

SUMMARY

What it does

This Agent Skill provides a structured workflow for preparing evidence-bounded, constructive peer-review drafts and manuscript assessments. It includes mandatory safety boundaries for handling confidential unpublished content, requiring user authorization and venue policy compliance. The skill offers local-only deterministic CLI tools for validating review intake, selecting reporting guidelines, mapping claims to evidence, auditing statistics and reproducibility, checking citations, generating review scaffolds, and linting reviews. It emphasizes human accountability and prohibits external service calls, fabrication, and impersonation. The skill is part of the Scientific Agent Skills library by K-Dense, licensed under MIT.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

document.analyzeweight 90 · confidence 90document.generateweight 80 · confidence 80data.validateweight 70 · confidence 70research.assistweight 90 · confidence 90workflow.manageweight 60 · confidence 60

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.