SkillsAdd

smithery/sundial-org

project-referee

Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identify weaknesses, check claim-evidence gaps, or find missing citations.

Installation

$ npx skills add smithery/sundial-org --skill project-referee
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

xcode-project-setup Similar name
firebase/agent-skills

Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill …

104.1K installs
stripe-projects Similar name
stripe/ai

Use when the user wants to provision infrastructure or third-party services using Stripe Projec…

62.4K installs
persona-project-manager Similar name
googleworkspace/cli

Coordinate projects — track tasks, schedule meetings, and share docs.

28.5K installs
expo-project-structure Similar name
expo/skills

Framework (OSS). Folder structure for a new Expo app. Use when scaffolding or laying out a new …

11.3K installs
create-spring-boot-java-project Similar name
github/awesome-copilot

Create Spring Boot Java Project Skeleton

9.5K installs
project-workflow-analysis-blueprint-generator Similar name
github/awesome-copilot

Comprehensive technology-agnostic prompt generator for documenting end-to-end application workf…

9.4K installs

Also in this package

Other skills from smithery/sundial-org.

npx skills add smithery/sundial-org
training-data-curation 0 tinker-training-cost 0 icml-reviewer 0 cs448b-visualization 0 cs-research-methodology 0 ai-co-scientist 0

Browse all from smithery/sundial-org

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,472 B
  • docs SUMMARY.md 211 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Project Referee

Review Workflow

Step 1: Assess Manuscript Stage

Ask or determine the manuscript stage:

  • Early draft: Focus on novelty, feasibility, relevance, structure
  • Mid-stage draft: Focus on development trajectory, completeness, preliminary results
  • Final submission: Apply full review criteria (see [references/reviewer-instructions.md](references/reviewer-instructions.md))

Step 2: Stage-Specific Review

Early Draft Protocol:

  1. Assess core contribution novelty and significance
  2. Evaluate method feasibility with current technology
  3. Check alignment with venue scope
  4. Review logical structure and completeness
  5. Identify major missing components
  6. Suggest high-level direction

Mid-Stage Protocol:

  1. Evaluate development progress
  2. Check section completeness
  3. Assess preliminary results against claims
  4. Review literature coverage
  5. Identify specific weaknesses
  6. Provide targeted refinements

Final Submission Protocol: Apply complete review process. See [references/reviewer-instructions.md](references/reviewer-instructions.md) for the full reviewer form.

Step 3: Search for Related Work

Proactively search for missing citations:

  • Recent work in the paper's domain
  • Papers with similar methods or contributions
  • Relevant benchmarks and baselines
  • Use WebSearch to find recent publications

Step 4: Provide Structured Feedback

Use the output format in [references/reviewer-instructions.md](references/reviewer-instructions.md):

  • Summary, Strengths, Weaknesses, Questions
  • Soundness (1-4), Presentation (1-4), Contribution (1-4)
  • Overall Score (1-10), Confidence (1-5)

Neuro-Symbolic Papers

For papers combining LLMs with symbolic reasoning, see [references/neuro-symbolic-review-criteria.md](references/neuro-symbolic-review-criteria.md) for additional criteria:

  • Symbolic formulation quality
  • Solver selection and integration
  • Faithfulness and verification
  • Comparison to baselines (Logic-LM, LINC)

References

  • [references/reviewer-instructions.md](references/reviewer-instructions.md) - Full reviewer form
  • [references/neuro-symbolic-review-criteria.md](references/neuro-symbolic-review-criteria.md) - Neuro-symbolic specific criteria