peer-review – skill Lập trình cho agent AI

Peer Review

Support an accountable human reviewer with a rigorous, fair, actionable assessment. Treat every unpublished submission and review as confidential.

Mandatory safety boundary

Before reading or analyzing unpublished content:

1. Confirm the user is authorized by the publisher, editor, author, or other material owner.

2. Check the target venue’s review, confidentiality, co-review, retention, and AI/tool policies.

3. Record conflicts, competence limits, requested scope, and specialist-review needs.

4. Default to local-only processing.

If authorization is unclear, do not inspect or quote the manuscript. Clarify only the unresolved authorization; existing documented authorization need not be requested again. Until resolved, use only the intake validator or synthetic/public fixtures. Local processing of the manuscript also requires authorization.

Running a bundled CLI locally does not make the surrounding assistant session local. Treat any manuscript content read into a hosted assistant as external processing when evaluating venue policy and authorization.

Never:

• Send unpublished manuscript, supplement, review, or editorial text to an external service without specific publisher/author authorization and venue permission
• Upload confidential content to a public model, search engine, citation service, grammar tool, plagiarism checker, or image service
• Reuse content for training, benchmarking, product improvement, or unrelated research
• Read broad environment state, .env files, API keys, or credentials
• Call a network, LLM, or image API from bundled tools
• Invoke another skill or a PDF/image pipeline automatically
• Impersonate an assigned reviewer, editor, journal, funder, or author
• Fabricate manuscript details, review findings, citations, analyses, experiments, reproduction, or an editorial outcome
• Announce a decision that belongs to an editor or panel

Delete local copies and derivatives when policy requires; otherwise retain only what the controlling policy authorizes. Record deletion or retention without copying confidential content into the record.

Read references/ethical_review_practice.md before handling confidential material.

Human accountability

Label generated text as a working draft. The accountable human must:

• Read the complete authorized submission and relevant supplements
• Verify every factual statement, calculation, citation, and manuscript location
• Resolve conflicts and disclose assistance as required
• Rewrite comments in their own expert judgment
• Submit through the authorized channel

Automated coverage, consistency, or lint results are not peer review and do not establish manuscript merit.

Intake gate

Copy and complete assets/review_intake_template.json, then run:

python3 scripts/validate_review_intake.py completed-intake.json

Proceed only when status is READY_FOR_LOCAL_REVIEW.

The validator blocks:

• Undocumented authorization
• Missing human accountability
• Unassessed or unresolved conflicts
• Unknown review model or unchecked venue policy
• Unauthorized AI assistance
• External service use
• Data reuse
• Missing deletion/retention planning

It validates declarations, not their truth.

A conflict marked disclosed_to_editor remains blocked. Use editor_cleared only after actual editor clearance, or none_identified when no conflict exists. Do not clear a conflict merely to pass the validator.

Review workflow

1. Establish scope and available evidence

Record:

• Submission type and stage
• Review question and requested focus
• Target venue and review model
• Materials actually available: manuscript, supplements, protocol, registration, analysis plan, data/code statement, prior decision, or response letter
• Competence areas and limits
• Missing material that prevents assessment

Do not infer absent content. Use “not reported” or “not available for review.”

2. Orient without deciding

Create a short neutral map:

• Research question
• Population or system
• Design and unit
• Intervention, exposure, test, or model
• Comparator/reference
• Outcomes and timing
• Principal claims

Do not write an acceptance/rejection recommendation. Identify what evidence would be needed to evaluate each claim.

3. Select reporting guidance

Copy assets/study_profile_template.json and run:

python3 scripts/select_reporting_guidelines.py local-profile.json

For checklist coverage:

python3 scripts/select_reporting_guidelines.py \
  local-profile.json \
  --coverage local-coverage.csv

Use the current base guideline, explanation/elaboration, applicable extensions, and target venue policy. See references/reporting_standards.md.

Critical distinction: reporting completeness is not design quality, risk of bias, validity, or merit. Never convert missing items into an automatic score or publication judgment.

4. Map claims to evidence

Prioritize central, causal, mechanistic, safety, diagnostic, prediction, and generalization claims.

For each claim, record:

• Location and claim ID
• Supporting result, figure, table, analysis, or citation IDs
• Direction, magnitude, population, outcome, timepoint, and uncertainty alignment
• Limitation or alternative explanation
• Bounded requested action

Run:

python3 scripts/validate_claim_evidence.py local-claim-matrix.csv

Start from assets/claim_evidence_matrix_template.csv. The report emits IDs and counts, not claim text.

5. Review methods and statistics

Assess in this order:

1. Question and target quantity

2. Design and unit of inference

3. Sampling, allocation, controls, masking, and timing

4. Sample-size or precision rationale

5. Inclusion, exclusion, attrition, and missingness

6. Analysis–design alignment and assumptions

7. Multiplicity and prespecification

8. Effect estimates, uncertainty, denominators, and harms

9. Interpretation, causality, and generalizability

Use references/common_issues.md and references/statistical_reproducibility.md.

When authors claim "no effect", "equivalent", or "no difference", check whether

the interval rules out scientifically important effects. A nonsignificant test

alone does not establish equivalence; an equivalence or non-inferiority claim

needs its stated margin and corresponding analysis. Request a narrower claim

when precision is inadequate rather than retrospective observed-power

calculations. See the [ASA statement on p-values](https://doi.org/10.1080/00031305.2016.1154108).

For a structured local audit:

python3 scripts/audit_statistics_reproducibility.py \
  local-statistics-reproducibility.json

Start from assets/statistical_reproducibility_template.json. Request specialist review when a central method exceeds competence; do not hide uncertainty behind a generic critique.

6. Review reproducibility and transparency

Check, as applicable:

• Protocol, registration, amendments, and analysis-plan consistency
• Data provenance, exclusions, transformations, and accession IDs
• Software, package, model, and parameter versions
• Code, environment, seeds, run instructions, and tests
• Data, code, materials, and model availability or justified restrictions
• Domain metadata standards

Do not claim reproduction unless authorized inputs were actually run with documented commands, environment, and outputs.

7. Review ethics and integrity

Check applicable approvals, consent, welfare, privacy, community governance, funding, sponsor role, conflicts, authorship/contribution, registration, biosafety, and dual-use concerns.

Describe observable evidence and uncertainty. Do not accuse authors or investigate them. Route credible concerns through the confidential editor channel under venue policy.

8. Review figures, tables, and citations

For figures and tables, assess:

• Consistency with text and supplements
• Denominators, units, axes, scales, uncertainty, and legends
• Accessible encoding and sufficient context
• Image acquisition/processing disclosure and source-data policy

This skill has no image-generation or PDF-conversion workflow. Use only user-authorized local artifacts and tools.

For Pandoc-style citations such as [@ref-id]:

python3 scripts/audit_citations.py local-manuscript.md local-references.csv

Start from assets/citation_references_template.csv. This checks a restricted, single-line bracketed citation subset and identifier format only; it does not implement the complete Pandoc citation grammar or verify that a source exists or supports a claim. See the parser limits in references/tool_reference.md.

9. Draft actionable comments

Generate a private scaffold only after intake passes:

python3 scripts/generate_review_scaffold.py \
  completed-intake.json \
  -o private-review.md

Every major/minor comment should include:

• Location
• Observation
• Evidence or criterion
• Why it matters
• Requested action

Prioritize:

-

… (nội dung đầy đủ có trong gói tải về)