Blind Review Sanitizer

Source: https://github.com/aipoch/medical-research-skills

Blind Review Sanitizer

Structured manuscript anonymization for double-blind peer review.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help

When to Use

• Use this skill when the task needs removal or review of author-identifying content in manuscripts prepared for double-blind submission.
• Use this skill for academic writing tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Workflow

1. Confirm the submission target, source file type, anonymization strictness, and whether acknowledgments should be preserved.
2. Check whether the provided material is a supported file format and whether author names or known identifiers are available.
3. Use the packaged script for supported files; otherwise produce a manual anonymization checklist without claiming full sanitization.
4. Return the sanitized artifact or a verification plan that separates changes made, remaining risks, and manual review points.
5. If the request lacks a file path or enough identifiers, stop and request the minimum missing input.

Use Cases

• Blind a manuscript before conference submission
• Review acknowledgments and self-citations for deanonymization risk
• Produce a manual anonymity checklist when automated processing is not possible

Parameters

Returns

• Sanitized manuscript file for supported formats
• Summary of removed identifiers when available
• Explicit note when manual verification is still required

Example

python scripts/main.py --input manuscript.md --authors "Alice Chen,Bob Smith"

Risk Assessment

Security Checklist

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Sensitive manuscript content stays within approved workspace
• Input file paths validated before processing
• Output file path reviewed before overwrite
• Error messages do not fabricate successful sanitization
• Manual review required before submission
• Metadata cleanup handled separately when needed

Prerequisites

Optional dependency: python-docx is required only for .docx processing.

Evaluation Criteria

Success Metrics

• Script path parses successfully
• Help output documents supported options
• Sanitization stays within double-blind preparation scope
• Missing file or missing identifiers trigger bounded fallback

Test Cases

1. Basic Functionality: Help output and script parse succeed
2. Edge Case: Missing file path triggers explicit stop condition
3. Output Quality: Remaining anonymity risks are called out clearly

Lifecycle Status

• Current Stage: Draft
• Next Review Date: 2026-03-20
• Known Issues: File metadata and embedded image review still require manual checks
• Planned Improvements:
  • Safer sample-file smoke test for richer audit coverage
  • More explicit metadata cleanup guidance

Output Requirements

Every final response should make these items explicit when they are relevant:

• Objective or requested deliverable
• Inputs used and assumptions introduced
• Workflow or decision path
• Core result, recommendation, or artifact
• Constraints, risks, caveats, or validation needs
• Unresolved items and next-step checks

Error Handling

• If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
• If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
• If scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
• Do not fabricate files, citations, data, search results, or execution outcomes.

Input Validation

This skill accepts requests that match the documented purpose of blind-review-sanitizer and include enough context to complete the workflow safely.

Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:

blind-review-sanitizer only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.

References

• references/audit-reference.md - Supported scope, audit commands, and fallback boundaries

Response Template

Use the following fixed structure for non-trivial requests:

1. Objective
2. Inputs Received
3. Assumptions
4. Workflow
5. Deliverable
6. Risks and Limits
7. Next Checks

If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.

When Not to Use

• Do not proceed when required input files, identifiers, parameters, or context are missing — ask the user to provide them first.
• Do not assume capabilities beyond this skill's declared scope when the user requests external operations or inferences.
• Do not proceed without user confirmation when overwriting existing results, executing high-cost batch operations, or expanding task scope.

Required Inputs

Output Contract

• Primary output: Structured result or target file aligned with this skill's objective.
• Optional output: Intermediate check notes, issue list, supplementary suggestions, or generated file paths.
• Format requirement: Unless the user specifies otherwise, prefer stable, reviewable Markdown or JSON; if the skill's bundled script requires a fixed format, use that format.
• If partially complete: Must explicitly mark as PARTIAL and state which steps are completed and which remain.

Failure Handling

• Missing critical input: Explicitly state which fields, files, or identifiers are missing and pause.
• Script, template, or resource execution failure: Report the failing step, likely cause, and recovery suggestions — do not silently degrade.
• Partial completion only: Return the verified portion first, then list remaining blockers and suggested next steps.

User Checkpoints

• Before executing batch processing, overwriting files, long-running searches, or multi-stage generation, confirm scope and output format with the user.
• Before proceeding when a key judgment is ambiguous, evidence is insufficient, or the workflow is entering the next stage, confirm with the user.

Quick Validation

• Check that key scripts, templates, or reference file paths this skill depends on exist.
• Check that the final output contains the core fields, sections, or files specified for this task.
• Check that results clearly mark assumptions, limitations, and incomplete items.