blind-review-sanitizer
Use blind-review-sanitizer for academic writing workflows that need structured anonymization, explicit assumptions, and clear output boundaries for double-blind submission.
56
46%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/blind-review-sanitizer/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description establishes a clear niche for academic blind review preparation, which provides good distinctiveness. However, it lacks concrete action verbs describing what the skill actually does (e.g., removes names, strips metadata) and could benefit from more natural trigger terms that users would actually say when needing this functionality.
Suggestions
Add specific concrete actions like 'removes author names and affiliations', 'strips identifying metadata', 'redacts self-citations' to improve specificity.
Include natural trigger term variations such as 'blind review', 'anonymous submission', 'peer review preparation', 'de-identify manuscript', or 'remove author information'.
Separate the 'what' and 'when' more clearly, e.g., 'Anonymizes academic manuscripts by removing author names, affiliations, and self-citations. Use when preparing papers for double-blind peer review or when user mentions blind submission.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (academic writing, double-blind submission) and mentions 'structured anonymization' and 'explicit assumptions' but doesn't list concrete actions like 'removes author names', 'strips affiliations', or 'redacts identifying references'. | 2 / 3 |
Completeness | The 'Use when...' clause exists but conflates what and when into a single phrase. The 'what' (structured anonymization, explicit assumptions, clear output boundaries) is vague, and the 'when' is essentially restating the same concepts rather than providing distinct trigger scenarios. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'academic writing', 'double-blind submission', and 'anonymization', but misses common variations users might say like 'blind review', 'remove author info', 'anonymous submission', 'peer review prep', or 'de-identify paper'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'blind-review', 'academic writing', 'double-blind submission', and 'anonymization' creates a clear niche that is unlikely to conflict with other skills. This is a well-defined, specialized use case. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity, including extensive boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that don't provide actionable guidance for Claude. While it has good structural elements like a parameter table and CLI examples, the actual workflow lacks concrete input/output examples and explicit validation checkpoints. The skill would benefit greatly from aggressive trimming and adding one complete worked example.
Suggestions
Remove or drastically reduce boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't add actionable guidance - these consume tokens without helping Claude execute the task
Add a concrete worked example showing actual input content, the exact command run, and the resulting sanitized output to demonstrate expected behavior
Consolidate redundant sections - the 'Example Usage', 'Audit-Ready Commands', and 'Quick Check' sections all contain overlapping information that could be unified
Add an explicit verification step in the workflow to confirm sanitization success (e.g., 'Run diff to verify all author names were removed') before marking the task complete
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. Contains multiple sections that repeat similar information (e.g., 'See ## Prerequisites above' and 'See ## Workflow above' cross-references), excessive boilerplate sections like Risk Assessment, Security Checklist, Evaluation Criteria, and Lifecycle Status that add little actionable value for Claude. The skill explains obvious concepts and includes unnecessary meta-documentation. | 1 / 3 |
Actionability | Provides concrete CLI commands and a parameter table with clear options, but the actual script behavior is not demonstrated with real input/output examples. The workflow steps are somewhat abstract ('Use the packaged script for supported files') rather than showing exact command invocations with sample data and expected results. | 2 / 3 |
Workflow Clarity | The workflow section provides a 5-step sequence with some validation checkpoints (step 5 mentions stopping for missing inputs), but lacks explicit validation-fix-retry loops. For a document manipulation task, there's no clear verification step to confirm sanitization was successful before considering the task complete. | 2 / 3 |
Progressive Disclosure | References external files appropriately (references/audit-reference.md) and has clear section headers, but the main document is bloated with content that should either be in separate files (Risk Assessment, Security Checklist, Evaluation Criteria) or omitted entirely. The structure exists but content distribution is poor. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
4a48721
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.