CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

42

Quality

42%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/blind-review-sanitizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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 identifies a clear and distinctive niche (academic blind-review anonymization) but falls short on specificity of concrete actions and natural trigger terms. It would benefit from listing specific operations the skill performs and including more user-facing keywords that researchers would naturally use when seeking this functionality.

Suggestions

Add concrete actions the skill performs, e.g., 'Removes author names, strips institutional affiliations, redacts acknowledgments and funding sections, replaces self-citations with anonymous placeholders.'

Expand trigger terms with natural user language variations such as 'anonymize paper', 'remove author information', 'blind review preparation', 'de-identify manuscript', 'peer review submission'.

Strengthen the 'Use when' clause with explicit triggers, e.g., 'Use when the user asks to prepare a paper for blind review, anonymize a manuscript, or strip identifying information before submission.'

DimensionReasoningScore

Specificity

It names the domain (academic writing, double-blind submission) and mentions some actions ('structured anonymization, explicit assumptions, clear output boundaries'), but these are somewhat abstract rather than listing concrete actions like 'remove author names, strip affiliations, redact acknowledgments'.

2 / 3

Completeness

The 'when' is partially addressed with 'academic writing workflows that need structured anonymization... for double-blind submission', but the 'what' is vague—it doesn't clearly enumerate what the skill actually does. The 'Use when' clause exists but is more of a general context than explicit trigger guidance.

2 / 3

Trigger Term Quality

Includes relevant terms like 'blind-review', 'anonymization', 'double-blind submission', and 'academic writing', but misses common user variations like 'anonymize paper', 'remove author info', 'blind review', 'peer review preparation', or 'de-identify manuscript'.

2 / 3

Distinctiveness Conflict Risk

The description carves out a clear niche: academic blind-review anonymization for double-blind submission. This is unlikely to conflict with other skills given its very specific domain focus.

3 / 3

Total

9

/

12

Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is significantly over-engineered with excessive boilerplate, redundant sections, and template-driven content that adds little actionable value. The core task—manuscript anonymization for double-blind review—is reasonable but buried under layers of generic process documentation. The strongest elements are the parameters table and the workflow steps, but even these are diluted by repetition across multiple sections.

Suggestions

Consolidate the workflow into a single, clear numbered sequence with explicit validation checkpoints (e.g., verify output file exists and contains expected redactions before returning to user).

Remove redundant sections: 'Quick Check' and 'Audit-Ready Commands' duplicate the same py_compile command; 'Implementation Details' restates 'Workflow'; 'Key Features' restates the description. Aim for under 80 lines.

Add a concrete input/output example showing a before-and-after snippet of anonymized text, so Claude knows exactly what the tool produces.

Remove boilerplate sections that Claude already knows how to handle (Response Template, Output Requirements, Evaluation Criteria, Risk Assessment) or move them to a separate reference file if they're truly needed for audit purposes.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. Multiple sections restate the same information (e.g., 'python -m py_compile scripts/main.py' appears 3 times, workflow steps are described in multiple places). Sections like 'When to Use', 'Key Features', 'Implementation Details', 'Output Requirements', 'Response Template', 'Input Validation', and 'Evaluation Criteria' contain boilerplate that Claude already knows or could infer. Cross-references like 'See ## Prerequisites above' and 'See ## Workflow above' add confusion rather than clarity. The skill could be reduced to ~30% of its current size without losing actionable content.

1 / 3

Actionability

The parameters table, example command, and workflow steps provide some concrete guidance. However, much of the content is procedural boilerplate rather than executable instruction. The actual script behavior is never shown—there's no example of what the output looks like, no sample input/output pair, and the 'Example run plan' is generic. The audit commands are just parse checks, not functional tests.

2 / 3

Workflow Clarity

The Workflow section provides a reasonable 5-step sequence with a stop condition for missing inputs, and the Error Handling section adds fallback guidance. However, there are no explicit validation checkpoints between steps (e.g., verifying the sanitization output before delivery). The workflow is also split across multiple sections (Example Usage run plan, Implementation Details, Workflow, Error Handling) making it hard to follow as a single coherent process.

2 / 3

Progressive Disclosure

Despite referencing 'references/audit-reference.md' and 'references/' directory, no bundle files are provided, making these references unverifiable. The SKILL.md itself is monolithic—nearly 200 lines of content that could be split into separate files (e.g., security checklist, evaluation criteria, response template). Multiple sections contain cross-references to other sections within the same file ('See ## Prerequisites above') that are confusingly placed and sometimes circular.

1 / 3

Total

6

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
aipoch/medical-research-skills
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.