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.

Quality

71%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/blind-review-sanitizer/SKILL.md

Quality

Content

85%

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

The body is highly actionable with concrete commands, a real example, a bundled script, and a well-sequenced workflow with explicit fallback and validation. Its main weakness is conciseness: numerous overlapping governance sections restate the same scope/input/output/error guidance and could be consolidated. Progressive disclosure is handled well with a single one-level-deep reference.

Suggestions

Consolidate the overlapping scope/input/output/error sections (When to Use, Use Cases, When Not to Use, Input Validation, Required Inputs, Output Requirements, Output Contract, Returns, Response Template, Failure Handling, Error Handling, User Checkpoints, Quick Validation) into a smaller set of non-redundant sections to recover token budget.

Remove the duplicated `python -m py_compile scripts/main.py` between Quick Check and Audit-Ready Commands, keeping one validation section.

Move the lifecycle, evaluation-criteria, and security-checklist material into references/audit-reference.md to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Core sections (parameters table, workflow steps, example) are tight, but the body carries heavy redundant governance boilerplate — Quick Check and Audit-Ready Commands repeat `python -m py_compile scripts/main.py`, and When to Use, Use Cases, When Not to Use, Input Validation, Required Inputs, Output Requirements, Output Contract, Returns, Response Template, Failure Handling, Error Handling, User Checkpoints, and Quick Validation substantially restate scope/inputs/outputs/errors. This matches level-2 'mostly efficient but could be tightened', not level-3 'every token earns its place'.	2 / 3
Actionability	Provides concrete executable commands (`python -m py_compile scripts/main.py`, `python scripts/main.py --help`), a full parameters table with types/defaults, a real example invocation (`python scripts/main.py --input manuscript.md --authors "Alice Chen,Bob Smith"`), and a bundled executable script, matching the level-3 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Workflow section gives a clear 5-step sequence with an explicit stop/fallback condition (step 5: 'If the request lacks a file path or enough identifiers, stop and request the minimum missing input') plus validation commands and overwriting/confirmation checkpoints for a destructive-adjacent operation, matching the level-3 'clear sequence with explicit validation steps' anchor rather than level-2's 'checkpoints missing or implicit'.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep references clearly: the References section links references/audit-reference.md with a description, and both referenced bundle files (references/audit-reference.md, scripts/main.py) exist and are only one level deep, matching the level-3 'clear overview with well-signaled one-level-deep references' anchor scored against the actual bundle structure.	3 / 3
	Total	11 / 12 Passed

Description

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, distinctive niche (double-blind manuscript anonymization) and bundles a when clause, but it reads as a recommendation to use a named skill rather than a concrete action list with an explicit 'Use when...' trigger. Strengthening the action verbs and adding an explicit trigger clause would lift specificity and completeness.

Suggestions

Replace the 'Use blind-review-sanitizer for workflows that need...' framing with concrete actions, e.g. 'Blind manuscripts for double-blind peer review by removing author names, affiliations, acknowledgments, and self-citations.'

Add an explicit 'Use when...' trigger clause listing natural terms users would say: manuscript, peer review, double-blind submission, anonymize, blind review.

Lead with what the skill does (verbs) before naming the skill, so the description answers 'what does this do' with multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain and attributes ('structured anonymization, explicit assumptions, and clear output boundaries for double-blind submission') but does not list concrete actions like remove, highlight, or blind; it describes what the workflow needs rather than what the skill does, so it stops short of the level-3 'multiple specific concrete actions' anchor.	2 / 3
Completeness	It conveys both what (structured anonymization, explicit assumptions, output boundaries) and a bundled when ('for academic writing workflows that need... for double-blind submission'), but the trigger is implicit within a 'Use X for...' clause rather than a clean explicit 'Use when...' trigger, so per the missing-explicit-trigger cap it stays at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('academic writing', 'anonymization', 'double-blind submission') but misses common variations a user might say such as 'manuscript', 'peer review', or 'blind review', matching the level-2 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The named skill, 'double-blind submission', and 'academic writing workflows' carve a clear niche unlikely to trigger for unrelated skills, matching the level-3 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.