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

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

60%Weight 40%Scale 1-5

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

The body is actionable and well-structured, with concrete commands, a parameters table, and a clean one-level reference to a real bundle file. Its main weakness is verbosity from heavily redundant guardrail sections that restate fallback, output, and validation guidance.

Suggestions

Consolidate the redundant guardrail sections (Error Handling, Failure Handling, Input Validation, When Not to Use, Required Inputs, User Checkpoints, Output Requirements, Output Contract, Response Template) into a single concise section to reduce padding.

Add an explicit validate->fix->retry feedback loop in the Workflow (e.g., run py_compile, on failure fix and re-run, only then proceed) to strengthen workflow clarity.

Move the bulk of the audit/security/evaluation checklist content into references/audit-reference.md so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, with multiple overlapping guardrail sections (Error Handling vs Failure Handling, Output Requirements vs Output Contract vs Response Template, Input Validation vs Required Inputs vs When Not to Use) that restate the same fallback/boundary guidance.	2 / 5
Actionability	Provides copy-paste-ready commands ("python -m py_compile scripts/main.py", "python scripts/main.py --help", a full run example with --input and --authors) plus a concrete parameters table backed by a real bundled script, with only minor gaps around output-handling variants.	4 / 5
Workflow Clarity	A 5-step Workflow with explicit stop/fallback checkpoints plus validation via Quick Check and Audit-Ready Commands gives a clear sequence; it lacks an explicit validate->fix->retry feedback loop, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Section structure is well organized with a clearly signaled one-level reference to references/audit-reference.md (a real file) and a real scripts/main.py, but a large amount of guardrail content is inlined that could be split into a separate file.	4 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

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, distinctive niche for double-blind anonymization and includes an explicit trigger clause covering both what and when. It is weakened by limited concrete action coverage and missing common trigger-term synonyms.

Suggestions

Add concrete capabilities to the description (e.g., 'remove or highlight author names, affiliations, and self-citations') to lift specificity above a single action.

Include natural user phrases such as 'peer review', 'redact author names', or 'blind a manuscript' to broaden trigger-term coverage.

Tighten the what/when split so the triggering condition ('for double-blind peer-review submission') reads as a distinct clause from the capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ("double-blind submission") and one concrete action ("structured anonymization"), but "explicit assumptions" and "clear output boundaries" are process qualities rather than concrete capabilities, so coverage is not comprehensive.	3 / 5
Completeness	Answers both what ("structured anonymization, explicit assumptions, and clear output boundaries") and when ("for academic writing workflows that need ... for double-blind submission") with an explicit "Use ... for" trigger clause, but the when could be more specific and the what/when are somewhat blended.	4 / 5
Trigger Term Quality	Includes relevant natural terms like "anonymization", "double-blind submission", and "academic writing workflows", but misses common variations and synonyms a user might say such as "peer review", "redact author names", or "blind manuscript".	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (double-blind manuscript anonymization) with distinct triggers, but the broad phrase "academic writing workflows" and generic process descriptors create minor overlap risk with general academic-writing skills.	4 / 5
	Total	14 / 20 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
Path: scientific-skills/Academic Writing/blind-review-sanitizer/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours 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.