pre-submission-reviewer

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR / MINOR) and flags banned AI-tone vocabulary and em-dash misuse. Use when the user asks to 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread', or within one week of a submission deadline.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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.

A well-structured, highly actionable review procedure with clear sequencing, an integrity gate, and real one-level references. The weakest areas are minor redundancy between the body and references and some repetition of the description's triggers in the Overview.

Suggestions

Remove the inline banned-AI-tone word list from Step 6 and rely on references/forbidden-patterns.md to avoid duplicating the canonical list in the body.

Trim the Overview's repetition of trigger phrases already present in the frontmatter description, keeping only the deadline-window framing.

Consider moving the per-paradigm weighting detail in Step 0 into a reference (e.g., references/paradigm-fit.md) to keep the core procedure leaner.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, domain-specific methodology rather than concepts Claude already knows, but the Overview repeats trigger info already in the description and the banned-word list in Step 6 duplicates content that lives in references/forbidden-patterns.md. Not 5 because these redundancies could be trimmed; not 3 because the bulk earns its place.	4 / 5
Actionability	Concrete per-dimension checklists, named reference files to consult, a worked severity taxonomy with examples, an explicit output template with table shapes, and grammar-rule ID citation give fully actionable, specific guidance for an instruction-only skill.	5 / 5
Workflow Clarity	A clearly sequenced Step 0 through Step 9 procedure with an explicit Integrity gate checkpoint before output, feedback handling ('a failure surfaces as a concrete finding'), and a checklist for the complex review process, matching the top anchor.	5 / 5
Progressive Disclosure	All five 'See: references/*.md' links are real, clearly signaled, and one level deep, and the canonical rule lists are appropriately externalized. Not 5 because the body retains substantial inline content (e.g., the full banned-word list in Step 6) that duplicates a reference, a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

96%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.

A strong, third-person description that clearly states what the skill does and when to use it, with concrete trigger phrases and comprehensive capability coverage. The only minor gap is slight overlap risk on generic triggers like 'proofread'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: 'pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality', a 'severity taxonomy (CRITICAL / MAJOR / MINOR)', and 'flags banned AI-tone vocabulary and em-dash misuse'.	5 / 5
Completeness	Explicitly answers both what ('Runs a pre-submission review ... across five dimensions ... severity taxonomy') and when ('Use when the user asks to ...') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say: 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread', plus a temporal 'within one week of a submission deadline'. Not a level below because synonyms are well covered; no file extension applies to this domain.	5 / 5
Distinctiveness Conflict Risk	The pre-submission technical-paper review niche is clearly distinct and bounded, but generic triggers like 'proofread' and 'find issues' carry minor overlap risk with other review/proofreading skills. Not 5 because some trigger overlap with closely related skills remains.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUSTDial/Supervisor-Skills
Path: skills/pre-submission-reviewer/SKILL.md
Commit: 207bc6f

Reviewed: 9 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.