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

92%

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

85%Weight 40%Scale 1-3

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

A well-structured, actionable review skill with a clear procedure, an explicit validation gate, and clean one-level reference disclosure. Only minor editorializing keeps conciseness off the top anchor.

Suggestions

Trim the 'Severity honesty cuts both ways' paragraph — the integrity gate and severity taxonomy already enforce calibration, and Claude does not need the philosophy spelled out.

Shorten or remove the opening line 'Three to five days before a submission deadline is the window where a careful external review pays off most.' — the 'When to use this skill' section already conveys timing.

Collapse 'The output is not a rewrite ...' into a single clause so the Overview opens directly with the procedure.

Dimension	Reasoning	Score
Conciseness	Mostly lean, actionable checklists with no concept-explanation padding, but editorial passages such as 'Severity honesty cuts both ways ...' and the opening context line spell out calibration philosophy Claude already grasps and could be trimmed.	2 / 3
Actionability	Concrete checks with specific thresholds and examples (e.g. 'ResNet~\cite{X}, never ResNet\cite{X}', 'paragraphs are not over 10 lines; split if so', the five-sentence Abstract formula) plus a copy-paste output template; for an instruction-only review skill this is fully actionable.	3 / 3
Workflow Clarity	A clear Step 0–Step 9 sequence with an explicit Integrity-gate validation checkpoint and a feedback loop (gate failure surfaces as a finding; the retrieval-skip fallback is handled), matching the anchor for explicit validation steps.	3 / 3
Progressive Disclosure	SKILL.md is an overview; detailed rule lists are pushed to five real, one-level-deep reference files (logic-and-structure, grammar-rules, latex-rules, forbidden-patterns, section-guides), each clearly signaled with 'See: references/X.md for ...'.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 names concrete capabilities, gives natural trigger phrases, and explicitly covers both what and when. Unlikely to conflict with adjacent drafting skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'runs a pre-submission review ... 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'.	3 / 3
Completeness	States what it does (five-dimension review with a severity taxonomy and banned-vocabulary/em-dash flagging) and when to use it via an explicit 'Use when ...' clause with multiple triggers and a deadline window.	3 / 3
Trigger Term Quality	Natural user phrasing — 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread' — are exactly the phrases a user would say when they need this skill.	3 / 3
Distinctiveness Conflict Risk	A clear niche — pre-submission review of technical papers with a severity taxonomy and banned-vocabulary scan — with distinct triggers unlikely to fire for drafting or general editing skills.	3 / 3
	Total	12 / 12 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: aff5de9

Reviewed: 23 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.