aris-paper-write

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

Quality

83%

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

77%

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

The body is a highly actionable, well-sequenced writing workflow with concrete code and strong validation checkpoints. Its main weaknesses are redundancy of the venue citation/page-limit rules and a monolithic structure that keeps detailed guidance inline rather than offloading it to the referenced support files.

Suggestions

State the IEEE-vs-ML citation style and page-limit rules once in a single 'Venue rules' section and reference it from Step 3, Step 4, and Key Rules instead of repeating them.

Move the per-section drafting guidelines (§0–§5 + Appendix) into a dedicated reference file (e.g. references/section-guidelines.md) and keep SKILL.md as an overview pointing to it, improving progressive disclosure.

Trim explanatory justification prose such as the 'Why this matters' paragraph under the BibTeX fetch chain, keeping only the actionable fetch chain and the [VERIFY] fallback rule.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but repeats IEEE-vs-ML citation and page-limit rules across Step 3, Step 4, and Key Rules, and includes justifying prose ('Why this matters: ...') that could be trimmed.	2 / 3
Actionability	Provides copy-paste-ready executable material: venue \documentclass templates, the DBLP/CrossRef curl fetch chain, the codex MCP review invocation, math_commands, and a Python bib-filtering pattern.	3 / 3
Workflow Clarity	A clear Step 0–8 sequence with explicit validation checkpoints (backup before overwrite, DBLP fallback A/B/C, reverse-outline test, and a final checklist) gives strong error-recovery feedback loops.	3 / 3
Progressive Disclosure	Shared references (writing-principles.md, venue-checklists.md, citation-discipline.md) are one-level-deep and well-signaled, but the SKILL.md is monolithic with substantial inline detail that could be split out, and no bundle files exist under ./references/, ./scripts/, or ./assets/ to verify the referenced paths.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 is concise, uses third-person/imperative voice, and explicitly pairs a concrete capability with natural bilingual triggers. It fully satisfies the what-and-when requirement; the only weakness is that it describes a single action rather than a fuller set of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Draft LaTeX paper section by section from an outline') but does not enumerate multiple distinct capabilities, so it is not comprehensive.	2 / 3
Completeness	Clearly answers both 'what' (draft LaTeX paper section by section from an outline) and 'when' ('Use when user says ... or wants to generate LaTeX content from a paper plan').	3 / 3
Trigger Term Quality	Explicit natural triggers users would say, in both English and Chinese ('write paper', 'draft LaTeX', '写论文', '开始写'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	A clear niche (LaTeX paper drafting from a plan) with highly specific bilingual triggers makes it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-paper-write/SKILL.md
Commit: 6da7f7c

Reviewed: about 8 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.