aris-paper-writing

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

A well-structured orchestration skill: concrete commands, sequenced phases with validation gates, and a review feedback loop. Its only weakness is verbosity — some checkpoint templates and the timeline table are non-essential.

Suggestions

Drop or condense the emoji checkpoint message templates; they are presentation sugar, and Claude can format phase summaries without literal templates.

Remove the Typical Timeline table (or move it to a reference); duration estimates are fragile and add tokens that do not change what Claude does.

Tighten the Phase 6 Final Report block to a short bullet list of required fields instead of a full markdown template.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but the full emoji checkpoint templates (e.g. "📐 Paper plan complete:") and the Typical Timeline table are padding that could be trimmed without losing guidance.	2 / 3
Actionability	Gives exact, copy-paste-ready slash commands per phase (e.g. `/aris-paper-plan "$ARGUMENTS"`), concrete constants (VENUE, MAX_IMPROVEMENT_ROUNDS), named output files, and the literal compile command `latexmk -pdf`.	3 / 3
Workflow Clarity	The six phases are clearly sequenced with explicit checkpoints between them, hard gates ("Compilation must succeed before entering the improvement loop. Fix all errors first"), and a review→fix→recompile feedback loop in Phase 5.	3 / 3
Progressive Disclosure	Content is well-organized into clear one-level sections (Overview, Constants, Inputs, Pipeline phases, Key Rules) with external sub-skill references signalled once ("See /aris-paper-figure SKILL.md for details") rather than nested, and no bundle files need splitting.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 description: concrete actions, an explicit Use-when trigger clause with natural multilingual terms, and a distinct niche. It is written in third person with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop" — and a concrete deliverable ("narrative report to a polished, submission-ready PDF"), matching the score-3 anchor.	3 / 3
Completeness	Clearly answers what it does (orchestrates a five-stage pipeline to a submission-ready PDF) and when to use it via an explicit "Use when..." clause, satisfying both halves of the score-3 anchor.	3 / 3
Trigger Term Quality	Provides natural terms a user would actually say in both English and Chinese — "write paper pipeline", "paper writing", "写论文全流程", "从报告到PDF" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — the complete paper generation pipeline — with distinct, specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-paper-writing/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.