aris-auto-paper-improvement-loop

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.

Quality

88%

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

Quality

Content

85%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 highly actionable, well-sequenced workflow with strong validation and feedback loops. Its main weakness is monolithic structure: all prompts, tables, and guidance live in one file with no progressive disclosure via referenced bundle files.

Suggestions

Move the long GPT-5.4 review-prompt templates (Steps 2 and 5) and the fix-pattern tables into a references/ file (e.g. REVIEW_PROMPTS.md, FIX_PATTERNS.md) and link to them from the body to enable progressive disclosure.

Fix the duplicate 'Step 9' numbering (both 'Document Results' and 'Summary' are labeled Step 9) and consolidate the repeated human-checkpoint blocks into one referenced procedure.

Consider trimming or moving the empirical 'Typical Score Progression' section out of the main flow so the core workflow stays lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable tables, code blocks, and constants rather than padded prose, though the duplicated Step 9 headers, repeated human-checkpoint blocks, and the trailing 'Typical Score Progression' section could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: concrete bash (latexmk, pdfinfo, grep), MCP invocation blocks with configs, and ranked fix-pattern tables covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	Steps 0–9 are clearly sequenced with explicit validation checkpoints ('Verify: 0 undefined references, 0 undefined citations'), a format-check stage, and feedback loops ('If any overfull hbox > 10pt is found, fix it and recompile'), plus state persistence for recovery.	5 / 5
Progressive Disclosure	Good section structure via headers, but everything is inlined in a single ~290-line SKILL.md with no bundle files; long review-prompt templates and fix-pattern tables that belong in separate reference files are not split out or signaled.	3 / 5
	Total	17 / 20 Passed

Description

91%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 both the capability and the trigger conditions with bilingual natural phrases. Minor risk of overlap with the related auto-review-loop skill and slightly under-specified fix actions keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('review → implement fixes → recompile, for 2 rounds') with a specific reviewer model, but does not enumerate the kinds of fixes applied, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (improve a generated paper via review→fix→recompile for 2 rounds) and 'when' (a clear 'Use when...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage across two languages with synonyms and phrasings users would actually say ('改论文', 'improve paper', '论文润色循环', 'auto improve', 'iteratively polish a generated paper').	5 / 5
Distinctiveness Conflict Risk	Scoped to a generated-paper improvement loop with a specific reviewer, but 'auto improve' and 'improve paper' are somewhat generic and could overlap with the sibling /aris-auto-review-loop skill.	4 / 5
	Total	18 / 20 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-auto-paper-improvement-loop/SKILL.md
Commit: 01ef795

Reviewed: ~17 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.