Scan reports · wanshuiyin/Auto-claude-code-research-in-sleep
auto-paper-improvement-loop: scan report
Autonomously improve a generated paper via GPT-6-Astra 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… An automated scan of this public skill from wanshuiyin/Auto-claude-code-research-in-sleep: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
60/100 · grade D
wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-paper-improvement-loop at 43a5daf
Spec 5 · Efficiency 5 · Clarity 25 · Security 25 (each out of 25)
Always loaded 67 tokens · on trigger 10,336 · on demand 0
eff/body-tokenswarn · SKILL.md~10336 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.eff/body-lineswarn · SKILL.mdSKILL.md body is 705 lines; keep it under 500 and move detail into reference files.spec/non-portable-keyswarn · SKILL.mdNon-spec frontmatter (argument-hint). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.spec/broken-refwarn · SKILL.md:10References ../shared-references/reviewer-backends.md, which isn't in the skill folder.spec/broken-refwarn · SKILL.md:47References PAPER_IMPROVEMENT_LOG.md, which isn't in the skill folder.spec/broken-refwarn · SKILL.md:220References PAPER_IMPROVEMENT_LOG.md, which isn't in the skill folder.spec/broken-refwarn · SKILL.md:489References skills/kill-argument/SKILL.md, which isn't in the skill folder.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | wanshuiyin/Auto-claude-code-research-in-sleep |
| Skill folder | skills/auto-paper-improvement-loop |
| Stars | 17,701 |
| License | MIT |
| Commit scanned | 43a5daf |
| Scanned | 2026-10-19 |
| Files | 1 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
For maintainers
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/wanshuiyin-auto-paper-improvement-loop)
Alternatives
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- TDD LoopOne red, the least green, a refactor, a commit. Repeat.Loads when the user wants a feature or fix driven by tests, one slice at a time.5 rules · Code ReviewScan 100$9
- Architecture MapMeasures the real graph. Ranks the five worst problems.Loads when the user wants to understand, onboard onto or improve a codebase's structure.5 rules · Code ReviewScan 100$12
- Still to LoopA still becomes a seamless 4-second loop.Loads when the user wants to animate a still image.3 rules · AI ModelsScan 100$12
Same repository
More from wanshuiyin/Auto-claude-code-research-in-sleep
- ablation-plannerGrade A96/100
- alphaxivGrade A96/100
- analyze-resultsGrade B85/100
- arxivGrade A94/100
- auto-review-loopGrade F50/100
- auto-review-loop-llmGrade A96/100
- auto-review-loop-minimaxGrade B85/100
- citation-auditGrade C70/100
- citation-crosscheckGrade C74/100
- claims-draftingGrade B80/100
- comm-lit-reviewGrade A100/100
- deepxivGrade A96/100
FAQ
Questions
- Is auto-paper-improvement-loop safe to install?
- No known risky patterns found. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit 43a5daf on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.