SKILLEMALL.ai
GitHub ↗ RU Sign in

BB auto-paper-improvement-loop

Autonomously improve a generated paper via Claude review through claude-review MCP → 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.

wanshuiyin/Auto-claude-code-research-in-sleep Agent Skills author: wanshuiyin MIT 1 file body ≈ 8 961 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Autonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds.

As a process B 72/100 · Nearly there — weak spots: execution cost

AnalyzerLaTeXAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
82
Run on models
none yet
Process rating
B
72/100
Nearly there
Execution cost w 6
40
When it triggers w 12
50
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8961 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 25, 173, 406): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 72/100

  • 40Execution cost. Instruction body is 8961 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 74 steps, 1 vague phrases
  • 100Failures and branches. 9 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 246: enough signal without eating the budget
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 74 items
  • +3Output format is stated explicitly
  • +4Has examples (17 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.