Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/auto-paper-improvement-loop
Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds.
Passed 14 of 18 test cases with the skill, and 7 of 18 without it.
and 13 more in the full report
11 fixed7 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When storing intermediate PDF builds during the multi-round improvement workflow, what exact file path names should be used for the original paper and subsequent builds?
| Checked | Without skill | With skill |
|---|---|---|
| Names original pre-edit build paper/main_round0_original.pdf. | Missed | Passed |
| Names output files main_round1.pdf and main_round2.pdf. | Missed | Passed |
The instructions your model reads when the skill loads.
Autonomously improve the paper at: $ARGUMENTS
This skill is designed to run after Workflow 3 (/paper-plan → /paper-figure → /paper-write → /paper-compile). It takes a compiled paper and iteratively improves it through external LLM review.
Unlike /auto-review-loop (which iterates on research — running experiments, collecting data, rewriting narrative), this skill iterates on paper writing quality — fixing theoretical inconsistencies, softening overclaims, adding missing content, and improving presentation.
gpt-5.4 — Model used via a secondary Codex agent for paper review.PAPER_IMPROVEMENT_LOG.md — Cumulative log of all rounds, stored in paper directory.true, pause after each round's review and present score + weaknesses to the user. The user can approve fixes, provide custom modification instructions, skip specific fixes, or stop early. When false (default), runs fully autonomously.💡 Override:
/auto-paper-improvement-loop "paper/" — human checkpoint: true
paper/main.pdf + LaTeX source files.tex files — concatenated for review promptIf the context window fills up mid-loop, Codex auto-compacts. To recover, this skill writes PAPER_IMPROVEMENT_STATE.json after each round:
{
"current_round": 1,
"agent_id": "019ce736-...",
"last_score": 6,
"status": "in_progress",
"timestamp": "2026-03-13T21:00:00"
}
On startup: if PAPER_IMPROVEMENT_STATE.json exists with "status": "in_progress" AND timestamp is within 24 hours, read it + PAPER_IMPROVEMENT_LOG.md to recover context, then resume from the next round. Otherwise (file absent, "status": "completed", or older than 24 hours), start fresh.
test cases passed, vs 7 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.