Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sidiangongyuan/codex-skills-library --skill paper-refinement-skillsgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-refinement-skills)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-refinement-skills"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-refinement-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-refinement-skills"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-refinement-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02100 |
| Opus 5 | $0.00029 | $0.01050 |
| Sonnet 5 | $0.00012 | $0.00420 |
| Haiku 4.5 | $0.00006 | $0.00210 |
Grade A, and why
paper-refinement-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Refinement Skills
Overview
Use this skill when revising academic papers section by section. Preserve verified technical claims, keep terminology consistent, and adapt tone and density to the target venue.
Incremental Maintenance
- For a local number, caption, or format fix, reuse the established paper story and table contract. Verify the scoped source and connected text only; do not restart story questioning, re-freeze the contract, run a full literature review, or rerun experiments for cosmetic-only changes.
Workflow
- Read the target sentence, paragraph, and immediate surrounding context before editing.
- Identify whether the problem is structural or local: argument flow, scope, redundancy, terminology drift, or sentence quality.
- Identify the paper story before polishing: dataset/benchmark, method, analysis, or system. Experiments should support that story, not read like a run log.
- Freeze the claim hierarchy: one central paper claim first, with ablations, reliability studies, and diagnostics presented only as supporting evidence.
- Revise conservatively: preserve verified claims, datasets, equations, and citations unless the user explicitly asks to change them.
- When a passage is repeatedly misunderstood, fix the ambiguity at its source instead of only softening nearby claims.
- When confusion comes from a category error, fix the category boundary before polishing the sentence. Separate dataset/protocol contents from diagnostic experiments, model design from evaluation controls, and baseline-conversion fairness from the paper's main contribution.
- Check the revised passage against the rest of the paper for claim consistency, notation, references, figure/table links, and rendering risks.
- After a figure or table changes, search nearby and later prose for stale terminology, old row names, obsolete panel structure, and implementation leakage. A consistent table has a matching body, caption, and local explanatory paragraph. If a new row is added to a delta-coded or reference-coded table, the prose must name the comparison reference and report movement in the same direction as the table cells. Read new numeric values from the project's source summary or artifact, check precision, reference, metric direction, and delta sign, and sync the scoped caption, nearby prose, and cross-references.
- Promote only reusable cross-paper heuristics into this skill, and update it or its references only with explicit user authorization. Exclude private project details from the reusable workflow.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +20 lines 2d10f702cb89
- 11d ago First seen · 103 lines · 58 tokens per session scan A d3ebcb86f798
paper-refinement-skills is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 2,100 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
pubmed-database
Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring. Use when a task needs biomedical literature from PubMed rather than general web search.
zeroplot
Create editable charts, diagrams, figures, posters, or slides from intent, data, or references.
pathway-enrichment
Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. Use whenever the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or…
polars-bio
High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.
scientific-visualization
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.