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 shubham0704/claude-skills --skill refining-ml-papersgit clone --depth 1 https://github.com/shubham0704/claude-skillsWrote 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/shubham0704/claude-skills/refining-ml-papers)<a href="https://agentmods.dev/skills/shubham0704/claude-skills/refining-ml-papers"><img src="https://agentmods.dev/badge/skills/shubham0704/claude-skills/refining-ml-papers/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/shubham0704/claude-skills/refining-ml-papers"><img src="https://agentmods.dev/badge/skills/shubham0704/claude-skills/refining-ml-papers.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 | $0.00075 | $0.04413 |
| Opus 5.5 | $0.00030 | $0.01765 |
| Sonnet 5.5 | $0.00015 | $0.00883 |
| Haiku 4.5 | $0.00007 | $0.00441 |
Grade A, and why
refining-ml-papers 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 18d 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refining ML Papers: From Feedback to Camera-Ready
This skill captures battle-tested patterns for revising scientific LaTeX papers in response to reviewer/advisor feedback. Built from extensive revision work on multi-file ICML-style papers with Overleaf git workflows.
When to Use This Skill
Invoke when the user:
- Has reviewer or advisor feedback to address
- Wants to restructure paper sections (move content, merge sections)
- Needs to explain tables or figures with concrete examples
- Asks to improve exposition clarity or reduce redundancy
- Wants to fix LaTeX compilation issues after restructuring
- Needs to prepare a camera-ready or arXiv version
Core Methodology
Phase 1: Understand the Paper Architecture
Before making ANY changes:
- Map the file structure:
Globfor**/*.texto find all LaTeX files - Identify the main file and all
\input{}dependencies - Read the target sections completely before editing
- Check for shared macros: Look for
\providecommand/\newcommandpatterns that indicate cross-file dependencies - Note existing labels:
Grepfor\label{and\ref{to understand cross-reference graph
# Typical modular structure:
main_arxiv.tex # Preamble + abstract + introduction + \input{} calls
methods.tex # Section 3
experiments.tex # Section 4
appendix.tex # Appendix
appendix_casimir.tex # Specialized appendix
references.bib # Bibliography
Phase 2: Plan Changes with Feedback Mapping
Map each piece of feedback to a concrete file + line range + action:
| Feedback | Action | File(s) | Risk |
|---|---|---|---|
| "Problem statement too late" | Move to Sec 1 + slim Sec 3 | main.tex + methods.tex | Cross-ref breakage |
| "Table entries unclear" | Add concrete instantiations paragraph | main.tex | None |
| "Sections redundant" | Merge + back-reference | methods.tex | Label conflicts |
| "Abstract doesn't state problem" | Restructure abstract | main.tex | None |
What ships with it
5 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.
- 18d ago Changed · +10 lines 73dbdbeafec1
- 26d ago Changed · +100 lines 68506425ff18
- 1mo ago First seen · 298 lines · 75 tokens per session scan A 7316eda8f9b2
refining-ml-papers is a skill published in the GitHub repository shubham0704/claude-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 75 tokens to every session and 4,413 once invoked, about $0.0003 per session on Opus 5.5. 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
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
running-cluster-experiments
Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing walltime, shaping jobs and arrays, deciding what to submit first, or after a job hit its walltime, produced no results, silently ran the wrong configuration, or got the wrong number of GPUs.
explaining-derivations
Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader without formal mathematical training, producing a worked companion document, or establishing whether a derivation can be justified at all. Triggers on "explain this derivation", "walk me through this…
self-surveying-literature
Audit a research paper draft (LaTeX sources + .bib) for related work it should cite but does not, above all close prior work that undermines its novelty claims. Searches Semantic Scholar, arXiv, DBLP and Crossref, follows citation graphs, verifies every hit, and produces a prioritized, evidence-backed report plus…
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…