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 nanoAgentTeam/research-claw --skill ml-paper-writinggit clone --depth 1 https://github.com/nanoAgentTeam/research-clawWrote 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/nanoagentteam/research-claw/ml-paper-writing)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/ml-paper-writing"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/ml-paper-writing/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/nanoagentteam/research-claw/ml-paper-writing"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/ml-paper-writing.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 | $0.00040 | $0.00612 |
| Opus 5 | $0.00020 | $0.00306 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
ml-paper-writing 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[SKILL: ML PAPER COMMON WORKFLOW]
Activate when: user asks to write/revise/check any ML/AI paper, regardless of venue (conference or journal).
Purpose
This skill is the shared, venue-agnostic layer. Venue-specific skills should handle template/macros/page limits, while this skill handles writing quality, citation integrity, reviewer alignment, and submission checks.
Coverage Boundary
- This skill covers common writing/citation/review SOP for both conferences and journals.
- This skill does not provide journal-specific template setup (
.cls/.sty/.bst, submission system steps, journal-only formatting policies). - For journals, pair this skill with the journal's official author guide or a journal-specific venue skill.
Required Reference Files
Use these references from references/ as the source of truth:
writing-guide.md— paper narrative and section-level writing qualitycitation-workflow.md— verified citation workflow and hallucination preventionreviewer-guidelines.md— reviewer evaluation lenses and rebuttal-oriented checkschecklists.md— mandatory checklist gates before submission
Execution Workflow
Step 1: Clarify Scope
- Confirm paper type: conference or journal
- Confirm current stage: first draft / revision / camera-ready
- Confirm what is venue-specific vs common writing work
Step 2: Apply Writing Quality Workflow
- Use
writing-guide.mdto enforce:- clear contribution framing
- precise claims and evidence alignment
- section-level coherence (abstract, intro, method, results, limitations)
Step 3: Apply Citation Integrity Workflow
- Follow
citation-workflow.mdstrictly - Never fabricate citations from memory
- If citation cannot be verified, mark as explicit placeholder and report it
Step 4: Apply Reviewer Lens
- Use
reviewer-guidelines.mdto evaluate:- technical soundness
- novelty/significance
- clarity and reproducibility
- Add missing evidence/ablation/limitations where needed
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.
- 10d ago First seen · 76 lines · 40 tokens per session scan A a38e1d290ece
ml-paper-writing is a skill published in the GitHub repository nanoAgentTeam/research-claw (292 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 612 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
neuroarxiv
Grounds a coding agent's architecture decisions in real arXiv prior art before it builds something new. Reads arXiv category-wise via real HTTP fetch, spawns parallel isolated reads across the papers found, scores/clusters them, then converges on ONE recommended path with citations, a first step, and known prior-art…
research-expert
Expert-level research methodology, academic writing, statistical analysis, and scientific investigation. Use when the user mentions methodology, statistics, academic writing, or experimental design, or when the task involves Research Design, Statistical Analysis, or Data Analysis.
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
arxiv-fetch
Fetch the latest arXiv papers and generate an on-demand digest. Use when the user asks to fetch/check today's (or the latest) arXiv papers, find new papers on a topic, or generate an ad-hoc arXiv digest. The agent judges relevance itself — no API keys needed.
ieee-acm-paper-writing
Draft, rewrite, compress, structure, calibrate, humanize, or audit engineering manuscripts for IEEE and ACM Transactions, journals, and conferences, with optional self-contained HTML audit maps. Use for abstracts, introductions, related work, system models, mathematical formulations, algorithms, experimental methods…
paper-read
Read, analyze, and extract knowledge from academic papers. Handles PDFs and arXiv links. Produces structured summaries, identifies core contributions, evaluates methodology, and enables cross-paper comparison.