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 hdu-ailab/EasyResearch --skill research-paper-writinggit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWrote 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/hdu-ailab/easyresearch/research-paper-writing)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/research-paper-writing"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/research-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/hdu-ailab/easyresearch/research-paper-writing"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/research-paper-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00164 | $0.03582 |
| Opus 5 | $0.00082 | $0.01791 |
| Sonnet 5 | $0.00033 | $0.00716 |
| Haiku 4.5 | $0.00016 | $0.00358 |
Grade A, and why
research-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 7d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Paper Writing
Scope
Use this skill for writing or revising an empirical research manuscript after
there is enough experimental evidence to support its method and result claims.
For a survey, review, tutorial, taxonomy, or literature-synthesis paper, use
survey-paper-writing; do not apply this Skill's baseline, seed, proposed-model,
or ablation gate to literature synthesis. For a hybrid survey with an original
benchmark, apply this Skill only to benchmark-derived claims.
This skill is not responsible for exploratory experiments or PDF conversion. Use research-project-workflow to orchestrate the full paper project. Use experiment for experiment setup, baselines, model trials, dataset expansion, and experiment-record management. Use paper-search for paper discovery. Use arxiv for arXiv metadata, BibTeX, and citation checks. Use pdf-to-markdown to convert public or user-provided PDFs before reading them deeply.
Non-Negotiable Rule
Do not start writing the manuscript body just because a few small or incomplete experiments exist.
Even when evidence is sufficient, never start drafting the full paper without explicit user consent. Only write the manuscript when the user explicitly says to draft, write, compose, or complete the paper. An initial end-to-end request to complete a paper carries that authority through accepted stages; do not ask again. Without such a directive, produce readiness reports and gap analyses instead.
Writing Readiness Gate
Before drafting Introduction, Method, Experiments, or Abstract, inspect the available experiment evidence.
Read when available:
<experiment-root>/experiment-record.md<experiment-root>/results/<experiment-root>/outputs/only for context or failed-run diagnosis<experiment-root>/logs/only when needed to verify commands or failures- result summary CSV/JSON/Markdown files
- ablation files and dataset/split manifests
The accepted Experiment handoff selects <experiment-root>: experiments/ for
local execution or experiment_ssh/ for SSH execution. These paths are relative
to the exact session cwd. Never merge evidence across both roots or guess the
mode when the handoff is missing. Follow another existing local layout only when
the dispatch explicitly supplies it.
What ships with it
55 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.
- references/autoreason-methodology.md 19 KB
- references/checklists.md 13 KB
- references/citation-workflow.md 15 KB
- references/experiment-patterns.md 26 KB
- references/human-evaluation.md 18 KB
- references/manuscript-revision-audit.md 4.9 KB
- references/paper-types.md 16 KB
- references/reviewer-guidelines.md 13 KB
- references/sources.md 9.2 KB
- references/writing-guide.md 16 KB
- templates/aaai2026/aaai2026-unified-supp.tex 4.4 KB
- templates/aaai2026/aaai2026-unified-template.tex 62 KB
- templates/aaai2026/aaai2026.bib 4.7 KB
- templates/aaai2026/aaai2026.bst 29 KB
- templates/aaai2026/aaai2026.sty 12 KB
- templates/aaai2026/README.md 18 KB
- templates/acl/acl_latex.tex 14 KB
- templates/acl/acl_lualatex.tex 3.0 KB
- templates/acl/acl_natbib.bst 44 KB
- templates/acl/acl.sty 11 KB
- templates/acl/anthology.bib.txt 1.1 KB
- templates/acl/custom.bib 2.0 KB
- templates/acl/formatting.md 18 KB
- templates/acl/README.md 2.1 KB
- templates/colm2025/colm2025_conference.bib 496 B
- templates/colm2025/colm2025_conference.bst 26 KB
- templates/colm2025/colm2025_conference.pdf 120 KB
- templates/colm2025/colm2025_conference.sty 7.5 KB
- templates/colm2025/colm2025_conference.tex 13 KB
- templates/colm2025/fancyhdr.sty 20 KB
- templates/colm2025/math_commands.tex 12 KB
- templates/colm2025/natbib.sty 44 KB
- templates/colm2025/README.md 51 B
- templates/iclr2026/fancyhdr.sty 20 KB
- templates/iclr2026/iclr2026_conference.bib 629 B
- templates/iclr2026/iclr2026_conference.bst 26 KB
- templates/iclr2026/iclr2026_conference.pdf 196 KB
- templates/iclr2026/iclr2026_conference.sty 8.8 KB
- templates/iclr2026/iclr2026_conference.tex 17 KB
- templates/iclr2026/math_commands.tex 12 KB
- templates/iclr2026/natbib.sty 44 KB
- templates/icml2026/algorithm.sty 2.2 KB
- templates/icml2026/algorithmic.sty 7.2 KB
- templates/icml2026/example_paper.bib 2.0 KB
- templates/icml2026/example_paper.pdf 189 KB
- templates/icml2026/example_paper.tex 29 KB
- templates/icml2026/fancyhdr.sty 31 KB
- templates/icml2026/icml_numpapers.pdf 2.8 KB
- templates/icml2026/icml2026.bst 27 KB
- templates/icml2026/icml2026.sty 27 KB
- templates/neurips2025/extra_pkgs.tex 2.8 KB
- templates/neurips2025/main.tex 574 B
- templates/neurips2025/Makefile 1.0 KB
- templates/neurips2025/neurips.sty 11 KB
- templates/README.md 6.5 KB
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.
- 7d ago Changed · +42 lines af10f91afe8b
- 11d ago First seen · 322 lines · 164 tokens per session scan A df0ef6ed71ad
research-paper-writing is a skill published in the GitHub repository hdu-ailab/EasyResearch (13 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 3,582 once invoked, about $0.0008 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
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of currentresearch with auditable repo…
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with…
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or…
env-and-assets-bootstrap
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full…
safe-debug
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research…