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 survey-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/survey-paper-writing)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/survey-paper-writing"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/survey-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/survey-paper-writing"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/survey-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 | $0.00063 | $0.02566 |
| Opus 5 | $0.00032 | $0.01283 |
| Sonnet 5 | $0.00013 | $0.00513 |
| Haiku 4.5 | $0.00006 | $0.00257 |
Grade A, and why
survey-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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survey Paper Writing
Scope
Use this Skill for a survey, review, tutorial, or literature-synthesis manuscript. The core contribution is evidence-backed organization and synthesis across papers. Do not require baselines, a proposed model, five seeds, or ablations unless the requested survey includes an original benchmark or other empirical study.
Use research-paper-writing for an empirical method paper. Use
paper-material-package through Search when the source package is missing or
does not support the requested coverage. Never invent a citation, result,
taxonomy assignment, or field-wide conclusion.
Required Inputs
Inspect these exact-cwd artifacts:
ref_papers/source.jsonref_papers/paper-notes.md- selected readable sources under
ref_papers/text/and PDFs when needed - existing files under
manuscript/ - the topic, review scope, expected paper count, date/source constraints, target audience or venue when supplied, and drafting authority carried by dispatch
Follow another existing layout only when the dispatch explicitly identifies it.
Survey Readiness Gate
Draft survey prose only when all required conditions hold or the dispatch records an explicit accepted limitation:
- The intended review scope and exclusions are clear enough to judge coverage.
- The material package meets the expected paper count, or the accepted shortfall and its consequence are explicit.
source.jsonandpaper-notes.mdhave one-to-one stablenote_keycoverage.- Papers used for substantive claims have complete factual cards and readable sources with evidence locators.
- Foundational work and relevant recent work are represented for the stated scope; frontier-only search results are not presented as field-complete.
- Bibliographic metadata and planned citation keys are verified.
- The dispatch explicitly authorizes the requested full draft or section. An initial request to complete the survey counts as full-draft authority.
Partial cards may remain as metadata-only context, but do not use them to support
claims beyond their available evidence. If the gate fails, write
manuscript/writing-readiness-report.md with the verdict, usable coverage,
blocking gaps, a targeted Search request, and the drafting scope currently safe.
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 · +57 lines bcfce077c597
- 11d ago First seen · 219 lines · 63 tokens per session scan A c418b695a3e4
survey-paper-writing is a skill published in the GitHub repository hdu-ailab/EasyResearch (13 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,566 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 2026-08-30.
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…
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.
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-code
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together…
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…
run-train
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized…