Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JeanDiable/academic-research-pluginnpx agentmods add skills/jeandiable/academic-research-plugin/survey-writingWrote 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/jeandiable/academic-research-plugin/survey-writing)<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/survey-writing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/survey-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/jeandiable/academic-research-plugin/survey-writing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/survey-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 | $0.00109 | $0.02797 |
| Opus 5 | $0.00055 | $0.01399 |
| Sonnet 5 | $0.00022 | $0.00559 |
| Haiku 4.5 | $0.00011 | $0.00280 |
Grade A, and why
survey-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 12d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The survey-writing skill performs comprehensive survey composition by automating the research discovery and organization pipeline. It accepts a research topic, systematically searches for relevant papers across multiple query variations, constructs a hierarchical taxonomy of methodologies and approaches, drafts a publication-quality survey manuscript with narrative sections covering each category, generates comparison tables, and collects complete BibTeX metadata. The output is a structured survey paper suitable for direct submission or as a foundation for further refinement.
Arguments
Parse the following arguments from the invocation string:
-
<topic>(required) — The research field or topic to survey. Examples: "neural architecture search", "federated learning", "knowledge distillation in vision transformers". If ambiguous or overly broad (e.g., "machine learning"), ask the user to narrow the scope before proceeding. -
--paper-count(optional, default: 100) — Target number of unique papers to retrieve and analyze. Values typically range from 50 (narrow domain) to 200 (broad field). -
--date-range(optional, default: 3y) — Time window for paper publication. Format:Ny(years) orNm(months), e.g.,5y,18m,2y6m. Only retrieve papers published within this window. -
--existing-papers(optional) — Comma-separated list of local PDF file paths that the user has already collected. These PDFs will be parsed to extract titles and abstracts, which are incorporated into the survey for completeness. Format:paper1.pdf,papers/paper2.pdf,/absolute/path/paper3.pdf.
Setup
Install dependencies once before running the workflow:
pip install -r "BASE_DIR/scripts/requirements.txt"
where BASE_DIR is the base directory for this skill, automatically injected by Claude Code.
Workflow
Step 1: Broad Paper Search
Decompose the research topic into 5–8 query variations covering synonyms, closely related sub-topics, and key methodologies relevant to the field.
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.
- 12d ago First seen · 261 lines · 109 tokens per session scan A 1ce150a3bce3
survey-writing is a skill published in the GitHub repository JeanDiable/academic-research-plugin (23 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 2,797 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…