A skill that writes a paper's Related Work section from knowledge stored in a research wiki. Related Work is the part of a paper that compares the study with earlier research.

Use it to create a LaTeX section with paper citations or a Markdown section with wiki links, based on a research question, selected ideas, or a paper plan.

It groups papers by research direction instead of producing a disconnected paper-by-paper list, while checking citations and following academic-writing rules.

How skyllwt/AutoSci configures Claude Code

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,706 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/survey/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/skyllwt/AutoSci

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/skyllwt/autosci/survey/github.svg)](https://agentmods.dev/skills/skyllwt/autosci/survey)

Your own site

<a href="https://agentmods.dev/skills/skyllwt/autosci/survey"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/survey/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/skyllwt/autosci/survey"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/survey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,419 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00030	$0.02419
Opus 5.5	$0.00012	$0.00968
Sonnet 5.5	$0.00006	$0.00484
Haiku 4.5	$0.00003	$0.00242

Measured 2mo ago against content hash 1c1919f457aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

survey 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 2mo 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.

.claude/skills/survey/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/survey

Generate a Related Work section ready for direct use in a paper, based on existing wiki knowledge. Draw material from wiki/papers/, concepts/, topics/; group by research direction (not paper-by-paper listing). End each group with a statement of how it differs from this work. Citations follow citation-verification.md; writing follows academic-writing.md Related Work rules. Supports LaTeX and Markdown output formats.

Inputs

query: one of:
- research question description (free text, e.g. "parameter-efficient fine-tuning for LLMs")
- list of idea slugs (from wiki/ideas/, used to organize related work around specific ideas)
- path to PAPER_PLAN.md (extract Related Work section definition from it)
--format (optional, default latex): output format
- latex: \cite{key} citations, embeddable directly in a paper
- markdown: [[slug]] wikilink citations, for wiki archiving
--max-papers (optional, default 30): maximum number of papers to cite

Outputs

wiki/outputs/related-work-{slug}-{date}.md — Related Work text (archived)
wiki/graph/edges.jsonl — derived_from edges (if a new output is created)
wiki/log.md — appended log entry
Terminal output — Related Work body text (for direct copy-paste)

Wiki Interaction

Reads

wiki/papers/*.md — Problem & Context, Key idea, Experiment & Results, Related, My take
wiki/concepts/*.md — Definition, Variants, Comparison, Known limitations
wiki/topics/*.md — Overview, Timeline, Open problems, Seminal works
wiki/ideas/*.md — Hypothesis, Motivation, origin_gaps (if input is idea slugs)
wiki/methods/*.md — Mechanism, Procedure, source_papers (when ideas reference methods)
wiki/index.md — content catalog, filtered by importance
wiki/graph/context_brief.md — global context
wiki/graph/edges.jsonl — inter-paper semantic relationships (same_problem_as, similar_method_to, builds_on, challenges)
.claude/skills/shared-references/academic-writing.md — Related Work writing rules
.claude/skills/shared-references/citation-verification.md — citation discipline

Read the full file on GitHub · 217 lines

Changes

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.

2mo ago First seen · 217 lines · 30 tokens per session scan A 1c1919f457aa

Subscribe to this mod's changes

survey is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 2,419 once invoked, about $0.0001 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 2026-08-30.

Research Writing and docs

survey next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
surveyskyllwt/AutoSci	Skill	1.7k	1mo ago	MIT	A	30	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

AutoSci: Skill for Claude Code