Borrowing it
Nothing to install: this file belongs to Lambenthan/empiricalwiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/survey/SKILL.mdgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote 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/lambenthan/empiricalwiki/survey)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/survey"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/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.
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/survey"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/survey.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 | $0.00035 | $0.02593 |
| Opus 5 | $0.00017 | $0.01296 |
| Sonnet 5 | $0.00007 | $0.00519 |
| Haiku 4.5 | $0.00003 | $0.00259 |
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 9d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/survey
基于 wiki 已有知识，生成可直接用于论文的 Related Work 章节。 从 wiki/papers/、concepts/、topics/ 取材，按研究方向分组（非逐篇罗列）， 每组以「与本文的区别」收尾。引用遵循 citation-verification.md， 写作遵循 academic-writing.md 的 Related Work 规则。 支持 LaTeX 和 Markdown 两种输出格式。
Inputs
query：以下之一：- 研究问题描述（自由文本，如 "parameter-efficient fine-tuning for LLMs"）
- claim slugs 列表（从 wiki/claims/ 中，用于围绕特定 claims 组织相关工作）
- PAPER_PLAN.md 路径（从中提取 Related Work section 定义）
--format（可选，默认latex）：输出格式latex：\cite{key}引用，可直接嵌入论文markdown：[[slug]]wikilink 引用，用于 wiki 存档
--max-papers（可选，默认 30）：最多引用的论文数量
Outputs
wiki/outputs/related-work-{slug}-{date}.md— Related Work 文本（归档）wiki/graph/edges.jsonl— derived_from 边（若新建 output）wiki/log.md— 追加日志- 终端输出 — Related Work 正文（方便直接复制）
Wiki Interaction
Reads
wiki/papers/*.md— Problem、Key idea、Results、Related、My takewiki/concepts/*.md— Definition、Variants、Comparison、Known limitationswiki/topics/*.md— Overview、Timeline、Open problems、Seminal workswiki/claims/*.md— Statement、source_papers（若输入为 claim slugs）wiki/ideas/*.md— Motivation（了解本文定位）wiki/index.md— 内容目录，按 importance 筛选wiki/graph/context_brief.md— 全局上下文wiki/graph/edges.jsonl— 论文间语义关系（same_problem_as、similar_method_to、complementary_to、builds_on、compares_against、improves_on、challenges、surveys）.claude/skills/shared-references/academic-writing.md— Related Work 写作规则.claude/skills/shared-references/citation-verification.md— 引用纪律
Writes
wiki/outputs/related-work-{slug}-{date}.md— 归档文件wiki/graph/edges.jsonl— derived_from 边wiki/log.md— 追加操作日志
Graph edges created
derived_from：related-work output → source papers
Workflow
前置：确认工作目录为 wiki 项目根（包含 wiki/、raw/、tools/ 的目录）。
Step 1: 定位相关知识
- 解析输入：
- 若为自由文本：提取关键词，在 wiki/index.md 中匹配 tags 和 titles
- 若为 claim slugs：读取每个 claim 的 source_papers，收集相关论文
- 若为 PAPER_PLAN 路径：读取 Related Work section 的 groupings 和 citations
- 读取 wiki/graph/context_brief.md 获取全局上下文
- 读取 wiki/graph/edges.jsonl：提取论文间语义关系（same_problem_as、similar_method_to、complementary_to、builds_on、compares_against、improves_on、challenges、surveys）
- 生成候选论文列表：
- 从 index.md 按 importance 降序排列
- 按 tags 和 domain 匹配度排序
- 限制为
--max-papers篇
- 若候选论文 < 5 篇：警告「相关论文不足，建议先 /ingest 更多论文」
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.
- 9d ago First seen · 217 lines · 35 tokens per session scan A 2a5a9a6ef0a9
survey is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 2,593 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
paper-workflow
A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…