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/novelty/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/novelty)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/novelty"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/novelty/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/novelty"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/novelty.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 | $0.00028 | $0.02369 |
| Opus 5 | $0.00014 | $0.01184 |
| Sonnet 5 | $0.00006 | $0.00474 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
novelty 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 10d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/novelty
对一个研究想法或方法进行多源 novelty 验证。搜索 WebSearch、Semantic Scholar、 wiki 内已有工作和 arXiv 最新预印本,然后由 Review LLM 交叉验证,输出 novelty 评分(1-5)、 最相似已有工作、差异化要点和下一步建议。 可独立使用,也被 /ideate Phase 4 调用。
Inputs
target:以下之一:- idea 的自由文本描述(一段话或几句话)
- wiki 中 ideas/ 页面的 slug(如
sparse-lora-for-edge-devices) - 论文标题或 arXiv URL(检查该论文方法的 novelty)
--quick:快速模式,跳过 Review LLM cross-verify(Step 3),仅做搜索--verbose:输出完整搜索结果,不仅是摘要
Outputs
- Novelty Report(输出到终端,不写入 wiki):
- Novelty Score(1-5)
- 最相似的已有工作列表(top 3-5)
- 与每个已有工作的差异化要点
- Review LLM 交叉验证意见(除非 --quick)
- 推荐行动:proceed / modify / abandon
- 该 skill 是只读查询,不修改 wiki 任何内容
Wiki Interaction
Reads
wiki/papers/*.md— 搜索已有论文中是否有类似方法wiki/concepts/*.md— 检查概念重叠wiki/ideas/*.md— 检查是否与已有 idea 重复(特别是 failed ideas 的 failure_reason)wiki/claims/*.md— 检查 idea 所依赖的 claims 当前状态wiki/graph/context_brief.md— 获取全局上下文辅助搜索
Writes
- 无。Novelty check 是纯查询操作,不修改 wiki。
Graph edges created
- 无。
Workflow
前置:确认工作目录为 wiki 项目根(包含 wiki/、raw/、tools/ 的目录)。
Step 1: 提取方法签名
- 若 target 是 slug:读取
wiki/ideas/{slug}.md,提取 title、Hypothesis、Approach sketch - 若 target 是自由文本:直接使用
- 若 target 是 arXiv URL:下载摘要,提取方法描述
- 从 target 中提取「方法签名」——方法的核心要素:
- What:做什么(任务/目标)
- How:用什么方法(技术路线)
- Why novel:声称的创新点
- 生成 3-5 个核心关键词用于后续搜索
Step 2: 多源搜索
并行执行以下搜索(使用 Agent tool 并发):
Source A — Web Search(5+ 查询):
- 直接查询:
"<method-name>" + "<task>"精确短语搜索 - 组件查询:
<component-1> + <component-2> + <domain>组件组合搜索 - Survey 查询:
"survey" OR "review" + <task-area> + 2024 2025 - 竞品查询:
<alternative-approach> + <same-task> - 最新查询:
<method-keywords> + arXiv + 2025 2026
Source B — Semantic Scholar + DeepXiv:
python3 tools/fetch_s2.py search "<method-keywords>" --limit 20
python3 tools/fetch_deepxiv.py search "<method-keywords>" --mode hybrid --limit 20
合并两个来源的结果(按 arxiv_id 去重)。DeepXiv 的混合语义搜索能发现 S2 关键词搜索遗漏的语义相似工作。
- 对 top 5 结果获取详情和 TLDR:
python3 tools/fetch_s2.py paper <s2_id>
python3 tools/fetch_deepxiv.py brief <arxiv_id>
使用 DeepXiv brief 的 TLDR 辅助快速判断方法相似度。 若 DeepXiv 不可用:仅使用 S2 搜索(回退到原有行为)。
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.
- 10d ago First seen · 201 lines · 28 tokens per session scan A 74a0e5c84106
novelty is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 2,369 once invoked, about $0.0001 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…
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"…
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…