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/paper-plan/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/paper-plan)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/paper-plan"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/paper-plan/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/paper-plan"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/paper-plan.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 | $0.00036 | $0.04173 |
| Opus 5.5 | $0.00014 | $0.01669 |
| Sonnet 5.5 | $0.00007 | $0.00835 |
| Haiku 4.5 | $0.00004 | $0.00417 |
Grade A, and why
paper-plan 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 1mo 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper-plan
从 wiki 的 claim graph 编译论文大纲。 输入 target claims(status: supported 或 weakly_supported),指定目标会议/期刊, 从 wiki 编译 evidence map → 确定叙事结构 → 生成章节大纲 + figure plan + citation plan。 Review LLM review 是必选步骤(作为 area chair 审查大纲说服力)。 输出 PAPER_PLAN.md 到 wiki/outputs/。
关键差异:大纲由 claim graph 驱动 — 每个 section 存在是因为它支撑某个 claim, 而非因为论文惯例要求有该 section。
Inputs
claims:目标 claims 的 slug 列表(空格分隔)- 每个 claim 应为
supported或weakly_supported状态 - 若包含
proposed或challenged状态的 claim,发出警告但继续
- 每个 claim 应为
--venue(必选):目标会议/期刊,决定页数限制和格式要求- 支持:
ICLR/NeurIPS/ICML/ACL/CVPR/IEEE
- 支持:
--title(可选):工作标题,若不提供则从 target claim 生成
Outputs
wiki/outputs/paper-plan-{slug}-{date}.md— 完整论文计划(PAPER_PLAN.md)wiki/graph/edges.jsonl— 新增 derived_from 边(plan → source claims/papers)wiki/graph/context_brief.md— 重建wiki/log.md— 追加日志- PAPER_PLAN_REPORT(输出到终端)— 计划摘要
Wiki Interaction
Reads
wiki/claims/*.md— 目标 claims 的 status、confidence、evidence 列表、conditionswiki/experiments/*.md— claims 的 supporting experiments(结果、metrics、key_result)wiki/papers/*.md— evidence 来源论文(Method、Results、Related)wiki/concepts/*.md— 涉及的技术概念(支持 Method 章节撰写)wiki/topics/*.md— 研究方向上下文(支持 Introduction 定位)wiki/ideas/*.md— 原始 idea 的 motivation 和 hypothesiswiki/graph/context_brief.md— 全局上下文wiki/graph/open_questions.md— 知识缺口(标注论文 limitation)wiki/graph/edges.jsonl— 关系图谱(构建叙事逻辑链).claude/skills/shared-references/academic-writing.md— 写作原则.claude/skills/shared-references/citation-verification.md— 引用纪律
Writes
wiki/outputs/paper-plan-{slug}-{date}.md— 论文计划文件wiki/graph/edges.jsonl— derived_from 边wiki/graph/context_brief.md— 重建wiki/log.md— 追加操作日志
Graph edges created
derived_from:paper-plan → claims(计划从哪些 claims 派生)derived_from:paper-plan → papers(计划引用哪些论文)
Workflow
前置:确认工作目录为 wiki 项目根(包含 wiki/、raw/、tools/ 的目录)。
Step 1: 加载 Claim Graph
- 读取所有 target claims 的
wiki/claims/{slug}.md - 对每个 claim,收集其 evidence 列表:
- 每条 evidence 的 source(paper slug 或 experiment slug)
- evidence type(supports / contradicts / tested_by / invalidates)
- evidence strength(weak / moderate / strong)
- 对每条 evidence source,读取对应的 wiki 页面:
wiki/experiments/{source}.md→ key_result、metrics、outcomewiki/papers/{source}.md→ Method、Results
- 从
wiki/graph/edges.jsonl加载相关边,构建 claims 之间的关系 - 读取
wiki/graph/context_brief.md获取全局上下文 - 读取
wiki/graph/open_questions.md标注 known limitations
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.
- 1mo ago First seen · 403 lines · 36 tokens per session scan A 7c6730c1637a
paper-plan is a skill published in the GitHub repository Lambenthan/empiricalwiki (96 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 4,173 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.
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.
accounting-software-selection
Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
patent-map
A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.