Agent skill

Sn Prepare Citations

by OpenSenseNova in OpenSenseNova/SenseNova-Skills

用于终稿完成且脚注需要后处理时:去重 [^key] 引用,转换为 [N] 编号,并追加参考文献. An agent skill from OpenSenseNova/SenseNova-Skills.

MITAuto-check passedResearch & Science

Install Sn Prepare Citations

skills CLI
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-prepare-citations -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenSenseNova/SenseNova-Skills sn-prepare-citations --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenSenseNova/SenseNova-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sn-prepare-citations .claude/skills/sn-prepare-citations && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sn-prepare-citations
GitHub stars
5.7k
Token cost
~408 tokens
SKILL.md length
128 words
Files
2 (incl. scripts)
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

用于终稿完成且脚注需要后处理时:去重 [^key] 引用,转换为 [N] 编号,并追加参考文献. An agent skill from OpenSenseNova/SenseNova-Skills.

  • Works in 9 steps: 从所有 evidence.json 的 sources[] 收集引用元数据。 → 按 URL 归一化去重,同 URL source 合并为同一编号。 → 检测 [^dN.cM] claim-id 引用泄漏;能映射到 claim… → …
  • Tasks that involve Citation management
  • SKILL.md covers 推荐用法(sn-deep-research v2), 参数, 处理逻辑 and 控制器处理要求, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Sn Prepare Citations is an agent skill from OpenSenseNova/SenseNova-Skills. 用于终稿完成且脚注需要后处理时:去重 [^key] 引用,转换为 [N] 编号,并追加参考文献。

Its SKILL.md is about 410 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/prepare_citations.py`).

It sits in Research & Science, covering Citation management and Deep research. The repository describes itself as: Modular SenseNova skills for building AI-powered office assistants and productivity workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Citation management
  • Tasks that involve Deep research

Example prompts

  • “/sn-prepare-citations”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. 从所有 evidence.json 的 sources[] 收集引用元数据。
  2. 按 URL 归一化去重,同 URL source 合并为同一编号。
  3. 检测 [^dN.cM] claim-id 引用泄漏;能映射到 claim evidence 时替换为对应 source_id,不能映射则报告 unresolved。
  4. 扫描正文中的 [^source_id],按首次出现顺序分配编号。
  5. 替换 [^source_id] → [N],移除脚注定义行。
  6. 根据 outline 插入或校准 L0 / TOC。
  7. 追加 ## 参考文献。
  8. 写出 report.md 和同目录 citations.json。
  9. stdout 输出结构化 JSON,包含 orphan citations、claim-id leakage、TOC 和 L0 状态。

What it can do on your machine

Read from SKILL.md and the folder at commit 7838651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sn Prepare Citations loads about 408 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~408

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenSenseNova/SenseNova-Skills at commit 7838651, republished under its MIT licence (© OpenSenseNova). 128 words, ~408 tokens.

Download SKILL.mdSave it as .claude/skills/sn-prepare-citations/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sn-prepare-citations
description
用于终稿完成且脚注需要后处理时:去重 [^key] 引用,转换为 [N] 编号,并追加参考文献。

sn-prepare-citations(引用渲染)

处理 sn-deep-research 的 stitched.md:从 evidence.json 收集 sources[],将正文中的 [^source_id] 转换为 [N] 编号引用,插入 L0/TOC,并追加参考文献。

推荐用法(sn-deep-research v2)

bash
python3 scripts/prepare_citations.py \
  --report <report_dir>/stitched.md \
  --evidence <report_dir>/sub_reports/d1.evidence.json <report_dir>/sub_reports/d2.evidence.json \
  --outline <report_dir>/outline.json \
  --output <report_dir>/report.md

参数

参数说明
--report输入 markdown。sn-deep-research 中通常是 stitched.md
--evidence全部 d*.evidence.json,用于收集 source 元数据和修复 claim-id 泄漏
--outline可选但推荐。提供 L0、TOC 和标题结构信息
--output输出 markdown。sn-deep-research 中通常是 report.md
--no-l0关闭 L0 摘要层渲染
--no-toc关闭 TOC 渲染

处理逻辑

  1. 从所有 evidence.json 的 sources[] 收集引用元数据。
  2. 按 URL 归一化去重,同 URL source 合并为同一编号。
  3. 检测 [^dN.cM] claim-id 引用泄漏;能映射到 claim evidence 时替换为对应 source_id,不能映射则报告 unresolved。
  4. 扫描正文中的 [^source_id],按首次出现顺序分配编号。
  5. 替换 [^source_id] → [N],移除脚注定义行。
  6. 根据 outline 插入或校准 L0 / TOC。
  7. 追加 ## 参考文献。
  8. 写出 report.md 和同目录 citations.json。
  9. stdout 输出结构化 JSON,包含 orphan citations、claim-id leakage、TOC 和 L0 状态。

控制器处理要求

  • orphan_citations 非空:不要交付,回 writer/stitcher 修正引用或删除 unsupported 内容。
  • claim_id_leakage.unresolved 非空:不要交付,回 writer 修正 [^dN.cM]。
  • claim_id_leakage.resolved 非空但 unresolved 为空:可以继续,但记录为警告;writer 后续应直接输出 [^source_id]。

旧兼容模式

不传 --outline / --output 时,脚本会覆写 --report 指向的文件,仅做引用编号和参考文献追加。sn-deep-research 正常流程不使用该模式。

© OpenSenseNova, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/sn-prepare-citations of OpenSenseNova/SenseNova-Skills.

  • SKILL.md
  • scripts/prepare_citations.py

Open the folder on GitHubat commit 7838651

Compare with similar skills

Sn Prepare Citations next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sn Prepare Citations compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sn Prepare Citations this skillOpenSenseNova/SenseNova-Skills5.7k—~408Automated safety check: PassMIT
Deep Research WorkflowTokenRhythm/opensquilla7.1k—~1.3kAutomated safety check: PassApache-2.0
Academic Research Suite for CodexImbad0202/academic-research-skills-codex12k—~12kAutomated safety check: PassCustom licence
Deep Research Literature SurveyHKUSTDial/Supervisor-Skills8.7k—~2.4kAutomated safety check: PassCC-BY-NC-SA-4.0
Parallel WebLeonChaoX/qinyan-academic-skills9431 repos~2.9kAutomated safety check: NotesMIT
Live Researchbrightdata/skills264—~1.8kAutomated safety check: PassMIT

Similar skills

  • Deep Research Workflow

    TokenRhythm/opensquilla

    Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.

    7.1k GitHub stars~1.3k tokensUpdated today
    Research & ScienceAuto-check passed
  • Academic Research Suite for Codex

    Imbad0202/academic-research-skills-codex

    A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.

    12k GitHub stars~12k tokensUpdated 5 days ago
    Research & ScienceAuto-check passed
  • Deep Research Literature Survey

    HKUSTDial/Supervisor-Skills

    Runs a survey-grade literature investigation: fixes the research questions, searches from adversarial angles, verifies citations and writes an evidence-first report.

    8.7k GitHub stars~2.4k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Parallel Web

    LeonChaoX/qinyan-academic-skills

    Search the web, extract URL content, and run deep research using the Parallel Chat API and Extract API.

    943 GitHub starsUsed in 1 repo~2.9k tokens
    Research & ScienceAuto-check: notes
  • Live Research

    brightdata/skills

    Produce a deep, multi-source, cited research brief on a topic from live web data using Bright Data's Discover API (intent-ranked web search + parsed page content).

    264 GitHub stars~1.8k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Deep Research Methodology

    RightNow-AI/openfang

    Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

    18k GitHub stars~2.6k tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed

More from OpenSenseNova/SenseNova-Skills

All 36 skills in this repo
  • SN Motion HTML

    OpenSenseNova/SenseNova-Skills

    Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.

    5.7k GitHub stars~2.2k tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Fallback Tools

    OpenSenseNova/SenseNova-Skills

    Fallback scripts for web search, image search and download, and image generation that PPT skills use only when the host agent lacks or fails its own tools.

    5.7k GitHub stars~575 tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Workbench

    OpenSenseNova/SenseNova-Skills

    Opens the PPT Workbench web editor for an existing SenseNova HTML slide deck so you can preview, inspect and visually edit it without regenerating.

    5.7k GitHub stars~2.5k tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Creative Renderer

    OpenSenseNova/SenseNova-Skills

    Turns an approved slide outline into a full-page image for every slide, one 16:9 PNG per page, and optionally packages the set into a PPTX.

    5.7k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • SenseNova PPT Entry

    OpenSenseNova/SenseNova-Skills

    Entry point for SenseNova presentation generation: creates a task folder, picks depth, output format and design richness, and routes to the right PPT skill.

    5.7k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes
  • China Market Open Data Search

    OpenSenseNova/SenseNova-Skills

    Researches Chinese market, macro, trade, procurement, listed-company and regulatory information from free official sources that need no sign-up or API key.

    5.7k GitHub stars~954 tokensUpdated today
    Auto-check: notes

Questions about Sn Prepare Citations

What does Sn Prepare Citations do?

用于终稿完成且脚注需要后处理时:去重 [^key] 引用,转换为 [N] 编号,并追加参考文献. An agent skill from OpenSenseNova/SenseNova-Skills. Sn Prepare Citations is an agent skill from OpenSenseNova/SenseNova-Skills.

When should I use Sn Prepare Citations?

Sn Prepare Citations fits situations like: tasks that involve Citation management; tasks that involve Deep research.

How do I install Sn Prepare Citations in Claude Code?

Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-prepare-citations -a claude-code`. Or copy the skill folder (skills/sn-prepare-citations in OpenSenseNova/SenseNova-Skills) into .claude/skills/sn-prepare-citations in your project. Claude Code loads it when a task matches its description.

How do I install Sn Prepare Citations in Codex?

Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-prepare-citations -a codex`. Or copy the skill folder (skills/sn-prepare-citations in OpenSenseNova/SenseNova-Skills) into .agents/skills/sn-prepare-citations in your project. Codex loads it when a task matches its description.

Can I use Sn Prepare Citations in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-prepare-citations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sn-prepare-citations, .gemini/skills/sn-prepare-citations, .github/skills/sn-prepare-citations and .opencode/skills/sn-prepare-citations in your project.

What does Sn Prepare Citations need to run?

Going by SKILL.md and its folder, Sn Prepare Citations needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Sn Prepare Citations access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sn Prepare Citations safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sn Prepare Citations use?

Sn Prepare Citations is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sn Prepare Citations use?

About 408 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sn Prepare Citations?

Skills that share tags, products or a category with Sn Prepare Citations: Deep Research Workflow (TokenRhythm/opensquilla, 7.1k stars), Academic Research Suite for Codex (Imbad0202/academic-research-skills-codex, 12k stars), Deep Research Literature Survey (HKUSTDial/Supervisor-Skills, 8.7k stars) and Parallel Web (LeonChaoX/qinyan-academic-skills, 943 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sn Prepare Citations?

OpenSenseNova (a GitHub organization) maintains it in OpenSenseNova/SenseNova-Skills, which has 5,747 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 9, 2026.

Source: OpenSenseNova/SenseNova-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.