原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

spark-to-paper-skills Skill

代码仓库 ↗

作者:Spark-To-Paper-Skills★ 1,215 (整个仓库)14 个 skill

★ 星标是整个仓库的,不是每个 Skill 的

选择要安装的 Skill

能做什么

此仓库是合集,包含 14 个 Skill

  • 连接方式 供 AI 读取的指令文件,其中有调用外部服务的步骤
  • 账号或密钥 有些步骤需要 OPENROUTER_API_KEY, TS_FIG_API_KEY, OpenAI, Hugging Face, OVERLEAF_TOKEN, TS_EMBED_API_KEY 的密钥(依据 README)
  • 分类 数据与研究
作者的原始说明
One sentence in, one draft paper out: spark-to-paper-skills automatically reviews papers, plans and runs experiments, and writes a research draft—typically using about $10 in API costs per paper.
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/spark-to-paper-skills-spark-to-paper-skills.svg)](https://mcp.popnx.com/en/skills/spark-to-paper-skills-spark-to-paper-skills)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

Firebase MCP

Gives AI development tools Firebase-specific capabilities and expertise.

作者:firebase广泛使用↓ 490.6万/周★ 4489 整个仓库的星标12个月前更新

MCP · 连接服务在你的电脑上运行✓ 品牌同名 GitHub · github.com/firebase

Supabase

MCP server for interacting with the Supabase platform

作者:supabase广泛使用↓ 24.6万/周★ 3021 整个仓库的星标昨天更新

MCP · 连接服务电脑或云端✓ 服务方 · supabase.com

Dbx

Query databases from AI agents using connections configured in DBX.

作者:t8y2广泛使用↓ 9446/周★ 3.1万7个月前更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
spark-to-paper-skills
timesfmShadowbrokergoogle-maps-scrapertradingview-mcp
作者Spark-To-Paper-Skillsgoogle-researchBigBodyCobaingosomatilaahmettaner
Skill 数141111
GitHub 星标1,21535,65111,6108,2785,317
最近代码更新2026年8月22日2026年11月13日2026年11月20日2026年11月15日2026年11月21日
许可证MITApache-2.0AGPL-3.0MITMIT

Spark-To-Paper-Skills 提供的 14 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

选择要安装的 Skill

只安装你真正会用的。点开名称查看该 Skill 的安装方法

安装整套(14 个)

如果想要全部,可以让 AI 一次装好。安装前请先了解 2 点

  • 每个已安装 Skill 的说明都会载入每次对话。装得越多,AI 越容易选错 Skill
  • 有些 Skill 与 AI 自带的工具功能重复。只安装真正会用的更好
安装到哪里
请帮我从 https://github.com/spark-to-paper-skills/spark-to-paper-skills 安装全部 14 个 Skill:ts-figure-optimize, ts-figure-svg, ts-idea2story, ts-kg-build, ts-paper, ts-paper-cite, ts-paper-data, ts-paper-experiment, ts-paper-figure, ts-paper-latex, ts-paper-plan, ts-paper-refine, ts-paper-review, ts-paper-write,供我所有项目使用,每个放在 ~/.claude/skills/<Skill 名称>(Codex 用 ~/.agents/skills/<Skill 名称>,Cursor 用 ~/.cursor/skills/<Skill 名称>)。各 Skill 在仓库中的文件夹:ts-figure-optimize = skills/ts-figure-optimize · ts-figure-svg = skills/ts-figure-svg · ts-idea2story = skills/ts-idea2story · ts-kg-build = skills/ts-kg-build · ts-paper = skills/ts-paper · ts-paper-cite = skills/ts-paper-cite · ts-paper-data = skills/ts-paper-data · ts-paper-experiment = skills/ts-paper-experiment · ts-paper-figure = skills/ts-paper-figure · ts-paper-latex = skills/ts-paper-latex · ts-paper-plan = skills/ts-paper-plan · ts-paper-refine = skills/ts-paper-refine · ts-paper-review = skills/ts-paper-review · ts-paper-write = skills/ts-paper-write。请先让我看所有文件,告诉我是否有脚本或会修改电脑设置,再告诉我每个 Skill 安装的完整路径,等我同意后再安装。
请帮我从 https://github.com/spark-to-paper-skills/spark-to-paper-skills 安装全部 14 个 Skill:ts-figure-optimize, ts-figure-svg, ts-idea2story, ts-kg-build, ts-paper, ts-paper-cite, ts-paper-data, ts-paper-experiment, ts-paper-figure, ts-paper-latex, ts-paper-plan, ts-paper-refine, ts-paper-review, ts-paper-write,装到这个对话当前打开的项目里(放在 .claude/skills/<Skill 名称>;Codex 用 .agents/skills/<Skill 名称>,Cursor 用 .cursor/skills/<Skill 名称>)。各 Skill 在仓库中的文件夹:ts-figure-optimize = skills/ts-figure-optimize · ts-figure-svg = skills/ts-figure-svg · ts-idea2story = skills/ts-idea2story · ts-kg-build = skills/ts-kg-build · ts-paper = skills/ts-paper · ts-paper-cite = skills/ts-paper-cite · ts-paper-data = skills/ts-paper-data · ts-paper-experiment = skills/ts-paper-experiment · ts-paper-figure = skills/ts-paper-figure · ts-paper-latex = skills/ts-paper-latex · ts-paper-plan = skills/ts-paper-plan · ts-paper-refine = skills/ts-paper-refine · ts-paper-review = skills/ts-paper-review · ts-paper-write = skills/ts-paper-write。请先让我看所有文件,告诉我是否有脚本或会修改电脑设置,再告诉我项目名称和每个 Skill 安装的完整路径,等我同意后再安装。

上传到 Claude 网页版和应用:需要上传 14 次,每个 Skill 一个 ZIP 文件。打开下方列表中的各个 Skill 即可下载

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • ts-figure-optimize

    The suite's SOLE figure vectorizer: turn ONE raster scientific figure (a PNG/JPG, e.g. a gpt-image-2 schematic) into an editable, publication-ready figure via DrawAI's **key-free HYBRID** — local perception (SAM3 region detection + PaddleOCR + Box-IR layout, no account) then a deterministic hybrid…

  • ts-figure-svg

    PaperBanana+ — turn a paper's figure brief into a native, editable, publication-grade SVG. Stage 1 runs the OFFICIAL PaperBanana (dwzhu-pku/PaperBanana, pulled by `setup_paperbanana.py`, its own Retriever→Planner→Stylist→Visualizer→Critic pipeline) to produce candidate PNGs. Stage 2 is the "+": Cla…

  • ts-idea2story

    Turn a raw research idea into a compelling, well-grounded research STORY (an 8-field structured proposal) ready to feed the ts-paper pipeline. Claude does almost everything natively — idea packaging, recall reasoning over a knowledge graph, agentic external literature search (WebSearch/WebFetch), s…

  • ts-kg-build

    Build a reusable research-PATTERN knowledge graph from a paper corpus, so ts-idea2story can recall prior problem→solution→story patterns. Claude does the reasoning (story-first pattern extraction, cluster naming + summaries); small scripts do the irreducible math (embeddings via a USER-SUPPLIED end…

  • ts-paper

    Generate a complete, publication-format journal/conference paper (LaTeX → compiled PDF) from whatever the user drops — a one-line idea, a proposal, or a proposal WITH real results. It ROUTES the input (idea→idea2story; proposal→proposal mode; results-present→data-aware mode), then runs plan→cite→wr…

  • ts-paper-cite

    Stage 2 of the ts-paper suite. Build a complete, REAL refs.bib for a Traitement du Signal paper — using the user's provided references first and Claude's native WebSearch/WebFetch only for genuine gaps. Every entry must have full metadata (authors, year, venue, vol(issue):pages, DOI); never a title…

  • ts-paper-data

    DATA-AWARE mode for the ts-paper suite. Activated by the orchestrator's router ONLY when the input ships REAL measured results (results_mode == "data_aware"); the proposal/no-numbers path is unchanged. Claude reads the user's data in ANY form (CSV / JSON / a pasted table / numbers in prose), judges…

  • ts-paper-experiment

    Repair an AI-generated scientific paper draft by diagnosing research logic, completing feasible experiments, rewriting the experiment section, and updating the full manuscript for claim-evidence consistency.

  • ts-paper-figure

    Stage 6 of the ts-paper suite. Fill a Traitement du Signal paper's figure placeholders with real diagrams. Claude DESIGNS a concrete, rich figure and GROUNDS it on a real on-topic top/mid-journal MAIN figure (Claude **WebSearches** for it, then `fetch_reference_figures.py` pulls that paper's MAIN f…

  • ts-paper-latex

    Stage 7 (final assemble + compile) of the ts-paper suite. Assemble drafted LaTeX section bodies + refs.bib + blueprint into a compilable paper in the active TEMPLATE and compile it to PDF. Copies the template's .sty/.cls + assets, runs the deterministic template-driven post-processes (caption posit…

  • ts-paper-plan

    Stage 1 of the ts-paper suite. Turn a research proposal into a single structured blueprint.json (title, ≤6 keywords, exactly 3 contributions, notation table, terminology glossary, experiment design, and per-section plans with word targets) for a Traitement du Signal proposal paper. Use when plannin…

  • ts-paper-refine

    Stage 4 of the ts-paper suite. One holistic pass that right-sizes each drafted section toward Traitement du Signal JOURNAL length (not conference page-compression), enforces cross-section coherence and terminology consistency, removes redundancy, and preserves all citations, equations, and markers.…

  • ts-paper-review

    Adversarial peer-review HARDENING pass for a ts-paper draft — the thing a forward-only drafter/refiner can't do: argue the other side of the paper's claims. Distilled from PaperJury into a lean Claude-native engine: N isolated domain reviewers read the whole paper (verbatim-quote anti-skim) → merge…

  • ts-paper-write

    Stage 3 of the ts-paper suite. Draft every section of a Traitement du Signal paper as LaTeX body files (sections/ .tex + abstract.tex) from the blueprint and refs.bib, following strict per-section recipes, the no-fabricated-results rule, and IIETA citation style. Write ALL sections in one pass. Use…

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude Code

依据开发者 README 和 repo 中的文件夹

安装

请先选择 Skill

此仓库有 14 个 Skill。请从上方列表选一个,该 Skill 的页面有完整安装方法,包括让 AI 安装和 ZIP 文件

让 AI 帮你安装
上传到 claude.ai

前往 Skill 列表 ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
1,215
星标是整个仓库的,不是每个 Skill 的
开发者
Spark-To-Paper-Skills
许可证
MIT
最近代码更新
2026年8月22日
repo 中的 SKILL.md 文件(含译本和模板)
14