Grantproof
Surfaces common writing-style mistakes in federal R&D grant prose — NSF SBIR/STTR, DoD SBIR, NIH SBIR, DOE, DARPA, NASA, NOAA, and similar. For each mistake, identifies where the issue is, explains why reviewers downgrade it, and shows a sample rewrite structure the founder can apply. Use when the user pastes draft writing for an R&D grant pitch or proposal.
Install
npx skills add ellewangyuan/grantproof --skill grantproofgit clone --depth 1 https://github.com/ellewangyuan/grantproof.git /tmp/grantproof
mkdir -p ~/.claude/skills
cp -r /tmp/grantproof/. ~/.claude/skills/grantproofPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Grantproof *A Claude Skill that surfaces common writing-style mistakes in federal R&D grant prose. Created by Dr. Elle Yuan Wang — served as an NSF SBIR/STTR reviewer, XPRIZE judge, AI-ALOE Lead Scientist. Coached and supported $21M in collective R&D grant funding over 10 years across federal R&D grant programs.* *Grantproof enforces a more rigorous writing register that R&D grant reviewers reward. Writing register is one layer of why a proposal gets funded — it does not guarantee approval. Strong writing supports a strong project; it cannot substitute for one.* ## Your role You are Grantproof, a writing-style editor for prose intended for federal R&D grant proposals — NSF SBIR/STTR, DoD SBIR, NIH SBIR, DOE, DARPA, NASA, and similar. When a user pastes founder-style prose, you scan it against the **7-pattern catalog** defined in this skill's files. For each detection you output: 1. **Where** the problem is, **what pattern** it matches, and **why** reviewers downgrade it. 2. **A sample rewrite structure** — an abstract template the founder applies to their own content. You do **NOT** rewrite the founder's actual passage. You do **NOT** give advice on proposal content, document structure, research design, or strategy. Those live in the paid **NSF SBIR Pitch Playbook**, the first launch in the playbook series. ## The core insight
Details
- Skill name
grantproof- Repository
- ellewangyuan/grantproof
- License
- MIT
- Repo updated
- 23 June 2026
FAQ
What does the Grantproof skill do?
Surfaces common writing-style mistakes in federal R&D grant prose — NSF SBIR/STTR, DoD SBIR, NIH SBIR, DOE, DARPA, NASA, NOAA, and similar. For each mistake, identifies where the issue is, explains why reviewers downgrade it, and shows a sample rewrite structure the founder can apply. Use when the user pastes draft writing for an R&D grant pitch or proposal.
How do I install the Grantproof skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ellewangyuan/grantproof --skill grantproof. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Grantproof popular?
It lives in ellewangyuan/grantproof, which has 5 GitHub stars and 0 forks.
Related skills
Humanize Chinese Writing
5fy-agent/humanize-chinese-writing
中文文本与 HTML 内容的去 AI 味、人性化改写、素材型长文、页面信息密度检查与分析稿审阅。用于用户说“去AI味”“像人写的”“自然一点”“保留原意改写”，或要求减少黑话、套话、模板腔、讲义腔、机器感，按个人文风润色中文稿、长文、HTML 页面文案、仪表盘和分析报告。优先保留事实、观点、语气、引用、链接、数据口径与代码结构，不以规避检测器为目标。
Godot Plugin
5TomLeeLive/openclaw-godot-skill
Control Godot Editor via OpenClaw Godot Plugin. Use for Godot game development tasks including scene management, node manipulation, input simulation, debugging, and editor control. Can modify, save, and delete scenes/nodes and capture project metadata and screenshots — destructive operations should be confirmed with the user. Use only on explicit Godot Editor requests like inspecting scenes, creating nodes, taking screenshots, testing gameplay, or controlling the editor, in trusted local projects.
Machiavelli Digital Twin / 马基雅维利分身
5niflhum/machiavelli-skill
A conversational digital twin of Niccolò Machiavelli, distilled from his complete works. Delivers power analysis, strategic decision-making frameworks, and risk assessment with Machiavelli's signature style - based on how things actually are, not how they ought to be. / 以马基雅维利的思维方式、分析框架和表达风格,为用户提供局势分析、决策建议和风险评估。 Three modes: /machia (dialogue), /machia-a (analysis), /machia-w (writing), /machia-e (eastern). Not for: pure emotional venting, everyday trivia, technical questions.
Game Terminology Vietnamization
5dungnotnull/game-terminology-vietnamization-agent-skill
Vietnamization & Localization of Deep Game Terminology (No Misleading Translations) — A production-grade Game Localization & Specialized Terminology Translation analysis harness with evidence-backed outputs, quality gates, and continuous knowledge updates. Use this skill whenever the user asks about game terminology translation, game localization, Vietnamization of game terms, specialized terminology translation, localization quality assurance, or needs analysis of game terminology in Vietnamese/English contexts.
Mr Li Writer
5NocodeMrLi/mr-li-writer-skill
面向中文内容创作的编辑判断、研究、策划、写作与平台原生交付工作流。根据标题、素材、参考资料、核心想法或模糊灵感，先识别读者任务、材料条件和创新必要性，再按需完成语境扫描、可写性判断与方向校准，并区分发布平台与内容目标，进行事实检索、观点设计、平台原生正文写作、标题策划和对应交付。适用于公众号文章、知乎回答、小红书原生笔记、官网/网页、个人博客、行业解读、实用指南和基于素材的扩展研究写作。
Dd Sdd
5anatolii-iumashev/dd-sdd
Discovery–Delivery Spec-Driven Development — AI SDLC через спецификации. При запуске проверяет готовность проекта (AGENTS.md, docs/rfc/, docs/specs/, симлинки треков) и спрашивает, с какого трека начинать. Два скилла: dd-discovery (читает контекст проекта и docs/specs/, декомпозирует решение по MECE и пирамиде Минто, ставит задачу в RFC в docs/rfc/), dd-delivery (реализует по RFC с тестами, дописывает в RFC тест-инструкции, обновляет docs/specs/, уносит RFC в архив).
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.