Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,459 skills from 2,407 repositories · updated 31 minutes ago
10,658 skills
- AI科幻-设计故事设定lornshrimp/Lorn.NovelWriteSkills用于【AI科幻】题材下的故事设定、手法、系统逻辑链与数据痕载体设计。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充都市系统摩擦、异常数据与技术代价边界，并明确要求优先强制加载并使用 `通用-设计故事设定`。关键词：AI科幻故事设定、系统逻辑链、数据痕载体、规则代价。OtherNo warnings★ 249↓ —
- 都市悬疑-撰写书评lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的全书 / 分部 / 分卷 / 分章书评撰写、重写与审计。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名、补充城市现实压迫、异常证据与人性代价的推荐话术，并明确要求优先强制加载并使用 `通用-撰写书评`。支持今日头条平台。OtherNo warnings★ 249↓ —
- 通用-输出新浪微博版lornshrimp/Lorn.NovelWriteSkills用于把小说章节改写为更适合新浪微博语境的版本。适合强调短促抓点、传播性、话题切口、即时情绪与高压缩阅读体验的正文输出；当前先承接已存在题材，后续可供更多题材复用。关键词：输出新浪微博版、微博、话题传播、短促抓点。OtherNo warnings★ 249↓ —
- 通用-审阅总大纲lornshrimp/Lorn.NovelWriteSkills用于审阅总大纲、全书总纲与战略层文件组。适合检查总纲包对象是否完整、M0 / X / C 体系是否稳固、四阶段机制递进是否成立、单元案矩阵是否持续供血主线，并输出可回写的总纲审阅报告。关键词：审总纲、全书总纲审阅、M0、X线、C线、总纲报告。OtherNo warnings★ 249↓ —
- AI科幻-创建小说正文lornshrimp/Lorn.NovelWriteSkills一个面向长篇网文 / 小说创作工作流的 AI 写作资产库。它不是“随手堆提示词”的仓库，而是一套围绕 题材设计 → 大纲搭建 → 章节创作 → 审阅润色 → 多平台改写 → 质量门禁 → 分发落盘 搭起来的可复用写作系统。OtherNo warnings★ 249↓ —
- AI科幻-审阅总大纲lornshrimp/Lorn.NovelWriteSkills审阅AI科幻小说总大纲、全书总纲、故事多面体、主线谜团与单元案矩阵。这里的“总大纲”默认指总纲层文件组，而非单一文件；至少包括 `小说总大纲.md`、`故事面/`、`伏笔与回收总纲.md`、`故事多面体大纲.md`，以及其它相关总表级大纲文件。用于审阅总纲层 Canon 文件及其联动关系。关键词：总纲审阅、总大纲、全书审阅、机制递进、单元案矩阵、总纲报告。OtherNo warnings★ 249↓ —
- 通用-执行对话冲突lornshrimp/Lorn.NovelWriteSkills用于设计、重写或强化对话冲突。适合把角色对话写成立场碰撞、潜台词拉扯、信息释放与情绪升级并存的有效场景。关键词：对话冲突、盘问、谈判、争执、潜台词、关系升级。OtherNo warnings★ 249↓ —
- 异能志怪-设计故事面lornshrimp/Lorn.NovelWriteSkills用于【异能志怪】题材下的故事面设计、重写与审计。作为题材包装层、兼容入口与路由层，负责保留异能志怪入口名、补充都市异术超能的题材边界，并明确要求优先强制加载并使用 `通用-设计故事面`。OtherNo warnings★ 249↓ —
- 女频爱情-输出知乎版lornshrimp/Lorn.NovelWriteSkills用于【女频爱情】题材下的知乎平台输出任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与平台节奏边界，并明确要求优先强制加载并使用 `通用-输出知乎版`。保情绪闭环、逻辑清晰、讨论感与当场反击的追读驱动，不洗成观点短文。OtherNo warnings★ 249↓ —
- 异能志怪-审阅总大纲lornshrimp/Lorn.NovelWriteSkillsUse when: 审阅总大纲、全书大纲、战略层大纲、主线谜团M0、重要支线X01-XNN、单元案矩阵C01-CNN、跨卷规划、里程碑锚点、系列连贯性、机制递进、终局闭环、总纲审阅报告。常见说法：审总纲、看全书结构、检查主线、看战略层、看终局闭环、看长线规划、总纲诊断、总纲体检。关键词：审阅总大纲、全书总纲、战略层审阅、主线谜团、单元案矩阵、跨卷规划、系列连贯性。OtherNo warnings★ 249↓ —
- AI科幻-正文润色lornshrimp/Lorn.NovelWriteSkills用于【AI科幻】题材下的正文润色。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充有限视角、数据链、系统阻力与数字压迫感裁判边界，并明确要求优先强制加载并使用 `通用-正文润色`。关键词：AI科幻正文润色、有限视角、数据链、系统阻力、代入感。OtherNo warnings★ 249↓ —
- 通用-强化章末钩子lornshrimp/Lorn.NovelWriteSkills用于强化章节结尾的章末钩子。适合章末抢救、结尾补针、翻页感增强、下一章驱动增强与最后 150–300 字局部强化。关键词：强化章末钩子、结尾没翻页感、只修结尾、下一章驱动、最后一句、章末补针。OtherNo warnings★ 249↓ —
- pytdcBioTender-max/awesome-bio-agent-skillsTherapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.OtherNo warnings★ 215↓ —
- tu-youyou-perspectiveBioTender-max/awesome-bio-agent-skills诺贝尔医学奖得主屠呦呦（Tu Youyou, 2015）的思维框架蒸馏。 核心镜片：从传统智慧中提取科学灵感的"古今转化"思维；低温突破决策。 警告：信息密度低（公开演讲/访谈极少），心智模型基于有限素材推断，诚实边界篇幅大。 触发词：「屠呦呦视角」「青蒿素思维」「古今转化」「传统中药现代化」。OtherNo warnings★ 215↓ —
- gwas-prsBioTender-max/awesome-bio-agent-skillsCalculate polygenic risk scores from DTC genetic data using the PGS CatalogOtherNo warnings★ 215↓ —
- graphql-query-optimizerproflead/codex-skills-libraryOptimize GraphQL queries and resolvers for performance. Use when a mid-level developer needs to reduce N+1 or payload size.OtherNo warnings★ 167↓ —
- atac-seqBioTender-max/awesome-bio-agent-skillsATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.OtherNo warnings★ 215↓ —
- OpenST Skills IndexBioTender-max/awesome-bio-agent-skillsSkills for Open-ST spatial transcriptomics data processing, from raw BCL files to spatially-resolved single-cell h5ad objects.OtherNo warnings★ 215↓ —
- ibgnnBioTender-max/awesome-bio-agent-skillsUse this model doc whenever the user wants to run IBGNN (Interpretable Brain Graph Neural Network) for fMRI phenotype prediction. IBGNN is a PyG-based GNN with a learnable MLP message function over [x_i, x_j, edge_attr], designed for connectome-based brain disorder analysis with post-hoc edge-mask explainer support.OtherNo warnings★ 215↓ —
- DevExpress/DEXT Componentsdelphicleancode/delphi-spec-kitStandards for using DevExpress (DEXT) components in Delphi VCL applicationsOtherNo warnings★ 57↓ —
- Delphi SOLID Patternsdelphicleancode/delphi-spec-kitSOLID implementation patterns for Delphi projects — Repository, Service, Factory, Strategy with constructor injection and interfacesOtherNo warnings★ 57↓ —
- word-statshumanizerai/agent-skillsGet word count, character count, reading time, and text statistics. Quick analysis without questions.OtherNo warnings★ 54↓ —
- Horse Frameworkdelphicleancode/delphi-spec-kitPatterns for developing REST APIs with Horse framework in DelphiOtherNo warnings★ 57↓ —
- lggnnBioTender-max/awesome-bio-agent-skillsUse this model doc whenever the user wants to run LG-GNN (Local-to-Global GNN) for fMRI phenotype prediction. LG-GNN is a PyG-based GNN with SABP (Self-Attention Brain Pooling) and mutual-information regularization. NeuroClaw adapts the original population-graph version to single-subject brain graphs.OtherNo warnings★ 215↓ —
Horse Framework
delphicleancode/delphi-spec-kit
OtherUpdated Mar 25, 2026
From the author
Patterns for developing REST APIs with Horse framework in Delphi
Install
npx skills add delphicleancode/delphi-spec-kit --skill 'Horse Framework' -a claude-code
Installs to .claude/skills/Horse-Framework/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 74
Security100
Provenance61
Maintenance50
Licence100
Adoption31
Files (1)
- SKILL.md