84938 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

t3-dot-env-zod

T3 Env setup with Zod for Next.js 16+ and Vite. Use for implementing or debugging `@t3-oss/env-nextjs` or `@t3-oss/env-core` schemas, `experimental__runtimeEnv`, client/server separation, build-time validation, presets, and Zod env-safe coercions.

onnokh
onnokh
0

技能推荐引擎

智能技能推荐系统,根据用户场景自动推荐最合适的3个技能方案,并支持自动打包和GitHub托管

adcwangfeng
adcwangfeng
0

WhatsApp消息处理技能

专门处理WhatsApp多模块消息的接收和响应系统,支持文本、图片、文件等多种消息类型的处理

adcwangfeng
adcwangfeng
0

gsc-analyzer

Strategic analysis of Google Search Console data for startup founders and marketing leaders. Transforms GSC exports into actionable growth insights with revenue impact estimates, competitive positioning, and prioritized action plans. Use when a user provides a GSC zip/CSV for (1) Brand vs non-brand analysis with revenue implications, (2) SEO opportunities with business impact sizing, (3) Content gap analysis with funnel mapping, (4) Paid search strategy with budget allocation, or (5) Strategic summaries with prioritized recommendations.

coreyrab
coreyrab
0

progressive-disclosure

Use when designing interfaces with complex functionality, settings panels, or expert features. Covers layering information so beginners aren't overwhelmed and experts aren't held back.

bfmcneill
bfmcneill
0

agent-behavior

Use at the start of any coding session to establish activity tracking and working patterns. Defines how the agent should document its work and communicate progress.

bfmcneill
bfmcneill
0

psychology-foundations

Use when you need to understand WHY certain UX patterns work. Covers cognitive psychology, behavioral science, and neuroscience foundations that underpin satisfying experiences.

bfmcneill
bfmcneill
0

trust-and-recovery

Use when designing error handling, confirmation dialogs, undo functionality, or any interaction where user trust matters. Covers building confidence through predictability and graceful failure.

bfmcneill
bfmcneill
0

flow-optimization

Use when designing interactions, workflows, or interfaces where user focus matters. Covers protecting flow state, reducing interruptions, and creating immersive experiences.

bfmcneill
bfmcneill
0

uv-workflow

Use when creating Python projects, managing dependencies, or running Python scripts. Covers uv package manager commands, best practices, and common patterns for modern Python development.

bfmcneill
bfmcneill
0

sveltekit-builder

Use when building SvelteKit apps with Svelte 5. Covers runes, SSR, forms, and stack patterns (Kysely, Better Auth, shadcn-svelte).

rosa
rosa
0

versioning

Use when releasing, tagging, or bumping versions. Defines semver rules and keeps package.json/pyproject.toml synced with git tags.

bfmcneill
bfmcneill
0

feedback-design

Use when building loading states, progress indicators, success confirmations, or error messages. Covers feedback loops and patterns that feel satisfying.

bfmcneill
bfmcneill
0

design-patterns

Use when refactoring code or designing flexible systems. Covers creational, structural, and behavioral patterns with Python examples.

bfmcneill
bfmcneill
0

verification

This skill MUST be invoked before any completion claim, success report, or task transition. Mandates 5-step evidence protocol. Use when about to claim "done", "complete", "working", "fixed", or any success state.

baxtercooper
baxtercooper
0

context-gathering

Use when entering an unfamiliar codebase, starting a new feature, or before any implementation task. Provides structured exploration protocol to understand before acting.

baxtercooper
baxtercooper
0

error-recovery

Use when tasks fail due to transient errors. Provides structured retry strategies and graceful degradation patterns. Invoke on network errors, rate limits, or intermittent failures.

baxtercooper
baxtercooper
0

estimation

Use before committing to a task. Provides complexity analysis and scope assessment. Invoke when user asks "how complex" or before large features.

baxtercooper
baxtercooper
0

finishing

Use when all tasks are complete. Presents completion options and enforces test gate. Work is never left in limbo.

baxtercooper
baxtercooper
0

orchestration

This skill should be used when orchestrating complex tasks, decomposing work into atomic units, dispatching to subagents, verifying outputs, or when discussing task verification and deviation tracking patterns.

baxtercooper
baxtercooper
0

parallel-dispatch

Use when facing multiple tasks or failures. Provides decision framework for concurrent vs sequential execution. Invoke before dispatching multiple subagents.

baxtercooper
baxtercooper
0

writing-plans

Use when creating implementation plans. Mandates exact file paths, complete code samples, and expected output. No vague language allowed.

baxtercooper
baxtercooper
0

systematic-debugging

Invoke when debugging failures. MANDATORY when 3+ fix attempts have failed. Enforces root cause investigation before fixes.

baxtercooper
baxtercooper
0

tdd

Use for any code implementation task. Enforces RED-GREEN-REFACTOR cycle. "If you didn't watch it fail, you don't know if it tests the right thing."

baxtercooper
baxtercooper
0

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

crystal9114
crystal9114
0

skill-finder

Find and install the best skill for your current task. Use when the user wants to discover skills, asks "is there a skill for...", "find a skill for...", or "/skill-finder". Searches skills.sh in real-time and uses LLM reasoning to match skills to the user's context.

dangogit
dangogit
01

playstore-competitor-analysis

Research and analyze competitor apps on the Google Play Store. Extracts app metadata (title, description, rating, reviews, category, developer, version, price, installs) and downloads screenshots. Supports analyzing multiple competitor apps for comparison, or searching for top competitors by keyword. Use when user wants to analyze competitors, research Play Store listings, gather competitive intelligence, compare multiple apps, or find top apps in a category. Triggers on Play Store URLs (play.google.com), app package IDs, or requests like "analyze competitor", "research this app", "compare these apps", "top 10 messenger apps", "find competitors for X".

linakis
linakis
0

scientific-schematics

使用 Nano Banana Pro AI 创建可发表级别的科学示意图,并支持智能迭代优化。使用 Gemini 3 Pro 进行质量审查;仅当质量低于当前文档类型要求阈值时才会重新生成。专注于神经网络架构图、系统架构图、流程图、生物通路图以及复杂科学可视化图表。

victory-hugo
victory-hugo
0

clinvar-database

查询NCBI ClinVar变异临床意义数据库。按基因/位置搜索,解释致病性分类,通过E-utilities API或FTP访问,注释VCF文件,用于基因组医学。

victory-hugo
victory-hugo
0

scientific-visualization

用于生成可投稿级别图件的元技能。当需要创建期刊投稿图(如多面板布局、显著性标注、误差条、色盲友好配色,以及符合特定期刊格式要求,如 Nature、Science、Cell)时使用。该技能可统筹调用 matplotlib / seaborn / plotly 并应用投稿级绘图风格。若仅用于快速探索性分析,直接使用 seaborn 或 plotly 即可。

victory-hugo
victory-hugo
0

treatment-plans

以 LaTeX/PDF 格式生成简明(3–4 页)、聚焦且可执行的医学治疗计划,覆盖各临床专科。支持一般内外科治疗、康复治疗、心理健康照护、慢病管理、围手术期管理与疼痛管理。包含 SMART 目标框架、循证干预措施(以最少的文本引用呈现)、合规要求(HIPAA)以及专业排版。强调简洁与临床可操作性。

victory-hugo
victory-hugo
0

venue-templates

可访问主要科学出版与投稿场景的 LaTeX 模板、排版规范与提交指南,包括顶级期刊(Nature、Science、PLOS、IEEE、ACM)、学术会议(NeurIPS、ICML、CVPR、CHI)、科研海报,以及科研项目申请(NSF、NIH、DOE、DARPA)。当准备期刊投稿、会议论文、科研海报或基金申请,并需要特定会刊/期刊的格式要求与模板时,应使用此技能。

victory-hugo
victory-hugo
0

sci-result-interpretation

面向科研写作的结果解读技能。根据用户提供的图表、统计检验和模型输出,生成详细的 Methods and Materials、Results、Discussion 三章节双语内容(中文在前,英文在后),并提供完整性与风格检查。用于“解读图表统计结果”“补全详细方法学”“撰写结果与讨论”等场景。

victory-hugo
victory-hugo
0

xlsx

全面的电子表格创建、编辑与分析工具,支持公式、格式设置、数据分析和可视化。当需要处理电子表格(如 .xlsx、.xlsm、.csv、.tsv 等)时使用,包括:(1) 创建包含公式和格式的新电子表格,(2) 读取或分析数据,(3) 在保留公式的情况下修改现有电子表格,(4) 在电子表格中进行数据分析和可视化,或 (5) 重新计算公式。

victory-hugo
victory-hugo
0

code-visualization-palette

用于代码驱动的数据可视化配色约束。凡是生成、修改、审查或解释 Python、R 及其他绘图库的可视化代码或图形样式时都应使用本技能,并强制按照基于 color.md 整理的规则选择离散、连续单色或连续双色配色并生成所需数量的颜色。若用户已经手动指定新的颜色、新的色板或新的配色方案,则不使用本技能。

victory-hugo
victory-hugo
0

gotree-phylogenetic-tree

使用 Gotree 命令行对系统发育树进行读取、检查、重定根、修剪、重命名、格式转换、支持度与枝长处理、折叠、比较、绘图、距离矩阵导出、随机树生成与远程下载上传。适用于 Newick、NEXUS、PhyloXML、Nextstrain/Augur v2 树文件的批处理、管道式工作流和终端自动化;涉及多序列比对请改用 goalign,涉及 Python 树分析请按需使用 biopython 或 scikit-bio。

victory-hugo
victory-hugo
0

pipeline-coding-standard

编写或者修改代码至符合规范科研和数据处理的流水线(pipeline)。仅适用于科研、分析pipeline;不要用于普通单文件小工具、Web 前端、通用库开发或 Notebook 探索分析。

victory-hugo
victory-hugo
0

pipeline-job-splitting

将已有的粗粒度科研、分析或生物信息学管线拆分为多个细粒度单核 HPC 子任务。用于 bash/shell 主控流程需要按样本列表、区域列表、染色体列表或其他任务清单切分,并为每个子任务生成独立配置文件和调度脚本的场景。适用于 LSF 优先的 HPC 提交重构、细粒度任务提交、粗粒度任务拆解为多个单核子任务、high-throughput submission、job splitting 或 scatter 风格改造。默认保留原有分析逻辑,只重构任务切分、配置派生与手动作业提交层。

victory-hugo
victory-hugo
0

python-dual-mode

将既有或新编写的 Python 脚本重构为双模式模块,用于稳定、可维护的数据处理流。

victory-hugo
victory-hugo
0

python-plot-editable-fonts

在Python数据可视化输出中强制使用可编辑的矢量字体文本。凡是在创建或修改Python绘图代码时(matplotlib、seaborn、pandas绘图库),均应使用这一设置,以确保导出的PDF/PS/SVG图像保留可编辑文本状态,避免将字形转换为路径。

victory-hugo
victory-hugo
0

r-pheatmap-pairwise-matrix

使用pheatmap包生成R代码以进行配对矩阵可视化。当用户明确要求生成R的pheatmap热图,针对配对矩阵,并在输入矩阵以矩阵形式、tidylong表或tidywide数据框传输,以及可能添加行和列的样本-组别标注时,请使用此类代码。

victory-hugo
victory-hugo
0

r-style

编写、生成、修改、补充、优化 R 代码时使用此 skill。凡是用户请求涉及 R 语言脚本、R 分析代码、R 可视化代码、R 数据处理代码,或者用户说"用 R 写"、"R 代码"、"写个 R 脚本"时,必须遵循本 skill 的风格规范。

victory-hugo
victory-hugo
0

scientific-critical-thinking

评估研究严谨性。用于评估方法学、实验设计、统计学有效性、偏倚、混杂因素以及证据质量(如 GRADE、Cochrane 偏倚风险评估),以对科学结论进行批判性分析。

victory-hugo
victory-hugo
0

scholar-evaluation

应用 ScholarEval 框架对学术与科研成果进行系统化评估。该技能基于同行评审研究评价标准,提供结构化评估方法,可对学术论文、科研项目申请书、文献综述及各类学术写作在多个质量维度上进行全面分析。

victory-hugo
victory-hugo
0

research-lookup

通过 OpenRouter 调用 Perplexity 的 Sonar Pro Search 或 Sonar Reasoning Pro 模型来检索最新研究信息。可根据查询复杂度自动选择最合适的模型。用于搜索学术论文、最新研究进展、技术文档以及一般研究信息,并提供引用来源。

victory-hugo
victory-hugo
0

research-grants

撰写具有竞争力的科研项目申请书,适用于 NSF、NIH、DOE 和 DARPA。支持各机构特定格式、评审标准、预算编制、广泛影响(broader impacts)、研究意义陈述、创新性论述,以及符合提交规范的合规性要求。

victory-hugo
victory-hugo
0

pptx-posters

使用 HTML/CSS 创建科研海报,并可导出为 PDF 或 PPTX。仅当用户明确要求使用 PowerPoint/PPTX 海报格式时才使用此技能;标准科研海报应优先使用 latex-posters。本技能提供基于现代 Web 的海报设计,支持响应式布局和便捷的可视化整合。

victory-hugo
victory-hugo
0

peer-review

系统化同行评审工具包。用于评估方法学、统计分析、研究设计、可重复性、伦理合规、图像与图表完整性以及报告规范,适用于跨学科的论文和科研基金申请评审。

victory-hugo
victory-hugo
0

tidyplots-plot-builder

生成和修复基于 tidyplots 的 R 绘图工作流。用于用户要求使用 tidyplots 包进行绘图、改图、配色优化、统计标注、分面输出、导出 PDF/PNG、多图排版、报错排查(如找不到函数/包)等场景。输入可以是数据结构描述、列名、目标图形类型、风格约束或期刊图规范。

victory-hugo
victory-hugo
0

ensembl-database

查询Ensembl基因组数据库REST API,覆盖250多个物种。基因查找、序列检索、变异分析、比较基因组学、同源基因、VEP预测,用于基因组研究。

victory-hugo
victory-hugo
0

Page 1573 of 1699 · 84938 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.