AI Skills Hub - Browse 180,000+ Agent Skills

Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs. Use when needing to understand how a library works internally, debug dependency issues, or explore package implementations.

Four-phase debugging framework with root cause tracing - understand the source before proposing fixes. Use when investigating bugs, errors, unexpected behavior, or failed tests.

Control Tuya devices via local Home Assistant (tuya-local) or Tuya Cloud using the tuya-hub Go CLI.

Fixes import statement ordering and organization issues. Use when encountering import-x/order errors or when imports are disorganized. Auto-fixable with ESLint.

Best practices for bundling scripts in skills including error handling, constants documentation, and execution patterns. Use when creating script-enabled skills.

Essential graph algorithms including DFS, BFS, Dijkstra shortest path, and Union-Find with production-ready implementations.

On-demand MCP server access via CLI without adding to settings.json. Use when exploring MCP server capabilities before installing, making one-off calls, testing MCP servers during development, or avoiding context pollution from rarely-used servers.

Control interactive CLI tools that require a real terminal via tmux send-keys. Use for git rebase -i, git add -p, vim, nano, Python/Node REPLs, or any command that hangs waiting for terminal input.

Create native Claude Code hooks in ~/.claude/hooks/. Use when adding event-triggered automation (PreToolUse, PostToolUse, Stop, etc.).

Create slash commands for user-initiated workflows. Use when building repeatable /name commands for Claude Code.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Deploy containerized web applications to any Linux server using Kamal. Use when users need to deploy, configure, debug, or manage Kamal deployments including initial setup, configuration of deploy.yml, deployment workflows, rollbacks, managing accessories (databases, Redis), troubleshooting deployment issues, or understanding Kamal commands and best practices.

Synchronizes documentation (README.md, CHANGELOG.md, API docs) with implementation. Preserves user content outside speckit markers. Updates are non-destructive and clearly delineated. Always run after /speckit.implement completes.

ProjectTypeKeeper is a type context management tool. It scans and organizes TypeScript interfaces, classes, enums, and backend entity definitions in the project to form an updatable type graph. When generating code or developing features, it provides accurate related types to ensure consistent naming and structure, reducing duplicate types and context gaps.

Behavior-preserving code cleanup and compaction with strict verification gates. Only runs when the repo has a runnable build/test command set. Refactors safely, removes dead code, reduces duplication, and hardens scripts without introducing breakage or violating guardrails.

Comprehensive, standardized error response system for PHP REST APIs with SweetAlert2 integration. Use when building REST APIs that need consistent error formatting, specific error message extraction from database exceptions, validation error handling, and seamless frontend integration. Includes PDOException parsing, business rule extraction, and complete SweetAlert2 error display patterns.

Run tests, linting, and validation to verify changes work correctly. Use after implementation to check acceptance criteria, run test suites, and ensure nothing is broken.

Final reporting phase for the orrery workflow. Outputs structured JSON summarizing execution results, test outcomes, and status. Use after orrery-verify completes or when reporting blocked status.

Write or modify code according to a plan step. Handle implementation.

Validates OpenCode configuration files for correctness and best practices

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Query the Read the Docs Search API to find documentation across projects and repositories. Use when searching documentation, finding related docs, finding API documentation, or gathering information about projects on Read the Docs.

Triage Read the Docs build failures using build logs and config context. Use when a build fails, logs need analysis, or you need fix recommendations.

Verify BibTeX references for academic papers. Checks citation accuracy against Crossref and OpenAlex databases using the RefCheck_ai algorithm. Use when the user wants to check references, verify citations, validate a .bib file, or find potential citation errors.

Render and preview Markdown files in browser with GitHub-flavored formatting and syntax highlighting

Render and preview Mermaid diagrams in browser with support for flowcharts, sequence diagrams, class diagrams, and more

Expert knowledge for developing, building, and debugging Substreams projects on any blockchain. Use when working with substreams.yaml manifests, Rust modules, protobuf schemas, or blockchain data processing.

File-based integration patterns for Windows on-premise. UNC paths, network shares, file watchers, encoding handling.

This skill should be used when implementing, debugging, or discussing the Gamma Markets e-commerce specification - an extension of NIP-99 for decentralized Nostr marketplaces. Provides comprehensive knowledge of event kinds (30402 products, 30405 collections, 30406 shipping), order communication flow via NIP-17 encrypted DMs, payment processing modes, and merchant preference handling. (project)

根据用户任务和画像，将任务拆解为步骤并生成子技能。使用场景：(1) 指挥官创建新任务时调用，(2) 用户请求任务拆解时使用，(3) 复杂任务需要分解时使用。

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Workbenches agents to investigate and fix independent problems concurrently

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Guide for creating and implementing plugins to extend OpenCode functionality, including hooks, custom tools, and event handling

Guide for using tmux to manage detached sessions for long-running processes, including lifecycle management, cleanup, startup, verification, and output capture

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Go 1.22+ enhanced HTTP routing with method matching and wildcards

DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Culturabuilder to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Manage passwords and credentials via Bitwarden CLI (bw). Use for storing, retrieving, creating, or updating logins, credit cards, secure notes, and identities. Trigger when automating authentication, filling payment forms, or managing secrets programmatically.

Salesforce administration using Salesforce CLI (sf/sfdx). Use when working with Salesforce metadata, custom objects, fields, users, profiles, permission sets, Flows, automation, or data management. Triggers on tasks involving sf/sfdx commands, Salesforce Setup configuration, metadata deployment, user security administration, or Salesforce data operations.

Find a git branch by Linear ticket ID prefix (e.g., STU-15)

Run Jest tests in the Commons monorepo. Use when testing code changes, validating implementations, debugging test failures, or when the user mentions running tests.

Parse Robot Framework output.xml results into JSON summaries, detailed suite/test breakdowns, tag and criticality stats, execution errors, failed test messages, keyword-level errors, and timing. Use when asked to read/merge output.xml, compute pass/fail counts, tag stats, criticality, error messages, elapsed time, slowest tests/keywords, or combine/merge multiple outputs via rebot.

Explain Robot Framework keywords and their arguments from library/resource/suite documentation. Use when asked how to use a keyword, what arguments it takes, or to retrieve detailed keyword docs from libdoc across one or more libraries/resources.

灰色预测模型是一种针对小样本、贫信息系统的预测方法，适用于数据量少、信息不足但具有一定趋势的预测场景，如经济预测、产量预测等。

用于检验时间序列数据是否服从正态分布的工具，提供多种统计检验方法（Shapiro-Wilk、Kolmogorov-Smirnov、Jarque-Bera）及可视化（Q-Q图），帮助判断数据是否满足正态性假设，为后续统计分析提供依据。

用于检验两个分类变量之间是否存在统计独立性的假设检验方法，通过卡方检验实现，可应用于如性别与消费偏好、地区与疾病发病率等场景的相关性分析。

Complete AI-powered Excalidraw diagram generation system with 23+ chart types, arrow optimization algorithm, JSON repair utilities, and comprehensive prompt engineering. Includes production-ready scripts (optimizeArrows.js, json-repair.js), detailed documentation, and implementation guides. Use for generating professional diagrams from text/images, building diagram generation features, or converting natural language to visual representations.

使用 beautiful-mermaid 项目将 Mermaid 图表渲染为 ASCII 艺术。提供解析、布局算法和渲染操作的完整实现指南，支持流程图、状态图、序列图、类图和 ER 图表。当 Claude 需要理解 beautiful-mermaid 的 ASCII 渲染系统或在项目中使用 ASCII 渲染功能时使用。

Permanently delete persona files from storage

AI驱动的网页标注工具，支持高亮元素和添加文字批注。智能防重复、自动滚动、碰撞检测。兼容 GitHub 等严格 CSP 网站。适用场景：(1) 标记网页元素进行讲解 (2) 添加文字批注和注释 (3) 代码审查和设计评审 (4) 教学演示和用户引导 (5) Bug 报告和问题标记

根据接口 URL 自动查找文档并生成 TypeScript 接口函数代码

Keep Ideaverse vaults healthy through audits, diagnostics, and maintenance workflows. Use when running vault diagnostics, detecting link rot, identifying orphan notes, finding MOC bloat, suggesting archival candidates, validating frontmatter, or generating vault health reports. Triggers on requests like "audit my vault", "find broken links", "check vault health", "what needs archiving", "find orphan notes", or "run maintenance".

Expert guidance for vibe-validate, an LLM-optimized validation orchestration tool. Use when working with vibe-validate commands, configuration, pre-commit workflows, or validation orchestration in TypeScript projects.

Comprehensive Akash Network skill for deployers, providers, and node operators. Covers SDL generation, CLI deployments, Console API, TypeScript/Go SDKs, provider setup, and validator operations. Use for "deploy to Akash", "generate SDL", "Akash provider", "Akash CLI", "Akash SDK", or "Akash validator".

Generate skills from documentation websites. Use when asked to create skills from docs, convert documentation to agent skills, or crawl a docs site.

Test linked service connections — handles IR detection, managed IR activation, and supports testing single, multiple, or all linked services by name or type

AI 开发架构师 - 帮助建立和维护项目规范，规则是长出来的，不是设计出来的

Build complex agent and intelligent system services with Agently (Model control + TriggerFlow).

Streaming outputs, runtime streams, and ReAct-style tool loops.

This skill should be used when users need to infer chromatin states from histone modification ChIP-seq data using chromHMM. It provides workflows for chromatin state segmentation, model training, state annotation.

Supabase edge function supabase/functions/lifecyclemodel_hybrid_search that builds hybrid search queries for lifecycle models and calls `hybrid_search_lifecyclemodels`. Use when tuning prompts, embeddings, or auth/env for lifecycle model retrieval.

Supabase edge function supabase/functions/flow_hybrid_search that converts flow descriptions into hybrid search queries and calls `hybrid_search_flows`. Use when debugging flow search, tuning prompts/filters, or adjusting embedding endpoints/auth.

Supabase edge function supabase/functions/process_hybrid_search that converts process descriptions into hybrid search queries and calls `hybrid_search_processes`. Use when debugging process search, tuning prompts/filters, or adjusting embedding endpoints/auth.

执行包含高级分析与机身几何的固定翼总体设计流程。用户要求首次方案就含高级分析、几何约束与机身外形时调用。

执行固定翼外形详细设计的产物生成（翼型/机身剖面/三视图HTML/创成式搜索/OpenVSP脚本）。用户要一键产出外形资产并验证时调用。

Use when generating PRISMA flowcharts and synthesis for systematic literature review. TRIGGERS: slr export, synthesize, PRISMA, generate report, synthesis, generate report, export review

Skills for querying the KBase/BERDL Datalake via the MCP REST API. Use this when users want to explore KBase databases, list tables, get schemas, sample data, or run SQL queries against the KBase data lake. Triggers on mentions of KBase, BERDL, or requests to query biological/microbiome data stored in KBase.

Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.

Java performance optimization for low-latency systems. Use when analyzing JMH benchmarks, optimizing hot paths, implementing lock-free algorithms, tuning JVM flags, or working with concurrent data structures. Triggers on performance issues, benchmark analysis, VarHandle/UNSAFE usage, memory barriers, false sharing, MPSC queues, or JCTools patterns.

Use when reviewing code quality, before refactoring, when complexity increases, when code feels "hard to change", during code review, or when onboarding to unfamiliar code - systematic identification of code smells with specific refactoring recipes

Use when building multi-day features, avoiding long-lived branches, features taking >1 day, changes touching multiple systems, or high-risk changes needing gradual rollout - break features into deployable increments that each provide value

Use when performing 3+ similar operations like file edits, searches, or git operations. Triggers on repetitive tasks, "do the same for", loop-like patterns. Enables parallel tool calls and batch-editor delegation.

Housekeeping guide for background process tools. You SHOULD load this skill before launching background processes to avoid stale processes, port conflicts, and buffer issues. Examples: - user: "Start the dev server" → load skill, then launch with proper cleanup practices - user: "Run npm run dev" → load skill to verify startup and use meaningful IDs - user: "What background processes have we launched?" → check for duplicate processes, port conflicts

Control vehicle with natural language. Use when user wants to warm up/cool down the car, lock/unlock doors, start/stop engine, check battery/fuel/location/status, or control charging. Translates phrases like "warm up the car" into mcs CLI commands.

Extracts PDF/DOCX resumes to structured YAML format. Use when the user has a resume file to convert, mentions importing an existing resume, or starts a resume workflow with a document.

Converts resume YAML to professionally formatted PDF using Typst templates. Use when the user wants to generate a PDF, compile their resume, compare template layouts, or create print-ready documents.

Manages resume projects and versions. Use first when the user starts resume work to initialize projects, import files, create versions before changes, or switch between resume variants for different roles.

Creates custom Typst resume templates tailored to specific content and page requirements. Use when the content doesn't fit built-in templates, the user needs custom styling, or content overflows the target page count.

Expert assistant for the Okyline schema language. Okyline enables JSON data validation by example, where constraints are expressed inline on field names. Use when creating, editing, or converting JSON Schema, Avro, or other schema formats to Okyline, or when answering questions about Okyline syntax and features. This skill should be triggered whenever the user mentions Okyline, references .oky files, or asks about example-driven JSON schema validation.

Run multiple linters (eslint, oxlint, tsc, biome) in parallel with unified JSON output. Use when linting code, checking for errors before commits, or debugging lint failures. Triggers on "lint", "check code", "run linters", or after editing JS/TS files.

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Observability, Security, Task Discovery) and five maturity levels. Use when users request `/readiness-report` or want to assess agent readiness, codebase maturity, or identify gaps preventing effective AI-assisted development.

Create, search, and update Notion pages/databases using the Notion API. Use for documenting work, generating runbooks, and automating knowledge base updates.

Deploy and manage applications on Vercel, including preview deployments and deployment protection. Use when working with Vercel-hosted projects or configuring Vercel deployments.

Execute custom scripts and logic within Flow Designer and IntegrationHub workflows. Covers FlowAPI methods, flow execution, and subprocess orchestration. Use when building workflow automations, executing flows programmatically from server scripts, or triggering subflows conditionally.

Perform date arithmetic, time calculations, and schedule management using server-side APIs. Covers GlideDateTime, GlideDate, GlideDuration, and scheduling operations. Use when handling date calculations, working with timezones, managing scheduled tasks, or implementing time-based business logic.

Implement browser-side client scripts with GlideAjax patterns, UI Policies, and g_form APIs. Covers performance optimization, preventing browser blocking, and safe DOM access. Use for OnChange/OnLoad/OnSubmit scripts, UI Policies, and client-side field validation.

Establish secure outbound integration connections using REST, SOAP, and HTTP protocols. Covers RESTMessageV2, OAuth token management, request signing, and response parsing. Use when integrating with external systems, implementing API clients, consuming REST/SOAP services, or managing OAuth authentication.

General server-side operations including system interactions, user session management, event queuing, and utility functions. Covers GlideSystem (gs) methods, logging, system properties, and background job coordination. Use for system-level tasks, user context operations, event publishing, or when performing administrative functions not specific to data manipulation, flows, or security.

Manipulate form fields, sections, and user interactions using GlideForm. Covers field updates, validation, visibility control, and form state management. Use for client-side form customization, OnChange/OnLoad scripts, field validation, and dynamic UI behavior.

Deploy ServiceNow configuration changes safely using Update Sets with proper naming, parent/child batching, and preview validation. Use when managing releases, migrating between instances, or orchestrating complex deployments with multiple Update Sets.

Query, insert, update, and delete records in the ServiceNow database with emphasis on performance and security. Covers GlideRecord, GlideQuery, GlideAggregate, and secure data access patterns. Use when working with database records, aggregating data, or implementing data-driven logic.

Participate in Council multi-agent collaboration sessions. Use when asked to join a council session, collaborate with other agents, or when given a council session ID to participate in.