Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Comprehensive expertise for working with Microsoft's GenAIScript framework - a JavaScript/TypeScript-based system for building automatable LLM prompts and AI workflows. Use when creating, debugging, or optimizing GenAIScript scripts, implementing prompts-as-code, working with tools and agents, processing files (PDF, CSV, DOCX), defining schemas, or building AI automation workflows.
Build and audit WordPress layouts with GenerateBlocks V2, including CSS Mode, responsive at-rules, dynamic data, Pro components, and recovery-safe block serialization. Use for new GB layouts, conversions, repairs, and hand-authored block markup.
Git workflow management with atomic commit principles. Capabilities: commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits. Actions: commit, push, pull, merge, rebase, branch, stage, stash git operations. Keywords: git commit, git push, git pull, git merge, git rebase, git branch, git stash, atomic commit, commit message, conventional commits, branching strategy, GitFlow, trunk-based, PR, pull request, code review, git history, cherry-pick, squash, amend, interactive rebase, staged changes. Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes.
GitHub Actions workflow patterns for React Native iOS simulator and Android emulator cloud builds with downloadable artifacts. Use when setting up CI build pipelines or downloading GitHub Actions artifacts via gh CLI and GitHub API.
Automates GitHub repository setup: 12 production-tested GitHub Actions workflow templates (React/Vite, Node matrix testing, Python, Cloudflare Workers deploy, basic CI), 4 YAML issue and pull request templates, Dependabot config, CodeQL security scanning, branch protection, and CODEOWNERS. Prevents 18 documented errors in workflow YAML syntax and indentation, action version pinning, runner versions, issue template structure, Dependabot PR limits, and CodeQL permissions such as security-events: write. Use when bootstrapping a new repo, adding CI/CD pipelines, creating issue or PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers from GitHub Actions, or fixing GitHub Actions workflow YAML syntax errors.
Godot 4.x game development (verified on 4.7) - scaffold, inspect and edit projects, scenes, UI, resources headlessly; author tilesets, ASCII-painted levels, themes, animation, audio buses, custom Resources, collision/navmesh bakes, shaders, export presets; draw pixel art from ASCII, clean generated art, synthesize sound effects and looping music; look up the installed engine's exact API; lint GDScript, scenes and shaders without Godot (Godot 3 renames, un-inferable :=, dead node paths, input actions, res:// paths); catch editor-only node warnings; move files safely; unit-test, smoke-run every scene with input fuzzing, debug, export; verify it all as text (node trees, UI layout, 2D/3D placement, level, image, audio read-backs), no vision or hearing needed. Use when Codex needs to build or fix a Godot game, write or repair .gd/.tscn/.tres/.gdshader files, add art, sound, levels or UI, migrate Godot 3 code, reorganize a project, or validate, test and export.
Use when debugging GPC errors, failures, or unexpected behavior. Make sure to use this skill whenever the user mentions gpc error, gpc failing, exit code, AUTH_FAILED, API_FORBIDDEN, NETWORK_ERROR, CONFIG_MISSING, EDIT_CONFLICT, upload failed, permission denied, timeout, rate limit, gpc doctor failing, unexpected exit code, command not working, GPC crash, debug GPC, verbose output, --json error, threshold breach, REPORT_ACCESS_DENIED, REPORT_BUCKET_NOT_FOUND, reports bucket access, bulk reports permission denied, API_DECLARATION_REQUIRED, App content declaration, foreground service declaration, API_ALREADY_EXISTS, API_ENDPOINT_RETIRED, ORDER_REVIEW_REFUND_INVALID, PLUGIN_PERMISSIONS_REQUIRED, PLUGIN_IDENTITY_MISMATCH, CONFIRMATION_REQUIRED, IMAGE_SYNC_DIR_UNREADABLE, THRESHOLD_NO_DATA, THRESHOLD_INVALID, TRAIN_GATE_NO_DATA, API_METRIC_GAMES_ONLY, INVALID_PACKAGE_NAME — even if they don't explicitly say 'troubleshoot.' Also trigger when someone encounters any GPC error they don't understand, when gpc doctor reports issues, when CI pipelines fail with GPC commands, or when they need to interpret exit codes. For auth-specific setup issues, see gpc-setup. For CI-specific issues, see gpc-ci-integration.
Scandit ID Capture (`IdCapture`) in Cordova / PhoneGap projects (`scandit-cordova-datacapture-id`) — scanning passports, driver's licenses, ID cards, residence permits, visas via MRZ, VIZ, barcode, or mobile documents. Use for integration, accepted-document and scanner configuration, captured-field result handling, anonymization, add-on capabilities (voided-ID detection, European driving-license back decoding, AAMVA barcode verification), and SDK version migration.
Build cross-language backends with the iii engine. Register functions in TypeScript, Python, or Rust callable from any connected service via WebSocket. Covers iii-sdk, state, KV Server, streams, triggers (HTTP/cron/queue/log), Bridge Client mesh, OpenTelemetry, Docker deployment, iii Console, and Prometheus metrics. Use when: setting up iii engine, cross-language function calls, iii-sdk integration, registerTrigger configuration, KV Server storage, queue/log triggers, Docker deploy, or debugging "ECONNREFUSED 49134", "type_not_found", "@iii-dev/sdk 404".
Frontend UI design, critique, audit, polish. Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Jacky Shen's Agile Coach AI assistant, providing structured prompt support for Scrum Masters and Product Owners. This skill MUST be activated whenever the user mentions any of the following Scrum, Sprint, Backlog, user stories, DoD, DoR Definition of Ready, Product Owner, Scrum Master, agile ceremonies, retrospectives, backlog refinement, sprint planning, release planning, risk identification, user personas, customer churn, product requirements, decision-making, scenario modeling, team facilitation, or any agile team workflow. Keywords are Scrum, Sprint, Backlog, user story, Product Owner, Scrum Master, DoR, agile, iteration, retrospective, prioritization, risk, persona, churn, PRD, facilitation, minimal experiment, root cause, pattern recognition. Whenever a user mentions agile team work, PO/SM scenarios, or needs structured agile prompt templates, this skill must be used.
Full lifecycle management of the JeecgBoot form designer (desform) — create, update, copy and delete form designs through conversation, manage form data (CRUD), generate PC/mobile form views, and create OA approval apps in one click (form + workflow + authorization). Use this skill whenever the user's intent involves the "form designer", including but not limited to: creating or generating a form ("做一个请假表单", "AI设计表单", "desform"), modifying an existing form or fields ("加个字段", "改一下表单"), copying/deleting a form, entering or querying form data, creating form views (including mobile), and asking about designer capabilities (control types, dictionary configuration, validation rules, related records, sub-tables, formula calculation, JS/CSS enhancements, default values, external links, etc.). It should also trigger when the user wants to create an OA app with an approval workflow ("创建OA应用", "创建审批单", "创建报销单", "创建请假单", "做一个OA表单带流程", "一键创建表单和流程", "面试申请", "出差申请", etc.). Even if the user only describes field requirements (such as "需要姓名、手机号字段") without explicitly saying "form", it should trigger as long as the context points to the form designer. Note: this skill only handles the form designer (desform), not Online forms — if the user explicitly mentions "Online表单" or "online表", use the jeecg-onlform skill.
Diagnose and tune JetBrains IDE VM options against the IDE's actual boot runtime, including bundled or custom JetBrains Runtime (JBR) 17, 21, and 25. Use whenever a user asks about JetBrains IDE performance, freezes, startup or indexing speed, memory pressure, garbage collection, heap sizing, `.vmoptions`, or IntelliJ IDEA, WebStorm, PyCharm, GoLand, Rider, CLion, PhpStorm, RubyMine, or DataGrip JVM tuning. Distinguish the IDE process from project JDK, Gradle, build, test, and remote-backend processes; propose evidence-based minimal changes, confirm effective flags after restart, and provide rollback and before/after measurement steps.
General-purpose coding-agent discipline based on Andrej Karpathy's observations about LLM coding pitfalls, requiring clarification, success criteria, simplicity, surgical edits, verification, and self-review for software engineering tasks.
Linear ticket lifecycle for any project. Use when starting work on a Linear issue, ending work on an issue, or asking what to work on next. Triggers include, start KAT-N, pick up, implement, finish, complete, done with, close, what's next, next ticket, next issue. Handles blocker validation, status transitions, context loading, branch creation, evidence gating, and chain promotion.
Document and refresh a software repository in an OKF knowledge bundle. Use when the user asks to document this repo, codebase, architecture, developer workflows, or operational behavior; create repository knowledge; or bring existing repository documentation up to date after code changes. Treats the repository as live, read-only evidence rather than source material to copy or retire.
Use this skill when designing, reviewing, or generating responsive CSS. Apply it whenever the user asks about breakpoints, media queries, container queries, fluid sizing, viewport or container units, or needs to validate responsive component behavior, even if they do not explicitly mention responsive design.
Laravel best practices and architecture patterns for building production-ready applications. Use when writing, reviewing, or refactoring Laravel code to ensure proper patterns for service providers, dependency injection, security, Eloquent, and performance.
Guides building sandbox-first Lattice SDK integrations without assuming a language or protocol up front. Use when the user wants to build, modify, or review a Lattice integration: publishing entities/tracks, connecting a sensor or telemetry source, building a taskable agent, watching or consuming entities, uploading media/objects, or bridging an external system into Lattice. Classifies the integration, recommends REST or gRPC when underspecified, defaults to environment-token auth, enforces live sandbox verification, and explains Entities/Tasks/Objects afterward
Teach programming and computer concepts while a coding agent builds, explains, or resumes a real software project; use for new project requests, existing or unfinished project walkthroughs, and questions expressing confusion or learning intent.
Discover project conventions and surface security concerns. Use when starting work in a new or unfamiliar project, when asked to "learn the codebase", "check project rules", "what are the conventions", "onboard to this project", or "anything shady in this codebase". Scans agent config files (.claude/, .cursor/, CLAUDE.md, etc.) and runs a security/smell sweep for hardcoded secrets, insecure patterns, suspicious dependencies, and dangerous configurations.
AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。学习者想创建、发现、调用、保护、评估、打包或迁移 Agent Skills 时，开始或续学此路线。每次调用教学一课，并将证据记录在 AGENT-SKILLS-LEARNING.md。Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills.
Maintain classic ASP.NET applications on .NET Framework, including Web Forms, older MVC, and legacy hosting patterns, while planning realistic modernization boundaries. USE FOR: working in Web Forms, legacy MVC, or classic ASP.NET applications; reviewing old IIS-centric configuration and lifecycle behavior; planning migration toward ASP.NET Core. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Light 科研主线 stage 6: turn the frozen question/estimand, experiment matrix, pre-registration, and data lineage into minimal runnable, test-first, leakage-free, reproducible experiment code that can be handed off to result-analysis. Use to implement or reproduce training/preprocessing/evaluation; design gold/property/metamorphic tests; control Python/NumPy/framework/CUDA/DataLoader randomness; review train/test or CV fit leakage; record config/code/environment/input hashes, stdout/stderr, raw metrics, patient/entity predictions, and failure artifacts; and run the stage-6 checkpoint. Data leakage or irreproducibility is critical; static scanning and two runs with the same seed do not prove absolute reproducibility across hardware.
Proven methodology for building and tracking features, projects, and issues in Linear. Use when the user wants to set up Linear tracking, sync or audit a board, run a Linear health check, finish install after skills add, or keep session discipline honest. Routes to linear-setup / linear-sync / linear-monitor / linear-finish-install as needed; linear-discipline is always-on.
Design and implement Litestar routing with app/router/controller composition, handler decorators, path and parameter modeling, route indexing/reverse lookups, ASGI mounting, and layered route metadata. Use when creating or refactoring endpoint topology and URL contracts. Do not use for purely internal service logic unrelated to HTTP route structure.
(NS) Consolidate delivered version deltas into living domain specs under docs/specs/ — INDEX.md and per-domain markdown. Use after version delivery when requirements, code-review-report, and execution-handoff exist — typically at version closure. Updates specs incrementally; never overwrite unrelated content. Do NOT run before code review approval.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.