Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert-level skill for AI Actions and integrations on Freshworks Platform 3.0. Use when (1) Creating actions.json and SMI functions (flat request, nested response), (2) Request templates and third-party API integration, (3) Pre-build validation (pricing, paywalls, account prerequisites), (4) Failure-case validation and test data guardrails, (5) Debugging broken endpoints, (6) Integration implementation checklist (auth, base URL, request body, trigger-friendly schema), (7) Scoping and planning new integrations (and comparing only when user asks).
Audit Go module dependencies: detect outdated packages, check for known vulnerabilities, review go.mod hygiene, identify unused or redundant deps, and evaluate dependency quality. Use when auditing dependencies, checking for CVEs, cleaning up go.mod, upgrading modules, or evaluating third-party packages. Trigger examples: "check dependencies", "audit deps", "go.mod review", "update modules", "vulnerability scan", "govulncheck". Do NOT use for code-level security issues (use go-security-audit) or architecture review (use go-architecture-review).
Google Guava best-practice patterns distilled from the official wiki, covering the of/copyOf/builder patterns for immutable collections and defensive copy rules, deciding between LoadingCache, Cache and Caffeine, immutable Joiner/Splitter pipelines, CharMatcher instead of regex, Preconditions with formatted messages, and CaseFormat name conversion. Corrects common LLM misuse: hand-rolled immutable collections, ConcurrentHashMap instead of Cache, unawareness of CharMatcher.
Audits a website codebase and makes code changes so AI engines (ChatGPT, Claude, Perplexity, Google AI Overviews) can better discover, parse, quote, and cite the site. Covers structured data, content structure, technical signals, and freshness.
End-to-end Jira bug-fix workflow (stages 0-10), driven by a single Jira link, from intake through PR/MR merge and Jira writeback. Manual mode (default) pauses for confirmation between stages; auto/force modes run end-to-end; ai-proxy overlay (thin freeze then occupy) is available independently. Triggers — 「修复这个 bug [URL]」「帮我修复 [URL]」「jira-fix [URL]」「自动修复 [URL]」「强制修复 [URL]」「继续修复」「从上次继续」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / fix this bug, jira-fix, auto fix, force fix, resume fix, ai-proxy mode, switch to ai-proxy. Do NOT use for batch fixes across multiple issues — use jira-fix-queue instead (it enqueues into goal-driven-queue; confirm, then run the queue).
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
Use when creating or developing Laravel features, before writing code or implementation plans - refines rough ideas into fully-formed Laravel designs through collaborative questioning, alternative exploration, and incremental validation.
Upgrade Laravel applications one major version at a time (9→10, 10→11, 11→12). Use when user wants to upgrade their Laravel framework version. Auto-detects current version from composer.json, identifies breaking changes, and applies necessary code fixes.
Complete Love2D game development from prototype to polished release. Covers core architecture, graphics, animation, tiles, collision, audio, and iOS deployment. Use when building Love2D games, implementing game mechanics, or deploying to mobile platforms.
Architects and orchestrates Model Context Protocol (MCP) ecosystems including server development, tool design, and transport configuration. Use when building MCP servers, designing agentic tool interfaces, configuring MCP transports, implementing OAuth security, or troubleshooting MCP connectivity. Use for outcome-oriented tools, Zod validation, progressive disclosure resources, elicitation, and async tasks.
Fix the errors reported by MegaLinter. Use after megalinter-check found errors, or when the user pastes MegaLinter/CI lint errors and wants them fixed. Applies safe fixes automatically (auto-fix linters first, then guided manual fixes using per-linter fix guides), asks the user when fixing is ambiguous, and can disable rules or linters with user confirmation. Never pushes to the default branch.
Create or revise Mermaid diagrams that render inside Markdown, README files, GitHub, GitLab, wikis, and documentation sites. Use when the user explicitly requests Mermaid or needs a Markdown-native flowchart, sequence diagram, state diagram, class diagram, ER diagram, journey, Gantt chart, mind map, timeline, or lightweight architecture diagram. Prefer PlantUML for strict UML/C4 deliverables and ProcessOn only when editable hosted output is requested.
Use when the user says 'migrate visual composer to gutenberg', 'convert vc to blocks', or 'move visual composer pages to the block editor'. Parses the Visual Composer data, maps elements to core blocks, and creates draft duplicates for review.
nuqs (type-safe URL query state) best practices for Next.js applications. This skill should be used when writing, reviewing, or refactoring code that uses nuqs for URL state management. Triggers on tasks involving useQueryState, useQueryStates, search params, URL state, query parameters, nuqs parsers, or Next.js routing with state.
Diagnose and fix measured startup, rendering, scrolling, memory, media, or network regressions in Expo React Native apps. Use for a reproducible performance problem or an explicit performance audit, not speculative library swaps or blanket memoisation.
Analyze performance issues based on reproducible baselines and profiler evidence. Use when the user asks to locate slow endpoints, slow tasks, slow queries, memory or network bottlenecks, formulate optimization plans, or verify optimization gains; distinguish measured conclusions from static inference, do not fabricate durations or improvement ratios, and require explicit authorization for production operations.
Internal step of plan-feature: from an already-designed SPEC (product half `designed`), fill the **engineering half** and generate the planning artifact set scaled to the feature's size (XS/S → SPEC-only with ≥ 2 phases in the SPEC, last = Hardening & PR; M/L → full set with a hardening phase), freeze one compact ACCEPTANCE.md for every size, and register the roadmap entry. Docs only — never code.
Universal meta-skill that bootstraps ANY software project regardless of programming language. Auto-generates 15-30+ hyper-detailed, project-specific coding skills BEFORE writing code. Language-agnostic: works with TypeScript, Python, Go, Rust, Java, C#, Swift, Kotlin, PHP, Ruby, and polyglot projects. AGGRESSIVE version enforcement: EVERY technology version MUST be verified via real-time lookup — never use memorized versions. Generates skills for architecture, security, performance, privacy, testing, error handling, accessibility, observability, data modeling, API design, DevOps. Each skill enforces zero-bug standards with concrete code examples, anti-patterns, and measurable budgets. Triggers on: "bootstrap", "new project", "start project", "create project", "set up", "generate skills" — use BEFORE any code exists.
Use when you have already determined the scope of Discover (P0/P1/P2) and now need to quickly establish the Level-0 north star (memory) and the Level-1 map-layer index skeleton (components/products) of `.aisdlc/project/`, so that evidence can later be filled in module by module without double-writing or drift.
Use when you are about to start Discover on an existing project but are still unclear about which entry points can serve as evidence (run/test/ci/contract/ops) and which modules to tackle first (P0/P1/P2), and you worry that the scope will spiral out of control and become unmaintainable.
Use when a Meta Quest app is built with Meta Spatial SDK in Kotlin: lane fit, toolchain, ECS, panels as Android views, hybrid apps. NOT for native OpenXR (quest-native), Unity, WebXR (quest-webxr), or profiling (quest-perf). Opt out: no xr, без xr. Triggers: “Spatial SDK” / “Спатиал SDK,” “MRUK”.
Use when the XR experience runs in the Meta Quest Browser: WebXR with IWSDK, three.js, or A-Frame, Bubblewrap PWA, Horizon Billing. NOT for native OpenXR (quest-native), APK submission (quest-store), or flat three.js (web3d-dev). Opt out: no xr, без xr. Triggers: “WebXR,” “three.js на Quest”.
Help with RAP business events and enterprise eventing including event definitions in behavior definitions, raising events from RAP handler methods, event bindings, SAP Event Mesh integration, event consumption, and event-driven architecture patterns in ABAP Cloud. Use when users ask about RAP business events, enterprise events, event mesh, eventing, raising events, event binding, event definition, event consumption, event-driven, asynchronous processing, event topics, or publish-subscribe in ABAP. Triggers include "RAP event", "business event", "raise event", "event mesh", "event binding", "enterprise eventing", "event-driven", "publish event", "consume event", or "asynchronous event".
Review code against the canonical architecture quality Rule set, including boundaries, dependency direction, cohesion, cycles, contract stability, coupling, composition, change surface, unreachable code and deprecation discipline. Cognitive-only atomic skill; output is a findings list.
Send an email to a mailing list via the SchemaVaults mail-server `/api/send` route, using either the `sendEmailToMailingList()` helper or the `schemavaults-send-email send-to-mailing-list` CLI from `@schemavaults/send-email`. Use when any server-side TypeScript/JavaScript code needs to send a notification to a mailing list audience — **or when Claude Code itself wants to send a one-shot notification at the end of a task** (preferred — invoke the CLI via `bunx schemavaults-send-email send-to-mailing-list …`; fallback — write a short script to `/tmp/` and run it with `bun`).
Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures, latency or throughput regressions, queue growth, timeouts, distributed stalls, crash dumps, wrong outputs after deploys, or PD/EP/HiCache issues, and the job is to turn the problem into a replay plus the right next debug tool.
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.