Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Volcengine Function Service: Use when users want to deploy a local frontend, Node.js or Python app, static site, or API service; create a serverless app from a template; connect an existing project to veFaaS; view its online URL; configure production environment variables, build or start commands, or ports; publish, roll back, invoke, or debug online functions; inspect logs, instance status, or resource configuration; pull or push cloud function code; create and manage sandbox instances; troubleshoot deployment or authentication failures, framework detection errors, missing gateways, and similar issues; call the veFaaS OpenAPI directly for advanced operations; get started with veFaaS and learn its concepts, capabilities, selection, or pricing; consult the official documentation in a terminal; or develop code using the veFaaS SDK or OpenAPI.
Use the vibestart CLI to create a TypeScript project, choose a stack or recipe, add capabilities such as Knip, Ultracite, or Docker, diagnose project state, or upgrade templates while preserving business edits, including resolving conflicts and porting template changes to starter source. Use when the user mentions vibestart, asks to maintain a project with a vibestart.jsonc, or needs help with these CLI workflows. Not for ordinary application feature development unrelated to the CLI.
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
Create beautiful, self-contained HTML visualizations from any content or idea. Use for: slide decks, presentations, infographics, dashboards, flowcharts, diagrams, timelines, comparison tables, data visualizations, landing pages, one-pagers, org charts, mind maps, process flows, kanban boards, report summaries, or any visual that helps humans digest information faster. Trigger on requests like "visualize this," "make a deck," "create a slide," "build an infographic," "show me a dashboard," "make this visual," or any request to present information in a visual HTML format.
Use Terraform/IaC for Volcengine resources only when the user explicitly chooses Terraform/IaC, already has a Terraform workflow/state, or confirms they need plan/diff/drift/destroy safety for VKE, managed databases/cache/storage, load balancers, domains/certificates, logging/monitoring, or team-managed infrastructure.
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR description for a Git staging-check) so you can catch up on what changed and what's proven to work before merging. Saves to tasks/walkthrough-[feature].md by default. Triggers on: /walkthrough, walkthrough, Phase 2 walkthrough, 生成 walkthrough, 生成走查文档, write the walkthrough.
All online operations must be handled through this skill, including searching, web scraping, post-login actions, and online interactions. Use when the user asks to search for information, view web content, visit a site that requires login, interact with a web interface, scrape social media content (Xiaohongshu, Weibo, Twitter, etc.), read dynamically rendered pages, or perform any online task requiring a real browser environment.
Health-check the wiki: scan all pages for broken wikilinks, orphaned pages, stale index entries, missing connections, em-dash violations, orphaned assets, and schema errors. Produces a dated lint report. Always use this skill when the user says /wiki-lint, mentions broken links, dead wikilinks, orphaned pages, 'what's broken in my wiki', 'are my links working', 'which pages have no connections', or asks for a wiki health check. Also use when the user notices a link that doesn't resolve, suspects the index is out of date, or asks whether the wiki is in good shape - even if they don't say 'lint'. Never auto-fixes anything; reports only. When in doubt whether a wiki health check is being requested, use this skill. Requires filesystem read access and write access to archive/.
A hand-drawn wireframe exploration — graph-paper background, marker / pencil tone, multiple tab labels for variants, sticky-note annotations, scribbled chart placeholders, hatched fills. Reads like a designer's whiteboard before any pixels are committed. Use when the brief asks for "wireframe", "sketch wireframe", "hand-drawn", "lo-fi", "whiteboard", "草稿", or "手绘原型".
WordPress accessibility review for themes, blocks, plugins, and admin interfaces. Use when reviewing keyboard navigation, focus behavior, semantic HTML, ARIA usage, form labeling, screen-reader support, contrast-related implementation issues, or when user mentions "accessibility review", "a11y", "keyboard navigation", "focus management", "screen reader", "ARIA", "semantic HTML", "accessible form", or "accessible block". Detects implementation-level accessibility issues in frontend output, block markup, admin screens, and interactive UI behavior.
Control Xiaomi/Mi Home smart speakers with playback/pause, volume adjustment, track switching, TTS voice announcements and more. Use this skill when the user needs to control Xiao Ai speakers, set timed reminders, or announce messages by voice. Supports smart device name matching (such as "Xiao Ai", "living room speaker") without remembering complex device IDs.
The main entry point for Ye Tong's local fitness membership business skills. Use when the user says “installed,” “show all skills,” “open the menu,” “how to use,” or “update Ye Tong skills,” or asks for Xiaohongshu content, daily trending topics, new-course WeChat Moments promotion, or performance management. Verify installation and the status of the three capability categories, then match the registered module. Supports in-package updates; does not teach peer coaches client acquisition or present unreleased capabilities as available
Create Xiaohongshu covers in Yetong’s original live-action style for fitness coaches serving local, in-person members. Use when there is a specific topic or draft and a cover, prompt, numbered composition selection, further refinement, or direct generation is needed. After reading the user’s activated DNA, follow the original step-by-step, one-question-at-a-time process, with five fixed compositions, a 3:4 aspect ratio, oversized text at the top and bottom, and a white, warm orange-yellow visual style. Not for broad topic ideation, changing only the posting title, or reviewing an entire draft.
Assess a fitness coach’s Xiaohongshu topic or existing draft aimed at potential local, in-person members. Use when the user has a specific topic or draft and wants to check whether it appeals to local members, seems credible, has a clear title and opening, sounds like them, and what to improve next. Does not generate topics, write an entire draft, or review platform compliance.
Use the local fitness coach’s activated DNA to find real trending topics on Douyin and credible public websites, selecting three topics per run that suit their target members. Use when the user asks for scheduled topic ideas based on their DNA, daily trending topics, or a one-time trial run. Can create scheduled tasks using the host’s native capabilities. Does not handle arbitrary task scheduling, full copywriting, automated publishing, or helping other coaches attract customers.
Create or revise titles for a fitness coach’s established topic for local members or an existing Xiaohongshu draft. Use when the user has a specific question, working title, or draft and wants to compare title angles and choose a title for publication. Read the user’s activated personal DNA and check the local audience, real evidence, and whether the draft delivers on its promise. Does not generate topics from broad directions or write an entire draft.
Generate Xiaohongshu topics that attract local, in-person members for fitness coaches. Use when the user asks “What should I post today?”, has only a broad direction such as weight loss, or wants topics generated and filtered in batches. Read the user's activated personal DNA, local inquiry pain points, and eight topic elements, and label the four content types. Does not write full copy or teach peer coaches client acquisition
Comprehensive backlink analysis using DataForSEO API. Analyze backlink profiles, find link building opportunities, detect toxic links, compare with competitors, and identify link gaps. Use when user says "backlinks", "link building", "referring domains", "link profile", "toxic links", "link gap", "competitor links", or "domain authority".
Core guide to the Yandex KIT e-commerce API (kit.yandex.ru store builder): authentication, base URL, rate limits, error contract, pagination and offline spec search/validation scripts. Use when a task involves the Yandex KIT API and no domain skill (catalog, orders, promotions, store, webhooks) clearly fits, or when you need auth, limits or error-handling basics. Russian triggers include: «что умеет API Яндекс КИТ», «найди операцию в API», «какой лимит запросов», «почему ошибка LIMIT_EXCEEDED», «как авторизоваться в Ките».
Put the MCP servers an existing agent uses behind one Redis Iris Context Gateway with redis-iris, so the agent connects to one MCP endpoint with one agent key instead of configuring each server and its secret. Asks whether the Gateway is in Redis Cloud or self-managed, then five questions (which MCP servers and secrets the agent has today, how many tools it sees, which read-only tools may be cached, which tools return large results, whether the framework speaks MCP itself). Self-managed, it provisions the Gateway and its Upstreams from the terminal with `iris context-gateway` and sets cache and compression policies. In Redis Cloud the developer creates them in the console. Then it points the agent at the Gateway in any framework and verifies it with `tools list` and `tools call`. Use when the agent configures several MCP servers one by one, carries one secret per server, loads too many tool schemas into the prompt, or the user asks for Context Gateway, one MCP endpoint, tool caching, or result handles.
Add Redis Iris Lens tracing to an existing AI agent through redis-iris, so every agent turn is one trace in the Lens UI with its LLM calls, tokens, tool calls, memory and document retrievals, and which of them entered the prompt. Detects how the agent runs (LangGraph or ADK attach, workflows.turn, another framework, or a plain loop), installs redis-iris[llm-tracing], calls lens.init(agent_id=...), opens one lens.turn() per turn where Iris does not open it already, and covers coexistence with an OpenTelemetry setup or LLM instrumentation the app already has. Use when the user asks to add Lens, tracing, observability, or per-turn traces to their agent, or asks why their Lens traces are missing.
End-to-end ticket implementation with a multi-agent team using TDD. Retrieves JIRA ticket details and Figma designs, spawns a PO to write requirements, gets developer approval, then proposes a test plan for review. Once tests are approved, implements tests first (red), then production code to pass them (green). Use --no-jira to skip JIRA retrieval and use inline instructions instead. Use --headless for fully autonomous execution where a reviewer agent replaces human approval.
Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks whether a change breaks the public API or needs tests, samples or docs, or asks what is wrong with the current diff. Required for changes to public APIs, core architecture (Runner, Workflow, BaseNode), new features and major refactors. Don't use for a single style nit (use adk-style), for diagnosing a failing test or a misbehaving agent at runtime (use adk-debug), or for wording a commit message or PR description (use adk-git).
Download and transcribe videos from YouTube, Bilibili, TikTok and 1000+ platforms. Use when user requests video download, transcription (转录/字幕提取), or converting video to text/markdown. Supports quality selection, audio extraction, playlist downloads, cookie-based authentication, and AI-powered transcription via SiliconFlow API (免费转录).
Use this skill whenever a user wants to execute operations against Algolia indices or accounts — deleting records, copying/migrating indices, backing up data, importing/exporting records, managing API keys, editing synonyms, configuring rules, changing settings like facets, clearing indices, or automating Algolia in CI/CD pipelines. The key signal is that the user wants to act on their Algolia data or configuration (server-side / backend / admin operations), regardless of whether they mention "CLI" or "command line." If someone names a specific Algolia index and wants to change, move, query, or manage it, use this skill. Do NOT use for frontend search UI work (InstantSearch, React components, autocomplete widgets), Algolia dashboard GUI questions, or evaluating Algolia vs. other providers.
Alibaba Cloud OpenAPI troubleshooting skill. Use this skill when the user needs to diagnose API call failures using Request ID, error codes, or error messages — via Aliyun CLI `openapiexplorer` plugin commands. Triggers: "RequestId 排查", "Request ID 诊断", "错误码解决方案", "API 调用失败", "get-request-log", "get-own-request-log", "get-error-code-solutions", "OpenAPI 故障排查", "API troubleshoot", "diagnose OpenAPI", "diagnose OpenAPI error codes", "diagnose OpenAPI error messages", "Diagnose OpenAPI API call failures using Request ID".
Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan_validation, check_response, check_accuracy_precision, check_detection_limits, check_bioanalytical_run, compare_methods) under ICH Q2(R2)/Q14, ICH M10, USP 1220/1225/1226, CLSI EP, or ISO/IEC 17025. Covers protocols, linearity, accuracy and precision, DL/QL, M10 run checks, TOST equivalence, Deming and Passing-Bablok. Use when designing a validation protocol with pre-stated acceptance criteria. Use when evaluating linearity, precision, or detection limit data. Use when checking an ICH M10 bioanalytical run or ISR. Use when comparing or transferring a method between labs. Does not decide a method is validated; USP, CLSI, ISO text is not supplied.
Keep web animations inside the frame budget — animate composite-only properties, keep motion off the main thread when the page is busy, and find the cause when an animation drops frames. Covers the layout/paint/composite pipeline, cheaper property swaps, CSS vs WAAPI vs requestAnimationFrame, Motion's hardware-accelerated path, React re-rendering per frame, inherited CSS variable recalculation, blur cost, and when `will-change` actually helps. Use when an animation is janky, choppy, stutters, or drops frames; when choosing which property to animate; when deciding between CSS and JS animation on performance grounds; or when reaching for `will-change` or GPU layers. For choosing easing, duration, or whether to animate at all use animate; for reviewing motion as a whole use review-animations.
Performs ARA Seal Level 2 semantic epistemic review of an Agent-Native Research Artifact directory, reading PAPER.md, logic/claims.md, logic/experiments.md, and trace/exploration_tree.yaml. Scores six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) from 1 to 5 and writes a severity-ranked level2_report.json with a Strong Accept to Reject grade. Use when Level 1 structural validation has passed and an ARA needs a critique before release. Use when checking whether claims are supported by their cited experiments. Use when auditing falsification criteria or scope over-claiming. Use when judging whether an exploration tree documents real dead ends. Not for structural or reference validation, which is Level 1.
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Use this skill to perform an end-to-end review of an existing Jetpack Compose UI test file or test suite. Sequences six audit phases (setup correctness, finder discipline, assertion strength, action correctness, time/idle correctness, debug output) and routes each finding to the precise sibling skill that fixes it. Produces a prioritized issue list — does NOT mutate code. Use when the user asks "review my Compose tests", "audit this test class", "is this test flaky", "why is this test slow on CI", "which Compose tests should I rewrite", or pastes a `*Test.kt` file and asks for feedback.
Build or refactor AureusERP Laravel plugins using the project's plugin-manager and Filament conventions. Use when creating/updating plugin service providers, plugin registration, install/uninstall flow, dependency setup, admin/customer panel wiring, ACL and role permissions, policies, resources/clusters/pages/widgets, settings pages, dashboard pages, model structure, and table views.
[Hyper] Use this skill when optimizing an existing Codex skill through baseline-first experiments, binary evals, Guard checks, and one-mutation-at-a-time iteration. Use for skill autoresearch, measured trigger/workflow improvement, self-optimizing a skill, benchmarking skill changes, or resuming skill experiment artifacts. If invoked without a target, ask for the target skill and eval intent before creating artifacts or mutating files. Do not use for one-off skill creation/refactor, generic docs polish, app QA, commit-only, or push-only requests.
Catalog of high-value award redemptions where points dramatically outvalue cash. Tiered by legendary/excellent/good with current rates, devaluation history, and booking caveats. Includes Oceania and South Pacific plays (Australia, New Zealand, Tahiti, Fiji) and transatlantic business-class sweet spots.
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like: lambda durable functions, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, and reliable serverless applications.
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.