Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Structured AWAITING_USER_INPUT checkpoint format for requesting human decisions. When hitting a decision point, stop, present context, show 2-4 labeled options with implications, state a recommendation, and wait. Groups related decisions into single multi-question checkpoints. Includes subagent state-save-before-pause and resume-without-redoing-work patterns, plus factory-mode urgency classification (blocking/next-review/informational). Use when encountering business rule ambiguities, architecture trade-offs, scope questions, destructive actions, or any point requiring human judgment. Triggers on: "should I use X or Y", "which approach", "need a decision", "before I proceed", "confirm this action", "trade-off", "destructive change". Also activates when delegating to subagents that may hit decision points. NOT for: implementation details with one correct answer, or style choices covered by project conventions.
Generate AGENTS.md for end-user assistance. Covers setup, installation, running, and troubleshooting. Use proactively when user asks for "getting started" help or during /init user workflow. Examples: - user: "/init user" → user assistance AGENTS.md with official docs - user: "Create getting started guide" → installation + setup + troubleshooting - user: "Document how to use this repo" → user-focused AGENTS.md - user: "Help users run this software" → setup, prerequisites, usage patterns
Generate accurate Volcengine SDK examples by locating an API through API Explorer search, fetching its swagger, and calling api/common/explorer/make-code with user-provided Params. Use when the user asks how to write Volcengine SDK code, generate SDK samples, or call a Volcengine API in Python, Go, Java, PHP, cURL, Node.js. Supports Chinese and English API names such as "角色扮演", "AssumeRole", or "STS AssumeRole". Also use for explicit SDK configuration questions about retry, timeout, AK/SK, STS, AssumeRole, temporary credentials, proxy, connection pooling, SSL, debug mode, request signing, response parsing, and error handling. If the user only needs API parameters, enum values, required fields, error codes, response schemas, pagination, or API comparisons, hand off to volcengine-api. If they need CLI-based operations, hand off to volcengine-cli.
Analyzes Weibo (微博) trending topics and generates creative product ideas based on hot search keywords. Fetches real-time trending data from Weibo API, researches background information and user insights, evaluates product development potential using a 100-point scoring system, and creates an interactive HTML dashboard. Use when analyzing Chinese social media trends, identifying product opportunities from trending topics, or generating market-driven creative product concepts.
Integration guide for the wujie micro-frontend framework. Covers main/sub application integration, Vue2/Vue3/React component wrapping, the startApp/setupApp/preloadApp APIs, route synchronization and navigation, keep-alive preloading, bus communication, plugins and lifecycle, sub-application refactoring, deployment troubleshooting, and common issues. Use when users mention wujie, micro-frontend, sub-application integration, or a main application loading a sub-application.
Validate and fix mini program AI SKILLs artifacts. Triggered in the following scenarios: static validation of the skills/ directory, running atomic interfaces end to end, verifying atomic component rendering, fixing validation errors, and outputting delivery documents. Relies on WeChat DevTools for real-device verification.
Generate Xiaohongshu (小红书/RED) content optimized for the platform's CES algorithm. Use when: (1) creating xiaohongshu/小红书 posts, (2) writing Chinese social media content for RED, (3) generating content with xiaohongshu SEO optimization, (4) planning xiaohongshu content calendars. Supports diary-style, tutorial, review, and list formats with proper AI content labeling.
Reference for any XRPL Standard (XLS-N) when implementing or reviewing XRPL protocol features. Trigger on: XLS number (XLS-30, XLS-70), amendment name (AMM, Credentials, MPT, DID, NFToken, Batch, Escrow, Clawback, Firewall, Permissioned DEX), transaction type (AMMCreate, CredentialCreate, NFTokenMint, DelegateSet, PermissionedDomainSet, BatchSubmit), or ledger object name (Credential, AMM, MPToken, Delegate, Oracle, Bridge).
Marketing context: maintain confirmed product facts, audience, positioning, brand voice, verbal messaging, proof, vocabulary, copy examples, or business-goal inputs that the user explicitly wants reused in future marketing work. Use Auto-draft by default; start Interview only when explicitly requested. Passive context discovery never authorizes a write.
Wires the Navigation component from @cognite/dune-industrial-components/navigation into a Dune app. Use when adding a navigation header, top nav bar, sticky header, nav items, active page, nav links, navigation component, theme toggle, or dark mode support to a Dune app.
Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI. Use when a decision has genuine tradeoffs, high stakes, or hidden assumptions worth adversarial collaboration, or when confidence diagnostics matter more than a single recommendation. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.). Do not use for simple factual lookups, tasks with a clear correct answer, routine single-perspective work, or code execution and tool orchestration beyond debate.
Use for tasks that require temporary files, including during another workflow. Also use before creating, inspecting, moving, removing, or reusing agent task directories such as `.agent-*`, and when they appear during repository discovery or validation. Don’t use for tasks limited to durable project outputs, programs’ internal temporary resources, or tool-managed caches.
EXPERIMENTAL. Use when looking for meaningfully duplicated logic in a codebase, especially duplicate behavior hidden behind different names, different syntax, different control flow, or independently evolved implementations. Not for style issues, not for syntactic clone detection, and not for fixing what it finds.
Install Alibaba Cloud Agent Toolkit end-to-end: verify and set up prerequisites (uv, Alibaba Cloud CLI, authentication, CLI plugins, MCP Server Core, bearer token exchange), then install the toolkit via the current client's supported plugin mechanism. Use when: alibabacloud agent toolkit install, environment check, prerequisite check, setup alibabacloud, plugin install, toolkit setup, mcp core setup, aliyun CLI setup.
Use when managing Alibaba Cloud Backup and Disaster Recovery Center (BDRC) via OpenAPI/SDK, including the user needs backup/disaster-recovery resource operations, including inventory, policy/configuration changes, status checks, and troubleshooting BDRC workflows.
Use when managing Alibaba Cloud Data Lake Formation (DlfNext) via OpenAPI/SDK, including the user needs DLF Next catalog/governance resource operations, including listing resources, create/update flows, status checks, and troubleshooting metadata workflow issues.
Diagnoses ClickHouse external dictionaries - load status, memory usage, layout choice, reload staleness, source connectivity and lookup performance. Use for dictionary load failures, FAILED or LOADING_FAILED status, stale dictionary data, high dictionary RAM and slow dictGet lookups.
Diagnoses ClickHouse RAM usage, memory limits, OOM errors and the allocation breakdown across queries, caches, dictionaries and primary keys. Use when MEMORY_LIMIT_EXCEEDED appears, the server is killed by the OOM killer, memory grows steadily, or GROUP BY and JOIN queries run out of memory.
Diagnose ClickHouse replication health, Keeper connectivity, read-only replicas, replica lag, replication queue backlog and slow fetches. Use for replication lag, read-only replica problems, growing replication queues, failed fetches, or Keeper/ZooKeeper session and latency errors.
Diagnoses ClickHouse SELECT query performance, query patterns, slow queries, failures and optimization opportunities. Use for query latency, timeouts, high CPU queries, queries reading too much data and repeated expensive query patterns.
Diagnoses ClickHouse disk usage, compression efficiency, part sizes, storage policies and IO throughput. Use when disks fill up, data grows faster than expected, compression looks poor, IO or merges are slow, or detached and tiny parts accumulate.
Use this when user provides a Yii2 codebase for analysis or migration planning. Provides 6-phase workflow: scan, capability extraction, dependency analysis, requirements extraction, semantic indexing, and migration roadmap. Apply when user mentions Yii2, PHP legacy modernization, or framework migration to NestJS
Use when creating, repairing, converting, packaging, or verifying app icons for any platform from briefs, references, brand marks, SVG/logo/text assets, generated concepts, or existing icons; use the optional Apple adapter when Icon Composer output is requested
Configure domains, routing, CORS, VPC, static IPs, and inter-service communication for DigitalOcean App Platform. Use when setting up custom domains, subdomain routing, cross-origin API access, or secure database connectivity.
arkcli shared execution protocol: first-time setup entry point, the authentication gate before running business commands, command routing and selection order, and output/security/confirmation rules. Deep details (identity resolution, AK-SK boundaries, API Key recovery, real-name gate, profile defaults and drift, temporary data-plane execution context, version checks and explicit upgrades, global flags, failure triage) are loaded on demand from references/. Triggered when the user uses arkcli for the first time, hits a not-logged-in/auth failure, asks whether the version is the latest or requests an arkcli upgrade, needs to decide between product commands and raw api, or when any arkcli-* skill needs shared context.
The artifact layer for AI agents. artifact.cafe is the Artifact Layer for AI Agents: publish interactive static artifacts (HTML apps, dashboards, mockups, reports, slides, docs) to a review URL that humans open with no login and comment on directly — pinning feedback to elements and text. Authors then publish new immutable versions. Use when asked to "publish this for review", "share this for feedback", "put this online for comments", "get review on this", "ship a preview", "make a review link", "publish an artifact", "send this to a reviewer", "publish v2", "make a poll", "guestbook", "RSVP", or "collect submissions"
Above-the-Line (ATL) and Below-the-Line (BTL) messaging framework for targeting executives vs end-users. Use when crafting messages for different seniority levels, deciding message length and tone, or adapting outreach to VPs/C-Level vs Managers/ICs.
Best practices for AutoML and hyperparameter search with Optuna, Ray Tune, and PyCaret, covering search-space design, validation splits, and leakage prevention. Use when tuning model hyperparameters, setting up a pruned or distributed hyperparameter search, designing a nested validation scheme, or evaluating whether an AutoML leaderboard result is production-ready.
Create storefront controllers using SFRA or classic patterns with server.get/post, middleware chains, and res.render/json. Use this skill whenever the user needs to build a page route, handle form submissions, create AJAX endpoints, extend or override existing controllers, or add middleware to a request pipeline. Also use when debugging route registration or response rendering -- even if they just say 'new page endpoint' or 'handle a POST request'.
Web typography from choosing fonts to spacing, wrapping and accessibility. Use when picking or pairing typefaces, configuring variable fonts or OpenType features, setting up a type scale, checking heading hierarchy, styling text in components, truncating text, styling underlines, selection, placeholders or carets, or reviewing frontend code for typography. Triggers on typography, fonts, font formats, woff2, variable fonts, font-weight, opentype, font-feature-settings, letter-spacing, line-height, type scale, heading hierarchy, heading levels, tabular numbers, text-wrap, truncation, line clamp, underlines, text-decoration, text selection, iOS input zoom, scaled input text, font smoothing, text contrast, measure, line length, text-box, smart punctuation, drop cap.
Plan static inspection of unknown binary files with a deterministic CLI whose Ghidra operations are currently unimplemented and fail closed. Use when you need to inspect a PE, ELF, or Mach-O file — triage suspicious binaries, map imported APIs, decompile functions, trace call paths, or produce structured evidence reports. Do not use for runtime analysis (debugging, dynamic tracing, sandbox execution), for modifying or patching binaries, or for binaries you already know everything about. The skill owns planning, hypothesis formation, and evidence synthesis; the CLI owns all deterministic operations.
Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.
Forensic bug and issue triage. Produces a graded investigation case file: symptoms, evidence (graded A/B/C by confidence), ranked hypotheses, suspected components, and a recommended planning response. INVESTIGATES and DOCUMENTS only — does NOT fix code, run tests, or implement. Hands off as a story to an external dev tool. Use when the user says: - "investigate this bug" / "triage this issue" / "debug triage" - "what's causing [symptom]" / "why is [feature] broken" - "something's wrong with [component]" / "users are reporting [problem]" - "figure out what happened" / "root cause this" - "I need a bug report" / "create an investigation case file" - "forensic analysis" / "diagnose this" - "error triage" / "issue investigation" - "what do we know about [incident/issue]". Three intents: Create (new case file), Update (add evidence to open case), Validate (check draft for completeness before handoff). Output lands in bmad-output/; a fix story is drafted on handoff.
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.