Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Make research code runnable and repeatable for artifact review by auditing README, dependencies, seeds, entrypoints, data instructions, result commands, and smoke tests with repro_check.py. Use for smoke tests, seed pinning, environment capture, reproducibility checks, or works-on-my-machine cleanup.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Text-to-image generation and image editing via Together AI, including FLUX and Kontext models, LoRA-based styling, reference-image guidance, and local image downloads. Reach for it whenever the user wants to generate or edit images on Together AI rather than create videos or build text-only chat applications.
Search for trending content on Toutiao: enter keywords to find the latest Toutiao posts (articles/images and videos), sort by reads or time, set a time range, view results in a terminal table, export to CSV, and generate interactive HTML reports. Use when users want to search popular Toutiao content, track Toutiao trends, or analyze viral articles. If the API returns insufficient credits (code=3210), automatically open Alipay to top up and continue the search.
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
Dark pattern detection and avoidance, persuasive vs. manipulative design, privacy UX, the regulatory landscape, sustainable/green UX, and UX writing with a microcopy library of action verbs, error messages, and empty-state copy. Use when writing interface copy or auditing a flow for manipulation.
Provides structured guidance for Vant of Vue 3.0. Use when the user needs Vant with Vue 3, asks about mobile UI components such as Button, Cell, Form, Dialog, Toast, Popup, ConfigProvider, theme customization, project setup, or wants to implement mobile-first interfaces with `vant` or `van-` components. This skill is aligned to the official Vant website and usage guide and should be used as the Vant Vue 3 skill entry.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
Keep an agent disciplined while vibe coding: small shippable slices, verify before done, prefer lean skills over long prompts, and separate UI from API layers. Use this skill when scoping work, starting a vibe-coding session, or the agent is thrashing — for any stack. Not for Sarvam API signatures (use sarvam-mcp, translate, speech-to-text, text-to-speech, chat, or voice-agents).
Download or open videos and recover platform captions, audio transcripts, keyframes, screen text, visual facts, and editing observations as a plain multimodal_transcript.md. Use for Douyin, Bilibili, YouTube, Xiaohongshu, experimental WeChat Channels links, or local video files when preparing complete source material for analysis or downstream Skill distillation.
Manage Volcengine's AI-native BaaS platform (Supabase edition / AIDAP / 火山引擎 AI 原生 BaaS 平台 Supabase 版) — a Volcengine-operated distribution that differs from official Supabase. Use when the user asks to create, inspect, or manage Volcengine Supabase or AIDAP resources — workspaces, branches, computes, SQL queries, schema changes, Auth, Realtime, Edge Functions, Storage buckets, frontend static-site hosting (Pages), API keys, connection info, or TypeScript type generation — or when a Volcengine deployment selects AIDAP as its database provider. Also trigger on Chinese prompts mentioning "火山引擎 Supabase" or "火山 Supabase". Operations run through the byted-supabase-cli command-line tool (installed via `npm i -g @byted-supabase/cli`; this is NOT the official `supabase` CLI). Do NOT use it for general database discussions, non-Supabase services (RDS MySQL, Redis), or pure client-side coding unrelated to Supabase backend management.
Official Volcengine documentation lookup tool supporting document search and full-text retrieval. Covers all Volcengine products, developer tools, support, and best practices, including the full lifecycle of product introductions, usage, billing, deployment, troubleshooting, API, SDK, and terms of service/agreements. Prefer this skill for any request involving Volcengine product consultation, usage questions, or documentation lookup.
Deploy and manage serverless applications on Volcengine veFaaS. Use when the user wants to deploy web apps, manage functions (pull code, upload and deploy), configure environment variables, inspect veFaaS projects, troubleshoot vefaas CLI/auth/framework issues, or work with veFaaS services.
Drafts peer-review rebuttals and author responses in the three real venue formats - (a) strict one-page LaTeX rebuttal PDFs (CVPR-style), (b) OpenReview threaded per-review replies under 10,000-character budgets (NeurIPS/ICML/ICLR), and (c) revise-and-resubmit packages with a change-log response document (CHI, SIGMOD/ICDE revision rounds, journals). Anchors every response to paper sections, tables, figures, and line numbers; enforces character/page budgets and point-by-point coverage with bundled checker scripts; ships a one-page rebuttal LaTeX template. Use when the user says "write my rebuttal", "respond to reviewers", "author response", "reviews came back", "reviewer 2 says", "revise and resubmit", "response letter", "rebuttal deadline", or needs to fit a response into an OpenReview character limit or a one-page PDF. Drafts files on disk only; never posts, uploads, or submits.
How to work in a Writing Pipeline project (the `writing-pipeline` starter pack): a three-stage drafting flow, ideas → drafts → published. Read when the project has these folders, OR when asked to capture an idea, start or revise a draft, review a piece before it ships, or publish it. Carries the stage flow and review behaviors so that guidance does not live inside template bodies or folder descriptions. Complements the platform `open-knowledge` skill; does not replace it.
Analyze mini-program project source code (including minified/obfuscated code), identify core business steps, extract network interfaces and JSAPI calls, generate a skill subpackage compliant with the wx.modelContext specification (with atomic interfaces + atomic components), and complete the app.json / project.config.json configuration integration. Trigger in these scenarios: turning mini-program page capabilities into mini-program AI atomic interfaces, generating skills/ subpackage code, deriving MCP tools from a source project, code generation for mini-program AI development mode. Handles static generation only; after generation completes, hand off to wxa-skills-validate for validation.
Use when you need to understand the positioning, capabilities, architecture or integration flow of the Ziniao browser WebDriver automation interface, for design discussions, integration planning or tool evaluation. Do not use it to write concrete automation scripts — when executing, refer directly to the interfaces and examples in reference/.
Periodically lint the full OpenSpec archive for cross-change decision drift, index/spec reconciliation, and structural over-coupling, the gap nothing else in the QRSPI/OpenSpec stack covers, since every other drift check (accelint-onboard-openspec, accelint-architecture-doc, accelint-qrspi-apply Phase 4) only looks forward from a single change's own artifacts. Use this skill when the user wants to "run archive synthesis," "lint the openspec archive," "check for decision drift," "audit the spec archive for contradictions," "find stale specs," "reconcile the specs index," "check capability coupling," or when accelint-qrspi-archive has surfaced its own suggestion that 15+ changes have archived since the last synthesis run. Also use when the user asks whether an old design decision still holds given everything decided since, whether specs/INDEX.md still matches the actual spec.md files on disk, or whether some capability has become an over-coupled refactor candidate. This skill never runs automatically and never blocks another skill — it is always either a human-invoked audit or an offered suggestion the human accepts explicitly.
Reference guide for the Atlassian CLI (acli), a command-line tool for interacting with Jira Cloud and administering Atlassian organizations. Use when the user wants to perform Jira operations (create, edit, search, or transition work items; manage projects, boards, sprints, filters, and dashboards), administer Atlassian organizations (manage users and authentication), or automate Atlassian workflows from the terminal. Covers all acli commands, including: jira workitem (create, edit, search, assign, transition, comment, clone, link, archive), jira project (create, list, update, archive), jira board/sprint, jira filter/dashboard, admin user management, and rovodev (Rovo Dev AI agent). Requires an authenticated acli binary already installed on the system.
Use when putting the agent in this repository on a Veris Bench bench as a "Your image" candidate, when updating that candidate to a new version, or when its bench attempts show empty replies, failed tool calls, no model calls for the grader, or never reach the bench's twins.
Operate the Agent Evaluation (agent-test) platform through ae-cli: manage evaluation assets, configure and run Agent or preset-output evaluations, and analyze results. Use for platform evaluation tasks and their model, credential, integration, or schedule setup.
Use when the user wants to build a CLI tool to automate browser interactions on a specific website using kimi-webbridge. Invoke when user says "create a CLI for X site", "build a tool to automate X", or wants to control a website programmatically via an AI agent.
Axora AgentGuard — AI agent security guard. Run /agentguard checkup for a full security health check, scans all installed skills, checks credentials, permissions, and network exposure, then delivers an HTML report directly to you. Also use for scanning third-party code, blocking dangerous commands, preventing data leaks, evaluating action safety, and running daily security patrols.
Design patterns for agentic AI: multi-agent orchestration UX, generative UI, RAG interfaces, LLM hallucination guardrails, confidence indicators, and trust calibration. Use when designing AI copilots or autonomous agents, adding verification affordances, or auditing an AI feature for safety, control, and consent.
Use akshare to retrieve real-time and historical data for Chinese financial markets. Use this skill to look up real-time quotes, historical data, and financial statements for financial products such as A-shares, Hong Kong stocks, U.S. stocks, indices, funds, and futures.
Comprehensive health inspection tool for Alibaba Cloud network products (EIP, CBWP, NAT Gateway, CEN, Transit Router, Physical Connection, VBR, Global Accelerator, CLB, ALB, NLB). Analyzes bandwidth utilization, connection count, QPS, and packet loss using Cloud Monitor data; generates a Markdown inspection report with monitoring charts, risk assessment, and scaling recommendations. All API calls are read-only. Use when users want to inspect network product usage, check bandwidth headroom, assess capacity before a business launch, or identify over-limit risk. Triggered by: inspect network products, network health check, bandwidth inspection, EIP/NAT/CLB/ALB/NLB/CEN/VBR/GA inspection, network utilization analysis, pre-launch network inspection, capacity assessment, bandwidth over-limit risk.
Analyze whether ClickHouse indexes (PRIMARY KEY, ORDER BY, skipping indexes, projections) are effective for the actual query patterns. Use when investigating index effectiveness, ORDER BY key design, query-to-index alignment, or when queries scan far more data than expected.
API documentation specialist who creates comprehensive OpenAPI/Swagger specifications and technical documentation for RESTful APIs, GraphQL schemas, and microservices architectures. Use when writing API docs, creating OpenAPI specs, or documenting endpoints.
Transform natural language application descriptions into production-ready DigitalOcean App Platform specifications. Use when designing apps, creating app specs, generating deploy.template.yaml, or architecting multi-component applications.
Debug running App Platform applications by accessing containers, analyzing logs, running diagnostics, and applying fixes. Use when apps fail to deploy, crash at runtime, have connectivity issues, or need performance diagnosis.
Create, edit, repair, and validate Arabic or Arabic-English content with logical-order Unicode, native RTL semantics, mixed-language handling, Arabic-capable typography, and format-specific QA. Use for Word, PowerPoint, PDF, web, spreadsheet, image, and reusable Arabic-copy tasks; pair it with the skill for the requested output format.
Search arXiv for research papers by topic, category, author, or date range. Returns structured JSON with titles, authors, abstracts, and links - no full text (pair with arxiv-analyze for that). Use when the user says "search arxiv", "find arxiv papers", "arxiv papers on", "latest papers about", or "arxiv research".
Turn a vague idea or task into a confirmed Working Brief by interviewing the user in rounds — every question that can be asked now, numbered, each with a recommended answer — then hand the brief to whoever does the work. Use when the user invokes Ask Me, wants to clarify scope or requirements before work begins (เคลียร์โจทย์ วางขอบเขต ทำ brief), or asks to execute a WORKING-BRIEF.md.
Use when setting up, troubleshooting, or modifying the shared hooks and agent-callable utility scripts that enforce the autonomous dev/review workflow. Triggers on phrases like "push to main is blocked", "block-commit-outside-worktree hook failing", "configure hooks after npx skills add", "what does check-pr-review.sh do", "set up workflow hook symlinks", or when editing files under `skills/autonomous-common/`. Provides the hooks the autonomous-dev / autonomous-review skills depend on, plus utility scripts (gh-as-user.sh, mark-issue-checkbox.sh, reply-to-comments.sh, resolve-threads.sh).
Performs an AWS security posture review against the CIS Amazon Web Services Foundations Benchmark v3.0.0. Auto-invoked when reviewing AWS infrastructure, IAM policies, S3 configurations, CloudTrail settings, VPC security groups, or RDS encryption. Walks through all five benchmark sections, evaluates each recommendation, and produces a prioritized findings report with remediation guidance mapped to specific CIS control IDs.
Retrieve and search logs from B2C Commerce instances using the b2c CLI. Use this skill whenever the user needs to view server logs, search for errors, filter log entries by level or time, or monitor logs in real-time. Also use when the user reports a 500 error, broken checkout, failing job, or any server-side issue that needs log investigation — even if they just say "something's broken on the sandbox" or "check the logs".
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.