Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Declarative UI widgets from JSON for React/Next.js from ui.inference.sh. Render rich interactive UIs from structured agent responses. Capabilities: forms, buttons, cards, layouts, inputs, selects, checkboxes. Use for: agent-generated UIs, dynamic forms, data display, interactive cards. Triggers: widgets, declarative ui, json ui, widget renderer, agent widgets, dynamic ui, form widgets, card widgets, shadcn widgets, structured output ui
Plan and coordinate approved multi-task work from prose, issues, repository evidence, or an explicitly selected Project by grouping selected issues into coherent PRs, delegating implementation in reusable task worktrees, and delivering verified draft PRs with required native stacks for dependent PRs. Never merges.
After one or more discovery or analysis rounds, explicitly asks "What is still missing?" Modalities not swept, claims not verified, sources not read, edge cases not considered, downstream effects not traced, assumptions not checked. The output becomes the seed for the next round of work (more angles, more verification, more research). Use near the end of Research, Review, or Understand phases, or before declaring a task complete. Invoke via /work-gaps.
Adversarial verification ("try to refute") of a claim or a SET of claims/findings/root-causes/design-decisions using N independent sub-agent refuters per claim. Runs as a PIPELINE (each claim's refuter-group is independent — no barrier across claims) with perspective-diverse lenses as the DEFAULT for security/auth/multi-tenancy/data-integrity/correctness claims. Survival is EVIDENCE-WEIGHTED, not naive majority: only verdicts that re-read the cited source count; lazy/empty verdicts are abstentions. Strongly prefers direct deterministic oracles (commands, tests, git, type checks, exact grep) over agent voting. Use when the user says "adversarial verify", "refute this", "have verifiers attack", "perspective-diverse review", "run adversarial checks on these findings", "ultracode verify", or "kill this claim".
Parallel blind search from multiple independent angles (by structure/files, by content/semantics, by git history/time, by entity/domain, by error paths, alternative-storage-paths, config/realm dimensions, etc.), then a BARRIER at the merge step that dedups against a persistent SEEN set and lists what no angle covered. Each searcher is kept ignorant of what the others found in the same round. Use when one search strategy is known to be incomplete: "find all X", security review, "where can this break?", data flow tracing. Invoke via /work-sweep.
Write and ship a blog post for your project that reads like a human wrote it and pulls SEO traffic to your site. Use when a contributor wants to draft, edit, or publish a blog post, add a post to the site, write about the project for search/traction, or make an existing draft sound less like AI. Enforces the house voice (no em dashes), picks a non-cannibalizing angle, uses ASD-STE100 Simplified Technical English for technical prose, wires the post into your site, and runs the humanizer pass before shipping.
Write articles from documents — convert PDF, DOCX, EPUB, URL, YouTube, or text into a series of Vietnamese articles in a chosen style (7 presets or custom 5 dimensions). Supports documents from a few pages to 100K+ words with tier-based processing. Output at CWD/writer-agent/.
Author and maintain Sigma detection rules — structure, logsource taxonomy, detection logic with modifiers, false-positive filtering, backend conversion with pySigma, and offline validation with Hayabusa or Chainsaw. Use when translating threat intel into vendor-agnostic detection logic, building a detection-as-code pipeline around Sigma, reviewing or tuning existing Sigma rules, or converting rules across SIEM backends.
Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.
In an external XGENT.ai Portal app's own repo, generate its companion CLAUDE.md / PRODUCT.md / DESIGN.md (with AGENTS.md written as a mirror) — read app.manifest.json and code facts, ask once about anything missing, fill in three ready-to-use documents from templates, leave no placeholders, and never overwrite existing files. Use when the task is "initialize/onboard a new external app repo", "add CLAUDE.md / AGENTS.md / PRODUCT.md / DESIGN.md to this app repo", "add a design document that impeccable can read", or when the user has just received an empty app repo or one with only code and no specs; apps inside the portal monorepo and non-XGENT projects do not use this skill. Use in an external XGENT portal app's own repo to scaffold its CLAUDE.md / PRODUCT.md / DESIGN.md (AGENTS.md is written as a mirror of CLAUDE.md) from the app manifest and repo facts — one round of questions, no leftover placeholders, never overwrites existing files.
Draft and publish posts to 小红书 (Xiaohongshu/RED). Use when creating content for 小红书, drafting posts, generating cover images, or publishing via browser automation. Covers the full workflow from content creation to browser-based publishing, including cover image generation with Pillow.
X Intelligence CLI for searching, monitoring, and analyzing X/Twitter from the terminal. Use for X/Twitter research prompts such as "search x", "find tweets about", "what's X saying", trend checks, follower diffs, real-time watch tasks, sentiment/report analysis, and bookmark-sync workflows. Best when recent community discourse matters (library/API changes, launches, market or cultural events). Supports search, watch, trends, bookmarks, likes/following (OAuth), Grok analysis, and JSON/JSONL/CSV/Markdown export. Non-goals: posting original tweets, DMs, or enterprise-only features.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g. adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Strategic web design consultant for building, reviewing, or auditing websites and landing pages. Trigger when the user asks to build a landing page, review a site's messaging, write hero copy or CTAs, audit for "AI slop," or plan page information architecture. Also trigger on keywords: "landing page," "above the fold," "hero section," "conversion funnel," "social proof," "product page design."
Conduct pure research for YouTube video topics by analyzing competitors, identifying content gaps, and documenting strategic insights. Use when you need to research a video topic before planning. Produces concise, insight-focused research documents that identify the biggest opportunities for video performance.
Manage a Zurl short link service — create, update, delete, search, and list short URLs, and fetch URL metadata. Trigger whenever the user asks to "shorten this link", "generate a short URL", "create a short link", "短链接", "缩短", "短链", manage short links, or pastes a long URL and asks to make it shorter. Do NOT skip this skill just because the user didn't explicitly say "短链接" or "short URL" — even "帮我缩短这个链接" or "把这个 网址变短" should trigger it. Any request involving URL shortening, short link management, or batch URL operations should use this skill.
Search a library of 4,600+ AI motion graphics with their prompts and 2,100+ video-editor presets before building any motion graphic or video edit from scratch. Use whenever the user wants styled captions on video (karaoke, word-by-word, TikTok, Reels, Shorts), hooks, kinetic typography, titles, lower thirds, text behind the subject, transitions, colour grades and film looks, split-screen layouts, font pairings, logo reveals, intros, product launch videos or explainer videos, in HyperFrames, Remotion or HTML, even if they only say make or build and never ask for examples. Returns ready presets that one MIT engine renders as a pure function of time, real examples with prompts and creator credit, and 40 explainer styles with starter prompts. Not for converting, trimming or transcribing video files or fixing a framework install.
Submit an 8D to a customer, format a Ford 8D report, BMW G8D, VW QMSS, or OEM complaint response for formal submission. Covers OEM-specific format requirements, evidence standards, and discipline-by-discipline writing rules for D0–D8. Use when preparing an 8D report for Ford, BMW, VW/Audi, Stellantis, or any customer requiring formal 8D closure.
Migrate an Angular application to the One Allianz (A1) Design System. Use when: migrating to A1 design system, applying One Allianz theme, migrating circle toggles to tiles, updating small stages, updating layout to left-alignment, A1 brand kit, ngx-brand-kit, ng-aquila migration, NDBX to A1.
Review abuse, fraud, spam, promotion abuse, payment fraud, refund abuse, account takeover risk, marketplace trust, game economy exploits, referral abuse, automation abuse, and moderation risk for software products. Use when designing controls, risk ladders, rate limits, manual review, user messaging, support escalation, or fraud-safe product systems.
Enumerate and abuse Active Directory Certificate Services with Certipy and Certify — the ESC1 through ESC16 escalation paths, vulnerable template and CA configurations, NTLM relay to web enrollment, certificate-based authentication and persistence, and the strong-mapping changes that gate several of them. Use when a domain has a certificate authority, when Certipy or BloodHound reports vulnerable templates, or when escalating from a low-privilege domain user
WCAG 2.1/2.2 compliance, WAI-ARIA implementation, screen reader optimization, keyboard navigation, and accessibility testing expert. Use PROACTIVELY for accessibility violations, ARIA errors, keyboard navigation issues, screen reader compatibility problems, or accessibility testing automation needs.
Integrate the Temps Node.js SDKs for server-side platform access, KV storage, and Blob storage. Use when the user wants to: (1) Call the Temps platform API from Node.js (deployments, projects, analytics, session replay, etc.), (2) Use Temps KV (key-value) storage, (3) Use Temps Blob storage for files, (4) Server-side integration with a Temps project, (5) Backend access to Temps resources. Triggers: "temps node sdk", "temps kv", "temps blob", "backend integration", "node.js temps", "@temps-sdk/node-sdk".
Use when a project needs admin/CMS/back-office UI architecture: roles, permissions, content workflows, AI assistant boundaries, audit logs, destructive-action confirmations, and builder handoff. Planning only; do not perform production admin actions or expose secrets.
Run a bounded adversarial sweep of an existing test suite. Use to harden a suite or subsystem against malformed inputs, boundaries, invalid state, races, dependency/resource failures, weak or redundant tests, flakes, and missing durable regressions. Skip ordinary test additions, load, chaos, and penetration testing.
Use when the user asks to generate, create, or scaffold ADVPL/TLPP code for TOTVS Protheus -- User Functions, Static Functions, TLPP classes, MVC (Model/View/Controller), REST APIs, SOAP web services, entry points (pontos de entrada), TReport/FWMsPrinter reports, jobs, or workflows. Also triggers on Portuguese phrasing like "gerar codigo", "criar rotina", "criar fonte", "novo ponto de entrada", "criar classe tlpp", "gerar api rest", "criar mvc", or routine name patterns like FATA001/MATA010. Covers naming conventions, Hungarian notation, namespace rules, identifier length limits, and mandatory User Function/error-handling structure.
Check and improve your brand's visibility across AI search engines (ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek). Set up tracking, run visibility analyses, audit your website for AI readability, and get actionable recommendations. Uses the npx goose-aeo@latest CLI.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end of a productive session when valuable context has emerged that is not yet documented. This complements agents-md-improver — improver audits, while this one captures.
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.