Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill to shape product or engineering work before committing time to it: set appetites instead of estimates, narrow raw ideas into bounded problems, sketch solutions at the right level of abstraction, de-risk rabbit holes, write pitches, bet with capped downside (circuit breaker), and govern builds with discovered scopes and scope hammering. Adapted from Basecamp's Shape Up and extended for human+AI-agent teams. Use when a raw idea, feature request, or "redesign X" grab-bag needs to become a bounded project before anyone builds; when planning how much work an idea is worth; or when delegated agent builds need budgets, kill criteria, and non-convergence rules. Do not use for discovering whether a problem is real (use product-discovery), for portfolio-level sequencing across quarters (product-roadmapping-and-portfolio), for formal specification after the bet is placed (spec-driven-development), or for task-level prioritization frameworks like RICE (product-methodology).
AI/LLM prompt jailbreak techniques. Use when the target system includes an AI chatbot, AI agent, or any LLM-based conversational system. Covers role-playing, encoding bypasses, language switching, context window attacks, logical chain progression, system prompt override, and other jailbreak methods.
Use when generating Datex Studio release notes for an application over a time range instead of between two explicitly chosen branches. Discovers which two published releases to compare — the last one strictly before `range_start` and the last one inside `[range_start, range_end]` — then delegates to `release-notes-generator` for the actual notes. Designed for unattended weekly runs (e.g. every Monday covering the prior Mon–Sun week), but works for any range. Trigger for: "weekly release notes", "release notes for <app> last week", "what shipped in <app> between <date> and <date>", "scheduled release notes run". For release notes between two explicitly-named branches, use `release-notes-generator` directly.
R3F performance optimization—LOD (Level of Detail), frustum culling, instancing strategies, draw call reduction, frame budgets, lazy loading, and profiling tools. Use when optimizing render performance, handling large scenes, or debugging frame rate issues.
Break a bloated, monolithic agent system prompt into a lean stable core plus extracted Ratel-style skills. Use when a prompt is too long or does too many things, to extract or factor procedures into skills, decompose or split a prompt, cut per-turn token cost, or `/ratel-decompose-prompt`. Writes a markdown decomposition plan (lean core, skill inventory, per-skill SKILL definitions, registration wiring) to <repo>/.ratel/ without rewriting the prompt or code. Reached from /ratel-assessment's Prompt Decomposition dimension; pairs with /ratel-tune-definitions.
Use when generating release notes between two Datex Studio releases. Enumerates the changed-dependency worklist with `dxs source release-tree`, mines each package's commits and linked DevOps work items, reads config diffs, and produces Technical and Customer release notes. Works for Datex products and for customer applications (which reference both the shared Datex catalog and their own org's packages). Trigger for: "generate release notes from X to Y", "write release notes between <old> and <new>", "release notes for <app> between branches A and B", "compare releases X and Y and summarize". For time-range-based anchor picking ("weekly notes", "what shipped last week"), use `prospective-release-notes` — it resolves the two branch IDs and then invokes this skill.
Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns, quality gates, and next-cycle vocabulary. Use after a build, QA pass, demo, user complaint, or abandoned attempt when the useful output is what the next pass must learn rather than the code itself.
Use when working with RisingWave — streaming SQL database, materialized views, sources, sinks, CDC from PostgreSQL/MySQL, Kafka ingestion, time windows (TUMBLE/HOP/SESSION), watermarks, EMIT ON WINDOW CLOSE, port 4566, risingwave-mcp, event streaming pipeline design, real-time analytics, stream processing
Building Roblox UI — engine primitives (GuiObjects, UDim2, AnchorPoint, layouts, inputs, containers) plus the Fusion 0.3 reactive framework. Use when writing, reviewing, or debugging UI components, sizing/positioning, layout structures, input handling, render order, or component lifecycle. UI layer only — engine semantics live in roblox-dev; language rules live in luau-expert; Rojo/Wally workflow lives in roblox-toolchain.
Analyzes decisions from multiple stakeholder perspectives (engineering, product, legal, finance, users) to uncover blind spots, surface tensions, and synthesize alignment paths with explicit tradeoffs. Use when stakeholders have conflicting priorities, need to pressure-test proposals, build cross-functional empathy, or when user mentions "what would X think", "stakeholder alignment", "see from their perspective", "blind spots", or "conflicting interests".
Run Indic speech and language tasks through the Sarvam MCP server: translate text, transcribe or dub audio, TTS, localize i18n files, LLM complete, document parse / extract / classify / split, or fetch Sarvam API docs/snippets while coding. Use this skill when the user wants Sarvam to act in chat, when sarvam_tools_* / sarvam_code_* are available, or when setting up sarvam-mcp in Cursor, Claude Code, Claude Desktop, Windsurf, Zed, Codex, Gemini CLI, VS Code, Cline, Continue, or LM Studio — even if they only say "translate this to Hindi" or "make it speak." Do not use for LiveKit/Pipecat agent code (voice-agents) or SDK-only coding when MCP is not installed (translate/text, translate/document, speech-to-text, text-to-speech, chat).
Analyzes Software Bills of Materials (SBOMs) for completeness against NTIA minimum elements, interprets VEX status documents, performs transitive dependency risk analysis, and detects license conflicts. Supports CycloneDX 1.5 and SPDX 2.3 formats with CSAF-based VEX correlation. Auto-invoked when SBOM files are shared, supply chain risk questions arise, or VEX documents require interpretation.
Record AI-driven browser demos with screencli. One command creates a polished screen recording with gradient backgrounds, auto-zoom, click highlights, and cursor trails — then uploads it to a shareable link. Use when the user wants to record a demo, screencast, walkthrough, or video of a web app.
Apply repository-grounded senior engineering judgment to substantial JavaScript or TypeScript work and bounded JS/TS changes with production or cross-boundary risk. Do not use for trivial syntax questions, generic tutoring, or tasks with no JS/TS artifact unless explicitly invoked. Use for Node, browser, frontend, worker, and edge work where correctness, contracts, state, effects, concurrency, compatibility, security, reuse, runtime alignment, or long-term ownership materially matters.
Audit and improve website discoverability across traditional search, answer engines, and generative search. Use for technical SEO, on-page content, structured data, question and entity architecture, AI citations, crawler controls, agent-readable content, local/national site portfolios, scaled-content quality, and reproducible visibility measurement. Do not use for only copy-editing, writing, CMS operations, or generic AI marketing claims without a defined search surface and verification plan
Use to author an Omni WorkSkillRouting rule (field-based skill criteria): map a related-entity field value to a required Omni Skill (e.g. add the Voice skill when Case.Origin = Phone), deployed as one WorkSkillRouting record via the Metadata API. Idempotent via the Metadata API files[].state signal; one rule per related entity. Triggers: add field-based skill routing, route by a Case field to a skill, route by a MessagingSession field to a skill, configure attribute-based skills routing, require an Omni skill for a field value. Do not use to create the Skill or bind agents to it (service-omni-skills-based-routing-configure), to create agent users, or to configure queues.
Configure Salesforce integrations: Named Credentials, Connected Apps, External Services, Platform Events, CDC, and auth flows. Use when setting up integration infrastructure, metadata XML, or choosing architecture patterns. Activate on .namedCredential-meta.xml, .connectedApp-meta.xml, .platformEvent-meta.xml, mentions of "Named Credential", "Connected App", "Platform Event", "CDC", "External Service", or "OAuth flow".
Create vertical 9:16 video clips from full music videos for Instagram Reels, TikTok, and YouTube Shorts. Takes full-length music video and extracts key moments, re-frames for mobile, and optimizes for social platforms. Use when creating short-form social content from PsalMix music videos or any video content.
Write ClickHouse queries for SigNoz dashboards over OpenTelemetry logs and traces. Use this skill whenever the user asks for SigNoz ClickHouse queries for logs or traces, SigNoz dashboard queries, log analysis, span counts, latency, or trace breakdowns.
Create new skills (SKILL.md files), modify and improve existing skills, and design skill descriptions for accurate triggering. Use when the user wants to create a new skill from scratch, edit an existing skill, optimize a skill's description, or convert a workflow they just demonstrated into a reusable skill.
Manage duoduo's idle auto-compact for channel sessions — enable/disable per conversation, read the measured compaction stats, and retune thresholds with the break-even formula when the owner changes model/backend or asks about idle-session cost. Trigger when the owner mentions 自动压缩/smart compaction/压缩策略, asks why a session was compacted (a compact notice appeared), switches a session to a metered or short-cache-TTL backend, or asks to protect a conversation from compaction. Also use proactively right after the FIRST auto-compaction of a session you manage — that event carries the calibration measurement.
For Ray mini-program smart-ui, assists with generating and modifying pages and components using a meta-first workflow. Use when the user requests UI construction, component refactoring, form and feedback interactions, navigation display, image-to-code, or smart-ui troubleshooting and upgrades; also covers using smart-ui Web Components (assets/wc/ directory) in a plain browser / H5 / non-mini-program host. Covers smart-ui only; consult _meta.json and the component docs before implementing, and do not invent props, events, or capabilities.
Socrates' thinking framework and questioning method. Based on deep research into 20+ sources including Plato's dialogues (Apology, Republic, Symposium, Phaedo, Meno, Theaetetus), Xenophon's Memorabilia, and Aristotle's related accounts, it distills 5 core thought models, 7 life heuristics, and a complete expression DNA. Purpose: as a thinking advisor, use Socrates' perspective to analyze blind spots in thinking, logical fallacies, cognitive biases, life choices, and other issues. Use when the user mentions "with Socrates' perspective", "how would Socrates see it", "Socrates mode", or "socrates perspective". Also applies to: critical thinking training, logical analysis, self-reflection, definition clarification, values examination, argument analysis. Even if the user only says "help me think it through", "is this logic right", "maieutics", "dig deeper", or "are there holes in my thinking", it can trigger. Do not trigger when the user is only asking general questions such as "is this decision reliable" or "help me make a choice" — activate only when Socrates' core methodology such as critical thinking, logical questioning, cognitive humility, or definition clarification is involved.
Choose and refactor visionOS app architecture across surfaces, scene boundaries, state ownership, and file layout. Use when deciding window vs volume vs immersive space, splitting a feature across scenes, cleaning up a monolithic spatial root, or defining the ownership map before implementing SwiftUI or RealityKit details.
Use when building a DB-backed job queue / task scheduler on SQLAlchemy 2.x whose readiness is dependency-driven, whose jobs are long-running and stateful, and whose only durable substrate is the relational DB — single box, embeddable, no broker, multi-dialect (SQLite / PostgreSQL / MySQL). Covers the generic jobs/job_deps model, the ready-set query, the per-dialect atomic lease (FOR UPDATE SKIP LOCKED on PostgreSQL + MySQL 8 vs BEGIN IMMEDIATE on SQLite, with dialect detection), crash-resume via heartbeat + lease expiry + stale-lease reclaim, the hung-but-alive per-dispatch timeout, weighted fair-share over group_key, the scan→rank→lease→dispatch→persist→reclaim tick loop, polling vs LISTEN/NOTIFY wake, and the at-least-once idempotency contract. Keywords: job queue, task scheduler, ready-set, SKIP LOCKED, lease, crash-resume, multi-dialect, SQLAlchemy, background jobs. Sync-first. Not the SQLAlchemy data layer or locking primitive (sqlalchemy), not migrations (alembic).
When legal analysis yields multiple possible conclusions, risk points, or issues in dispute, these risks need to be systematically ranked by likelihood of occurrence and severity of impact, so that decision-makers can focus on the most critical risks and allocate resources sensibly. This skill triggers in the following scenarios: (1) multiple compliance risks are found in legal due diligence and need to be ranked; (2) litigation strategy requires assessing the likelihood and consequences of multiple adverse conclusions; (3) transaction structuring requires identifying and ordering key legal obstacles; (4) contract review uncovers multiple risky clauses whose amendment priority must be determined; (5) regulatory compliance assessment requires tiered management of multiple violation risks; (6) any scenario requiring strategic trade-offs among legal risks under limited resources.
Quality-control workflow for complex, multi-step tasks that need research, clarification, a verifiable plan, independent review, and evidence-backed delivery. Use for substantial implementations, decision studies, multi-file deliverables, and exhaustive document or visual checks, or when the user explicitly asks to use SureForge. Scale down for small tasks; do not activate automatically for casual questions, simple lookups, or trivial edits.
Create professional SVG logos from concept briefs or descriptions. Use when generating SVG logo files, creating logo variations (horizontal, vertical, icon-only), or implementing logo designs. Triggers on "create SVG logo," "generate logo," "make a logo," "logo SVG," "design a logo," or when given a logo concept brief from logo-ideation.
Use this skill for Angular apps needing Excel-like UI using the Syncfusion Spreadsheet Component. Trigger for creating, viewing, editing Excel (.xlsx, .xls, .xlsb) and CSV files; embedding spreadsheet editors; data binding from APIs/JSON; using formulas, charts, validation, filtering, or conditional formatting. Also trigger when users reference spreadsheet files ("open xlsx", "load Excel file", "add Syncfusion spreadsheet", "bind data to spreadsheet"). Do NOT trigger for standalone file processing without UI components.
Use this skill when a user asks how to generate, integrate, or implement a Word‑like document editor in Blazor using Syncfusion. Trigger it for requests involving the Syncfusion Blazor Document Editor, Blazor‑based integration, document editing and formatting, comments and track changes, working with tables and images, managing headers and footers, applying document protection, and building end‑to‑end document workflows in Blazor applications.
Syncpack (monorepo dependency version synchronization tool) reference. .syncpackrc configuration, lint / fix / update / format commands, versionGroups, semverGroups, updateGroups, customTypes, source, catalog protocol, semverRangeOnly, minimumReleaseAge, severity, sourceMode, package.json ordering, dependency version alignment, CI integration.
Issue, cancel, and fetch Hungarian invoices via the szamlazz.hu Agent API. Handles VAT calculation, NAV taxpayer lookup, partner caching, and PDF generation. Use when the user mentions számla, számlázás, invoice, sztornó, díjbekérő, proforma, or wants to bill a customer.
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs. Use this skill when the user provides chart images and requests technical analysis, trend identification, support/resistance levels, scenario planning, or probability assessments based purely on chart data without consideration of news or fundamental factors.
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
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.