Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Convert self-contained SVG scientific flowcharts and architecture diagrams into vector PDFs that preserve real text, as well as natively editable PowerPoint PPTX. Use when asked to convert SVG/PDF figures to editable PDF/PPTX, preserve editable text and vector shapes, or avoid a slide that is only a screenshot. Includes a tested SVG→PDF→text-template→native DrawingML workflow; the PPTX helper targets flattened path-based SVGs, not arbitrary SVG artwork.
Answer questions using Einstein's thought-experiment method, relativistic thinking and imagination-driven approach. Use when the user explicitly asks for this figure's perspective, mentions "einstein-perspective", or wants to apply its core method to analyze a problem; do not trigger automatically for general questions.
Set up a server-side proxy to forward Electric shape requests securely. Covers ELECTRIC_PROTOCOL_QUERY_PARAMS forwarding, server-side shape definition (table, where, params), content-encoding/content-length header cleanup, CORS configuration for electric-offset/electric-handle/electric-schema/electric-cursor headers, auth token injection, Bun fetch concurrency cap (BUN_CONFIG_MAX_HTTP_REQUESTS default 256), ELECTRIC_SECRET/SOURCE_SECRET server-side only, tenant isolation via WHERE positional params, onError 401 token refresh, and subset security (AND semantics). Load when creating proxy routes, adding auth, or configuring CORS for Electric.
Design Postgres schema and Electric shape definitions together for a new feature. Covers single-table shape constraint, cross-table joins using multiple shapes, WHERE clause design for tenant isolation, column selection for bandwidth optimization, replica mode choice (default vs full for old_value), enum casting in WHERE clauses, and txid handshake setup with pg_current_xact_id() for optimistic writes. Load when designing database tables for use with Electric shapes.
Build, test, and tune detection content — Sigma, YARA, Suricata, and EDR/SIEM queries — mapped to MITRE ATT&CK with explicit false-positive analysis and detection-as-code practices. Use when writing or reviewing a detection rule, converting IOCs or TTPs into alerts, measuring detection coverage, or reducing alert fatigue.
Analyzes errors, searches past solutions in memory, provides immediate fixes with code examples, and saves solutions for future reference. Use when user says "debug this", "fix this error", "why is this failing", or when error messages appear like TypeError, ECONNREFUSED, CORS, 404, 500, etc.
GitHub security research methodology: search GitHub for evasion/Loader/C2 technique repositories, analyze code patterns, extract new techniques into the knowledge base. Use when the knowledge base lacks evasion techniques for the current detection environment - first search high-star GitHub repositories, analyze the code, then write to evasion-techniques-db.json or loader-components-db.json.
Use when a user asks what AI-writing flags mean, whether detector output proves AI authorship, or wants a careful interpretation of possible false positives, especially for academic, hiring, publication, disciplinary, or other consequential decisions.
Use when the user wants to create an activity, generate an activity, initialize an activity, or create a new activity page, even if `c init` is not mentioned. Wraps `c init act` (source activity) and `c init mdc` (MDC activity) in `--non-interactive` mode, collecting missing parameters directly from the user.
Post-verification feature-branch closeout menu: after verify (and archive when applicable), and after optional delivery-discipline when code delivery is needed, present PR / merge / keep / continue options; optional worktree cleanup; selecting merge MUST load merge-discipline Parts A→B→C→R→D; keep/continue MUST NOT trigger merge gates. Open/update PR delegates to delivery-discipline. Triggers — 「分支收尾」「feature 收尾菜单」「合入或保留分支」「branch closeout」 / feature branch closeout, post-verify branch menu. Do NOT use as a name alias for finishing-a-development-branch.
Runs a pre-handoff QA checklist on a Figma design before it goes to engineering. Use when asked to QA a Figma design, do a pre-handoff check, or validate a Figma file is ready to build. Produces a structured QA report covering file hygiene, component usage, accessibility, and handoff readiness with explicit pass/fail status per item. Optimised for Opus 4.7 and newer models.
Translate Figma design properties and structures into IDS (Iress Design System) component implementations. Use when the user provides Figma designs, mentions Figma MCP, asks to convert a design to code, or references Figma component names, variants, or auto-layout properties.
Audit Figma MCP, design-to-code, code-to-canvas, canvas-editing, and design-system workflows for correctness, freshness, privacy, evidence, and routing quality. Use this skill when the user asks whether a Figma workflow, skill, task plan, MCP capability claim, or agent handoff is valid, current, safe, or production-ready.
Use when the user wants to find plugins for DeepSeek Harness: "Is there a plugin that can…", "help me install XX", "what's fun in the ecosystem". Discover public repositories across individuals and organizations from the dsh-plugin topic on all of GitHub, filter candidates, wait for the user to decide, first report what permissions the plugin requires, then determine the installation method from the repository declaration and verify mounting. Only handles finding and installing; for developing new plugins, switch to make-dsh-plugin.
FMC finish-work workflow: run bun run check, fix failures, commit with a user-facing English message by default, and only show a draft when the user clearly did not want a commit. Use for finish work, run checks, wrap up, land changes, or create commits.
When the user is looking for low-cost leverage alternatives, or analysing the financial advantages of a "collect first, provide the service later" business model. Language signals: "is there a low-cost source of funds" / "what are the benefits of a prepayment model" / "the business model of insurance companies" / "how to invest with other people's money" Not applicable to: pure operating decisions that require no financing/leverage analysis.
Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adaptation. Capabilities: text-to-image, image-to-image, LoRA fine-tuning, custom styles. Triggers: flux, flux.2, flux dev, flux schnell, flux pro, black forest labs, flux image, flux ai, flux model, flux lora
Turn raw footage into polished, share-ready clips without downloading a single app. This free-video-trimmer-online skill lets you cut unwanted sections, isolate the best moments, and export clean video segments directly from your browser. Supports mp4, mov, avi, webm, and mkv formats. Perfect for content creators, students, and social media users who need fast, no-cost trimming without watermarks or paywalls.
Access and interact with my FreshRSS instance via python scripts. Use for any RSS-related question, including reading articles, searching past content, finding feeds, getting recommendations, managing subscriptions, checking unread counts, marking read/star, or exploring what I follow. Triggers on keywords: RSS, FreshRSS, feed, unread, headlines, articles, subscriptions, starred.
Create distinctive, production-grade, high-quality frontend interfaces. Use this skill when the user asks to build web components, pages, works, posters, or applications (for example websites, landing pages, dashboards, React components, HTML/CSS layouts, or styling any web UI). Generate creative, polished code and UI design, avoiding generic AI aesthetics.
Google Analytics 4, Search Console, and Indexing API toolkit. Analyze website traffic, page performance, user demographics, real-time visitors, search queries, and SEO metrics. Use when the user asks to: check site traffic, analyze page views, see traffic sources, view user demographics, get real-time visitor data, check search console queries, analyze SEO performance, request URL re-indexing, inspect index status, compare date ranges, check bounce rates, view conversion data, or get e-commerce revenue. Requires a Google Cloud service account with GA4 and Search Console access.
Audit a game, feature, failure loop, combat encounter, reward system, progression wall, or high-variance mechanic for perceived fairness and frustration. Use when diagnosing whether players feel cheated, whether difficulty feels deserved, whether randomness, feedback, and challenge interact badly, or why a design remains technically functional yet still produces anger, blame, or refusal to retry
Review and design game economy systems for mobile, PC, casual, live-service, and app-like games including currencies, sources/sinks, progression, rewards, daily check-ins, battle passes, IAP, ads, events, refunds, anti-abuse, fairness, and live-ops measurement. Use when building or auditing monetization and retention loops in games.
Comprehensive GameMaker Studio 2 and GML expertise covering beginner to advanced topics. Provides guidance on object creation, GML syntax, event systems, data structures, file I/O, shaders, networking, platform-specific features, performance optimization, and debugging. Automatically invoked when working with .gml files, .yy files, .yyp projects, or GameMaker-related tasks. References official manual (manual.gamemaker.io) for authoritative documentation.
Extract answer keys from Chinese Gaozhong-style English exam papers (PDF or image) and format them into a standardized structured output. Trigger when the user sends an English exam paper, answer key, mock test answer sheet, or similar file and asks to extract, organize, or structure the answers. Trigger even for casual requests like "look at the answers", "extract answers", or "organize this".
GCSE Physics tutor and revision assistant for 15–16 year old students preparing for 2026 exams across AQA, Edexcel, OCR, and WJEC boards. Use when a student asks for help understanding physics topics, answering exam questions, revising for GCSEs, practising required practicals, solving calculation questions, or wants guidance on exam technique for GCSE Physics.
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.