Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Read-only exposure audit of the user's MacBook (and ~/Documents/code projects) for a CVE, breach, malicious package, or other security advisory, then write a structured report to ~/Documents/security-audits/. Use when the user shares a breach/CVE/malware/supply-chain advisory and asks if they're affected, says "scan my system for X", "are we affected by Y", "check if I'm vulnerable to Z", or requests any hack/breach/cyber/vulnerability audit on this MacBook. Output matches the existing audit format in ~/Documents/security-audits/.
Automatically summarizes the day's top stories from multiple news sites, using browser automation to visit and read news content. Use for tasks such as when the user asks to "summarize today's news", "get today's headlines", or "generate a news summary", or asks questions like "what's important in the news today?" or "show me today's headlines on news sites". Supports Chinese news sites (Sina, NetEase, Tencent, etc.) and international news sites (BBC, Reuters, etc.), and produces a detailed Markdown-format summary report.
Use DBML as the standard format for database schema documentation. Apply this whenever creating, updating, reviewing, or repairing database docs, ERDs, schema diagrams, table inventories, migration summaries, Doctrine migration changes, SQL schema docs, ORM model docs, or CI schema drift failures. Prefer db/schema.dbml over Mermaid, Prisma schema, ad hoc Markdown tables, or prose-only database documentation unless the user explicitly requests another format.
Performs discounted cash flow (DCF) valuation analysis to estimate intrinsic value per share. Triggers when user asks for fair value, intrinsic value, DCF, valuation, "what is X worth", price target, undervalued/overvalued analysis, or wants to compare current price to fundamental value.
Cuts a full multi-persona demo down to only the screens relevant to one specific buyer in a deal (admin console, end-user experience, analytics and reporting, whatever applies) by transcribing the demo's structure, confirming with the user exactly which sections this persona cares about, duplicating the project to keep the full demo intact, then removing the irrelevant sections at clean boundaries and checking that transitions still read naturally. This is subtraction, not reframing: no new narration is written beyond trimming a seam. Use when the user says "cut this demo down to just the admin screens", "trim this to only what this buyer cares about", "remove the parts of this demo not relevant to this persona", or "make a shorter version of this demo for this buyer that skips a section".
Guidance for Docker storage and data persistence. Covers storage types (Volume/Bind Mount/Tmpfs) with comparison and use-case selection, volume lifecycle management (create/ls/inspect/prune), bind mount patterns, tmpfs for ephemeral data, backup and restore strategies, storage driver selection (overlay2), database persistence best practices (PostgreSQL/MySQL/Redis), and NFS/cloud storage integration. Use when the user asks about docker volume, data persistence, bind mount, tmpfs, storage driver, backup, data volume, or needs persistent storage for containers. 使用场景:docker volume、数据持久化、bind mount、tmpfs、存储驱动、数据卷、备份恢复、数据库持久化.
Upload local documents to TianGong AI Unstructure `/mineru_with_images` API for fine-grained parsing and return only plain fulltext content. Use when a task needs document fulltext extraction with `return_txt=true`, strict file-type allowlist validation, API base URL/auth token from environment variables, and optional provider/model overrides.
Word document beautification and formatting expert. Specifically for converting text content in Word documents into professional table formats, applying consistent styles (dark blue header, zebra-striped data rows, borders), and supporting versioned iterative management. Use this skill when the user needs to beautify Word documents, create professional tables, or incrementally optimize document sections.
Use this skill when the user wants to review, audit, improve, or plan email sending best practices. This includes deliverability, inbox placement, sender reputation, consent, list hygiene, subject lines, preview text, preference centers, onboarding emails, lifecycle emails, product updates, or deciding between marketing and transactional email. It works for any email stack, but when Loops is involved, use Loops behavior and docs as the source of truth. Trigger on phrases like "email deliverability", "inbox placement", "sender reputation", "double opt-in", "unsubscribe", "subject line review", "preview text", "lifecycle emails", "onboarding emails", "product update email", "transactional vs marketing", or "email sending best practices". Do not prefer this skill for pure API implementation; use the Loops API skill for integration details.
Use when creating, modifying, or removing API endpoints on a Datex Studio branch. Covers the full lifecycle: requirements, prerequisite creation (datasources, flows), endpoint wiring, and verification. Trigger for: "create an endpoint", "expose this flow as an API", "add an API for X", "modify endpoint", "remove endpoint", "change endpoint alias", "create an API that does X".
Create professional engineering diagrams using drawio XML format with industry-standard symbols. Best for electrical schematics, P&ID (Piping & Instrumentation), rack diagrams, fault tree analysis, PLC ladder logic, and logic gate diagrams. Built on drawio with engineering-specific stencils. NOT for simple flowcharts (use mermaid) or network topology (use network skill).
Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency, high-risk controls, general-purpose AI obligations, governance, and implementation milestones. Use when an organization needs to triage an AI use case, vendor, model, product, or portfolio for Regulation (EU) 2024/1689; prepare an AI inventory, gap register, implementation roadmap, or counsel briefing; assess provider, deployer, importer, distributor, product-manufacturer, authorised-representative, or GPAI-provider responsibilities; or re-check readiness after regulatory or product changes.
Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.
Generate images and videos with Kling O3 — Kling's most powerful model family. Text-to-image, text-to-video, image-to-video, and video-to-video editing. Use when the user requests "Kling", "Kling O3", "Best quality video", "Kling image", "Kling video editing".
React feature-based architecture guidelines for scalable applications (formerly feature-architecture). This skill should be used when writing, reviewing, or refactoring React code to ensure proper feature organization. Triggers on tasks involving project structure, feature organization, module boundaries, cross-feature imports, data fetching patterns, or component composition.
Fix mispronounced product names, acronyms, and jargon in a video's voiceover by respelling them phonetically and regenerating only the affected lines. Use when the user says "it's pronouncing our product name wrong", "fix the pronunciation of X", "the voiceover says the acronym weirdly", "make it say KYOO-bee not cube", or points at specific words the narration gets wrong.
Use when handling file uploads, attachments, private/public file access, or S3 storage configuration. Prevents broken file URLs, permission leaks on private files, and failed uploads from incorrect MIME handling. Covers File DocType, frappe.get_file, upload API, private vs public directories, S3 integration, file URL patterns, attach field types. Keywords: file, upload, attachment, File DocType, private, public, S3, file_url, get_file, attach, upload not working, file missing, broken file link, download file, image not showing, attachment error.
Use when implementing search functionality in Frappe v14-v16. Covers link field search (search_link), global search, FullTextSearch (Whoosh), SQLiteSearch FTS5 [v15+], Awesomebar customization, search_fields configuration, custom search queries, and website search. Prevents common mistakes with missing search_fields and permission filtering. Keywords: search, search_link, global_search, FullTextSearch, Awesomebar, search not finding, link field empty, autocomplete not working, global search missing results, search_fields, standard_queries, SQLiteSearch, FTS5, Whoosh.
Use when creating or modifying Frappe Workflows, defining states and transitions, adding action conditions, or troubleshooting workflow permission errors. Prevents stuck documents from misconfigured transitions, missing state permissions, and circular workflow paths. Covers Workflow DocType, workflow states, transitions, actions, conditions (Python expressions), workflow permissions, workflow_state field, Workflow Action DocType. Keywords: workflow, states, transitions, actions, conditions, workflow_state, Workflow Action, approval, document workflow, approval process, document stuck, cannot change status, workflow not moving, who can approve.
Use when debugging or handling permission errors in Frappe/ERPNext. Prevents broken document access from throwing in permission hooks. Covers PermissionError (403), has_permission hook failures, User Permission restricting too much or too little, perm_level blocking field access, System Manager bypass not working, Guest access denied, sharing permissions not applying, permission_query_conditions breaking get_list, owner-based permissions confusion, Apply User Permission checkbox behavior, and the permission debug workflow using frappe.permissions.get_doc_permissions. Keywords: PermissionError, has_permission, permission_query_conditions, permission denied, cannot access, user blocked, sharing not working, role not enough, User Permission, perm_level, sharing, guest access, owner permission.
Use when running bench commands, managing sites, configuring multi-tenancy, or setting up domains. Prevents misconfigured bench environments, broken site routing, and DNS mismatches. Covers bench CLI commands, site creation, bench init, multi-tenancy setup, DNS-based routing, common-site-config. Keywords: bench, site, multi-tenancy, domains, bench init, bench new-site, bench setup, common_site_config, bench command not working, site setup, multi-tenant, domain routing, new site.
Use when Codex is building, revising, or reviewing a frontend UI, web app screen, responsive layout, component surface, dashboard view, form flow, visual system, or no-template product interface that needs visual polish, accessibility, screenshots, or browser QA.
Unusual Capital Flows (资金异动): detects unusual capital-flow signals for a user-mentioned stock with `get_financial_unusual`, including 资金分布、买卖经纪商、资金流向、卖空数量、卖空比例 and their unusual changes. Use when the user asks about 资金动向、资金异动、净流入、净流出、主力行为、大单小单、谁在买谁在卖、买卖经纪商、卖空异动、卖空/做空/沽空、主力是否在进场或离场,or gives a broad 异动 request such as “英伟达异动”、“NVDA 异动”、“腾讯有没有异动/异常” without narrowing the dimension. For broad 异动 requests, use together with `futu-unusual-technical-signal-alerts` and `futu-unusual-derivatives-activity`. Before calling the CLI, first normalize the user-mentioned stock name, Chinese company name, English company name, or ticker into a standard symbol such as `US.TSLA` or `HK.00700`.
L2 flash swap orchestration: fc preview and create (1:1, 1:N, N:1), spot balance checks, min/max gates, optional dust-to-GT, order history. Use this skill whenever the user wants flash swap, instant convert, consolidate alts to one coin, split one asset into several via flash, diagnose below-minimum flash size, or convert wallet dust to GT. Trigger phrases include "flash swap", "flash convert", "swap to USDT", "consolidate to USDT", "dust to GT", "small balance to GT", or "flash swap history".
Agent simulation and GEO simulation prompt generation for AI visibility auditing. Use when the user wants to create simulation tasks via the TPC CLI, generate unbranded GEO prompts to test whether AI recommends a product, or run agent simulations.
Manage project milestones including create, list, update, view, and close operations. Use when planning releases, tracking milestone progress, or organizing issues/MRs by milestone. Triggers on milestone, release planning, milestone progress, version milestone.
11 GTM plays with detailed execution - New Team Members, Skills-Targeting, Role-Targeting, Industry Research, Resources for ICs, Leaving Employees, No Dedicated Role, Bad Reviews, AI Ideas, ServiceBell Allbound, Inbound Followers. Use when building outbound campaigns, creating signal-based plays, or expanding your GTM playbook.
Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model
Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audit skills/rules, instruction audit, redundancy of agent instructions, usefulness of skills, Ship/Review/Hold/Slim/Keep-core for harness, or wants Track A/B/C harness evaluation. Do NOT use for harness setup or init, feature spec-driven work (tlc-spec-driven), or applying Ship/Slim trims unless the user explicitly asks after the report.
Canonical guide to authoring Claude Code hooks, both prompt-based and command-based. PROACTIVELY activate for: (1) creating a hook, (2) adding PreToolUse or PostToolUse hooks, (3) validating tool use, (4) implementing prompt-based hooks, (5) blocking dangerous commands, (6) event-driven automation, (7) configuring hooks.json, (8) using ${CLAUDE_PLUGIN_ROOT}, (9) hook matchers and filtering, (10) debugging hooks that do not fire. Provides: hooks.json schema, event reference, security guidance, and examples.
Run the full Lean Offer System from idea to sellable offer to pitch in one flow. Use when you have an idea but no offer, an offer that doesn't sell, or need speed and clarity. Covers market, offer creation, value optimization, pricing, positioning, hooks, pitch, and sales structure — outputs LEAN_OFFER_SYSTEM.md.
Turns any request for an AI-generated image into precise, generation-ready prompt specs and — when the FAL.ai automation is configured — the generated files themselves, using the single model fal-ai/nano-banana-pro. Use whenever the user asks to 'generate an image', 'make a picture of X', 'create a thumbnail / hero image / illustration / infographic', 'write me a prompt for this image', or any visual that isn't specifically product photography, a social-platform graphic, or a brand mark (hand those to the sibling skills). Produces one prompt-spec block per asset (subject, style, composition, lighting, mood, aspect ratio, negative constraints) plus file-naming and variant conventions, and runs docs/creative_cli.py to generate when a FAL_API_KEY is available.
Cross-LLM peer review of an implemented change (the diff) via `compozy exec`: an independent reviewer runtime pressure-tests the diff and writes one scoped Markdown findings artifact for user-directed remediation. Project-agnostic — any repo or language; auto-discovers project rule files and the verify command. Use after an implementation pass (feature, bug fix, refactor) when the user explicitly asks for an external review of the diff before commit or PR. Do not use for spec/TechSpec review — use spec-peer-review.
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.
