Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture support, and tech stack customization. Use when setting up new projects, improving existing CLAUDE.md files, or establishing AI-assisted development standards.
This skill should be used to summarize coaching or therapy session transcripts after a Fathom/Granola sync. The agent analyzes the transcript itself (no API key, runs on the subscription) and appends key insights, decisions, action items, and trail connections. Supports quick extraction or deep analysis with cross-session pattern detection.
A cognitive-science-based assistant for deep understanding of source code (improved Chinese edition). Supports three analysis modes: Quick (fast overview), Standard (standard understanding), and Deep (deep mastery, with automatic parallel processing for large projects). Combines elaborative interrogation, self-explanation tests, and retrieval practice to help you truly understand and master code.
Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback on their code.
Assist with Colibri: pure-C LLM inference engine for running GLM-5.2 (744B MoE) on consumer machines with ~25 GB RAM. Use when setting up, building, converting models, running inference, configuring expert streaming and caching, optimizing speculative decoding (MTP), GPU integration, and integrating Colibri into production pipelines. Includes build setup, model download & conversion, chat/inference modes, performance tuning, and API integration patterns.
Use when the user asks to "analyze competitors" or "竞品分析"; benchmarks competitor keywords, content, backlinks, AI citations, and traffic share into strengths, weaknesses, and an action plan. Not for a pairwise topic-coverage gap map—use content-gap-analysis. 竞品分析/竞争对手
Use this skill to map a competitor's organic search footprint with Keywords Everywhere ranking keywords, traffic estimates, and content-theme clusters. Trigger it when comparing SEO visibility, identifying competitor keyword strengths, or preparing deeper content-gap analysis.
Use this skill to attach a USB device or emulator to ADB, list transports with `adb devices` / `adb devices -l`, disambiguate among multiple devices using `-s SERIAL`, `-d` (single USB), `-e` (single TCP/IP), or `-t TRANSPORT_ID`, gate scripts on a transport with the canonical `adb wait-for[-TRANSPORT]-<state>` syntax (TRANSPORT in {usb, local, any}; state in {device, recovery, rescue, sideload, bootloader, disconnect}), interpret device states (`device`, `offline`, `unauthorized`, `no permissions`, `recovery`, `sideload`, `bootloader`, `rescue`), accept the RSA fingerprint dialog on first connect, and install Linux udev rules. Use when the user mentions `error: more than one device/emulator`, `error: device not found`, `unauthorized`, `no permissions`, `daemon not running`, "wait for device to boot", `wait-for-device-online` (which is not a real subcommand), or asks how to script around emulator startup.
Generates a fully structured SEO content brief for a target keyword and optionally pushes it to a Notion database. Use this skill whenever the user says 'create a content brief', 'brief this keyword', 'run a content brief for', 'generate a brief', 'write a brief for [keyword]', 'content brief on [topic]', or any variation where someone needs a keyword researched and turned into a structured writing assignment with H1, H2 outline, FAQ, internal links, word count target, and writer notes. Also triggers when the user provides a keyword and asks for an SEO brief, editorial brief, or writing spec. Outputs a mandatory structured format that the text parser maps directly to Notion properties. Supports single-keyword and batch (CSV) modes.
Use when the user needs marketing copy, social media content, brand voice development, ad copy, newsletters, or persuasive writing for business audiences. Trigger conditions: social media post drafting, email campaign copy, landing page text, ad copy creation, brand voice definition, content calendar planning, headline writing, A/B test copy variations, newsletter composition.
Design help systems and support patterns that work for people with cognitive disabilities. Use when designing help content, tooltips, onboarding, FAQs, support flows, documentation, or any context where users need guidance. Triggers on: help, support, FAQ, tooltip, onboarding, tutorial, guidance, stuck, confused, documentation, instructions.
Use this skill when the user asks to create, scaffold, update, or review a MoviePilot agent skill. This includes adding a new built-in skill under the repository `skills/` directory, editing an existing built-in skill, writing `SKILL.md` frontmatter and workflow instructions, choosing `allowed-tools`, adding helper scripts when needed, and bumping the built-in skill `version` so changes can sync into `config/agent/skills`.
Use when creating or maintaining a verification skill for a specific app or scenario; not for writing only a test plan, one-time acceptance testing, or read-only consultation. Generates scoped, executable verify-* workflows that validate real entry points and save evidence for reuse by agi-mode.
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".
Use CryptPad encrypted collaboration for integration, automation, and diagnosis with its browser integration API, instance discovery, document import/export, and session-key lifecycle. Use for CryptPad API feasibility, embedded editors, sharing, persistence, or self-hosted instance troubleshooting. Do not use for EncryptPad/OpenPGP, generic office-file conversion, or designing an unrelated collaboration service.
Design customer service operations including tiered support (L1/L2/L3), response templates, SLA definitions, escalation procedures, and complaint handling. Use this skill when the user needs to set up a CS team, create service standards, design escalation flows, or improve response quality — even if they say 'our CS is a mess', 'how should we handle complaints', 'set up support tiers', or 'create CS SOPs'.
Use when the user needs to turn DOCX, PDF, TXT, XLSX, research reports, business materials, or raw data into high-density, editable, consulting-style PPTX; also suitable for PPTs that require SCR argumentation, visual style exploration, detailed charts, and rendering quality checks.
This skill MUST be used when planning or executing an end-to-end data analysis or when explicitly asked for 資料分析流程、分析規劃、分析報告產出. It SHOULD guide methodological choices in multi-step analysis, including descriptive analysis, inference, prediction, or clustering. It MUST NOT force modeling into descriptive work or expand a single metric query into a full workflow.
DDEV local development environment for Craft CMS projects. ALWAYS load this skill when running any ddev command, configuring .ddev/config.yaml, or troubleshooting local container issues. Covers config.yaml (project type, PHP/Node versions, database, docroot), shorthand commands, add-ons and built-in Mailpit, custom commands, Vite dev server exposure, database import/export, Xdebug toggling, sharing local sites, and troubleshooting (port conflicts, container restarts, ddev-injected env vars silently overriding your .env or config/general.php).
Strip AI-generated slop from a codebase, product, and prose. Code slop — console statements, `any` types, unused imports, commented-out code, redundant comments, needless defensive try-catch on trusted paths, over-nesting. Product slop (with --product) — marketing-filler copy, generic AI phrasing, default-shadcn look, unstyled loading/error states, dead buttons and half-wired flows. UI slop (`ui`) runs a project-derived design-system primitive pass. Prose slop (`prose`) cuts AI tells from writing. Can scope to the current branch's diff or sweep the whole tree. Use when asked to clean up AI-generated code, unslop writing, remove slop, or make an app feel finished before shipping to customers.
Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs via autonomous reproduce-analyze loops, with human help only as a fallback. Only for hard-to-diagnose bugs; in those cases, remind the user that debug-mode is available, and never proactively activate this skill
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribeUrl` / `transcribeFile` (REST) plus `client.listen.v1.createConnection()` / `connect()` (WebSocket). Use `deepgram-js-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-js-conversational-stt` for Flux turn-taking on `/v2/listen`, and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen.v1", "nova-3", "live transcription", and "websocket transcription".
Guidance for Microsoft Defender for Cloud — cloud security posture management (CSPM) and cloud workload protection (CWPP) across Azure, AWS, and GCP. Covers Foundational vs Defender CSPM, Secure Score, Defender plans (Servers, Storage, Containers, Databases, App Service, Key Vault, APIs, AI), agentless scanning, attack path analysis, and remediation prioritisation. WHEN: Defender for Cloud, CSPM, cloud workload protection, Secure Score, harden cloud posture, Defender plans, attack path analysis, multicloud security, remediate recommendations, cloud security hardening, improve Azure Secure Score, harden Azure subscription, protect VMs and containers, multicloud CSPM across AWS and GCP, cloud security graph. DO NOT USE for SaaS posture (use cloud-app-security-posture), Sentinel SIEM (use sentinel), or extending Azure to on-prem servers (use azure-arc).
Check dependencies for known vulnerabilities using npm audit, pip-audit, etc. Use when package.json or requirements.txt changes, or before deployments. Alerts on vulnerable dependencies. Triggers on dependency file changes, deployment prep, security mentions.
Use Desktop Commander MCP (typically tools like `mcp__desktop-commander__*`) for local files, precise edits, search, and long-running processes on the machine. Use it when the task requires direct local execution, rather than IDE-only actions or remote platform operations.
Integrate DFlow Proof — a Solana wallet identity-verification primitive (Stripe Identity under the hood) — to gate your own app's features behind KYC. Use when the user asks "how do I KYC a wallet?", "check if a wallet is verified", "add KYC to my DeFi app", "redirect to dflow.net/proof", or "gate a feature by jurisdiction or identity". Do NOT use for geoblocking (separate concern), for age gating (Proof doesn't currently verify age), or for spot swaps (no KYC required).
A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet", "creator guide", "playbook", "PDF guide", or "电子指南".
Use when a task has multiple independent subtasks that can be executed concurrently by separate agents. Triggers when decomposed work has 2+ subtasks with no data dependencies, when subtasks operate on different files or codebase sections, when serial execution time would be significantly longer than parallel, or when independent analyses or deliverables need concurrent generation.
Creates a Technical Specification from an existing PRD: deep project analysis, technical research (documentation MCP when available, otherwise Web Search), clarifying questions, then the architecture and implementation guidance. Use to create a tech spec or define architecture for a feature with a PRD. Not for PRDs, task breakdowns or code implementation.
Use when user wants to manage Docmost documentation via docmost-cli: pages, spaces, workspace, members, groups, invites, comments, shares, files, search, and export/import. Trigger on requests about wiki/docs pages, knowledge base, page history/trash, page organization, access control, public sharing, file attachments, and workspace administration from terminal.
Look up CE.SDK SvelteKit reference docs, guides, and configuration pages. Use when the user needs CE.SDK docs for SvelteKit — configuration, UI customization, export options, feature guides, or getting-started instructions. Also triggered by "IMG.LY", "CreativeEditor", "CE.SDK", or "cesdk" when the user needs an existing SvelteKit doc page. Not for writing code (use build) or concept explanations (use explain). <example> Context: User asks about SvelteKit configuration user: "How do I configure the editor in SvelteKit?" assistant: "I'll use /imgly-sdk:docs-sveltekit to look up configuration options." </example> <example> Context: User asks about SvelteKit SSR user: "Does CE.SDK work with SvelteKit server-side rendering?" assistant: "Let me use /imgly-sdk:docs-sveltekit to find the relevant documentation." </example>
The Douyin traffic allocation dashboard is for content creators, operations, e-commerce, and marketing teams who want to know where Douyin traffic is flowing; it generates traffic distribution, category hierarchies, and platform direction signals usable for content planning based on the input material.
Digital signal processing algorithms and techniques for real-time audio. Covers filter design (biquad, Moog ladder, SVF, FIR, Linkwitz-Riley), audio effects (delay, reverb, dynamics, modulation, distortion, stereo processing), sound synthesis (oscillators, bandlimited waveforms, FM/PM, noise generation, envelopes), spectral analysis (FFT, envelope detection, beat detection), and DSP utilities (fast math, interpolation, denormal prevention, dithering). Use this skill whenever implementing audio DSP in C/C++, building synthesizers or effects, writing filter code, generating waveforms, or any task involving digital audio processing — even if the user doesn't explicitly mention "DSP."
Create visual concepts, image-generation prompts, and optional AI-generated images for product hero images, marketing creatives, social posts, ads, ecommerce PDP visuals, and general visual design tasks. Use when the user asks for visual strategy, image prompt writing, product/marketing image direction, or direct text-to-image generation. In Codex environments use the built-in imagegen tool; elsewhere use the bundled script backed by the apiz CLI.
Generate code for EDC export validation, clinical data range checks, cross-form consistency checks, SDTM structure validation, controlled terminology verification, and define.xml generation. Use when the user asks to validate clinical trial data exports, check vital sign or lab value ranges, verify AE date consistency, validate SDTM datasets against CDISC rules, generate define.xml, or build an automated data review pipeline. Triggers include "EDC validation", "range check clinical data", "cross-form consistency", "SDTM validation", "controlled terminology check", "define.xml generation", "Medidata Rave export", "Oracle InForm", "Veeva Vault CDMS", "clinical data cleaning", "edit check", "data query", "SDTM structure check", "lab range check", "vital signs validation", "AE date check", "protocol deviation detection", "OpenCDISC", "Pinnacles 21", "P21 validation".
Identify and design for edge cases that disproportionately affect users with disabilities. Use when reviewing designs for completeness, planning test cases, or when someone says 'that's an edge case.' Triggers on: edge case, corner case, that's unlikely, only a few users, exception, unusual scenario, we'll handle that later, happy path, unhappy path, error state, empty state.
Parse and extract clinical data from HL7v2 messages and FHIR R4 resources using Python. Use when the user mentions HL7v2, HL7, FHIR, PID segment, OBX segment, MSH segment, Patient resource, Observation resource, Condition resource, MedicationRequest, EHR data extraction, clinical message parsing, FHIR bundle, HL7 to FHIR conversion, ADT message, ORU message, lab result extraction, or clinical data quality checks. Triggers include "parse HL7", "extract FHIR", "HL7v2 message", "FHIR resource", "PID segment", "OBX segment", "Patient resource", "Observation resource", "EHR parsing", "clinical data extraction", "HL7 to CSV", "FHIR to DataFrame".
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.