Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build Convex schemas, queries, mutations, actions, and client usage with strict validators and indexes. Use for data modeling, function authoring, argument/return validation, and performance guidance. Use proactively when work touches convex/schema.ts, functions, or api.* references. Examples: - user: "Design tables for multi-tenant app" → defineSchema/defineTable with indexes - user: "Write a mutation" → args/returns validators + auth checks - user: "Optimize query" → add index and withIndex range expression - user: "Use useQuery" → show generated hook usage
Use when the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. For writing new copy, see copywriting.
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies
Autonomous agent commerce — buy gift cards, top up phones, get eSIMs with USDC on Base or USDC SPL on Solana mainnet via x402 protocol. No account, no OAuth, no API key. No native gas needed (ETH on Base relayed by Cryptorefills; SOL on Solana paid by CDP facilitator). For AI agents with Base or Solana wallets. 10,500+ brands, 180+ countries. Keywords: x402, USDC, USDC SPL, Base, Solana, mainnet-beta, partial-sign, EIP-712, EIP-3009, TransferChecked, compute-budget, VersionedTransaction, pay-skills.
Use when implementing SDK code hooks for custom logic (not spec configuration or runtime overrides). Covers SDK lifecycle hooks: BeforeRequest, AfterSuccess, AfterError for custom headers, telemetry, HMAC signing, and request/response transformation. Triggers on "SDK hooks", "add hooks", "BeforeRequestHook", "custom logic in SDK", "telemetry hook", "SDK middleware", "intercept requests", "HMAC signing hook", "custom code in hooks directory".
Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that the cw-prose-writing skill can follow. Creates either simple markdown files or full .skill packages. Audience is AI (Claude), format is directive and example-based.
Refactor code to reduce cyclomatic complexity so it stays readable, maintainable, and aligned with the long-term vision of the codebase, not just optimized for AI comprehension. Use whenever the user asks to refactor, simplify, clean up, or review code quality; mentions complexity, maintainability, readability, spaghetti code, deeply nested logic, or god functions; or asks to check AI-generated code before merging. Also use proactively after writing any nontrivial function with heavy branching.
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after completing Steps 1-3.
DAX performance optimization for semantic models. Automatically invoke when the user asks to “optimize DAX,” “fix slow DAX,” “DAX performance,” “tune a measure,” “debug a measure,” “DAX anti-patterns,” or mentions slow queries, server timings, or DAX authoring.
Diagnose and fix failures in a built third-party `.ppmplugin` control: crashes, silent no-ops, PCF error outputs, or incorrect behavior. Uses the reported symptom, `shared/error-codes.md`, and file-level evidence to trace the manifest, Android/iOS modules, PCF dispatch, and build configuration. Produces a ranked diagnosis, asks for approval, then applies a surgical fix while keeping the committed manifest and affected contracts synchronized. Re-validates manifest changes through /generate-ppmplugin-manifest.
Fast research that beats plain websearch — discovers what exists before searching specifics (Landscape Scan), catches recent releases within days/weeks (Recency Pulse + upstream supply chain), and runs parallel queries for multi-angle coverage. Good for everyday research and current-info questions. Use when user requests research, comparison, or "what's the latest on X". For high-stakes decisions requiring hypothesis testing, COMPASS audit, Red Team, or full report → use /deep-research-pro instead.
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.
Capture a 2-3 line pitch from the user, draft a product overview (PRD.md) and a technical design (ARCHITECTURE.md) for a third-party `.ppmplugin` native control, then walk through every operation's iOS + Android implementation strategy with opinionated recommendations (library choice, hosting, key APIs, edge cases) and capture the agreed spec in ARCHITECTURE.md §3.<n>. The depth of ARCHITECTURE.md is what lets the scaffold skill generate complete working code instead of TODO placeholders. Iterates with the user until they approve both docs. Optionally seeds from a design doc / FRD URL. PRD.md + ARCHITECTURE.md are the source of truth for every downstream skill (generate, build, assemble). Run this BEFORE any code is generated.
Keeping a design system in an LLM's context: loading tokens compactly, persisting design decisions across sessions, handling multiple variants, and budgeting the context window. Use when generated UI drifts from the design system, or when setting up tokens and decisions so every session and agent uses the same ones.
Use for design thinking, or when a product or service problem needs user understanding before solutions: "what do users really need?", "how might we...", "plan a discovery sprint", "validate this concept". Skip when the spec is frozen or the task is code maintenance.
Swap any pair of Solana tokens via DFlow. Use when the user wants to trade, swap, or convert tokens on Solana, get a price quote, build a swap UI, tune priority fees so a swap lands under congestion, build a gasless / sponsored swap where the app pays fees, or take a builder platform fee on swaps. Covers both the `dflow` CLI and the DFlow Trading API. For live prices / streaming order book / depth, use `dflow-market-data` instead.
Book rides, check prices, query orders, cancel orders, plan routes (driving/transit/walking/cycling), and search places via the DiDi MCP. Use when the user mentions 滴滴, 打车, 叫车, 回家/上班要打车, 查一下从 A 到 B 多少钱/怎么走, 查询订单, 司机在哪/多久到, 预约叫车, 路线规划, DiDi, ride-hailing, or booking a taxi.
Build and review HTMX interactions in Django server-rendered projects, especially generated django-saas-starter apps. Use when adding hx attributes, partial template responses, request.htmx branching, django-htmx response headers, forms, swaps, triggers, redirects, polling, boosted links or forms, or coordinating HTMX with Alpine.js local state.
Look up CE.SDK Angular reference docs, guides, and configuration pages. Use when the user needs CE.SDK docs for Angular — 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 Angular doc page. Not for writing code (use build) or concept explanations (use explain). <example> Context: User asks about Angular configuration user: "How do I configure the editor in Angular?" assistant: "I'll use /imgly-sdk:docs-angular to look up configuration options." </example> <example> Context: User needs Angular integration user: "How do I use CE.SDK in an Angular component?" assistant: "Let me use /imgly-sdk:docs-angular to find the relevant documentation." </example>
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, deletes small UI and purely mechanical records, classifies other implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.
Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought, and save/load. Use this when starting any new DSPy project or when fixing non-idiomatic DSPy code (hard-coded prompts, ad-hoc string templates, untyped outputs, non-serializable classes).
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions “email sequence,” “drip campaign,” “nurture sequence,” “onboarding emails,” “welcome sequence,” “re-engagement emails,” “email automation,” “lifecycle emails,” “trigger-based emails,” “email funnel,” “email workflow,” “what emails should I send,” “welcome series,” or “email cadence.” Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding-cro.
Discover, compare, and deploy pre-built Ludus cyber range environments for security training, attack simulation, and detection engineering. Use when users ask to choose a lab, verify prerequisites, or deploy known environments such as GOAD, SCCM, Elastic, or Vulhub.
Design error prevention, error messages, and recovery flows for cognitive accessibility. Use when designing forms, checkout flows, account creation, settings, data entry, or any flow where users can make mistakes. Triggers on: error handling, error messages, form errors, validation, users make mistakes, users abandon, error recovery, undo, forgiving design.
The Eva Positioning 2.5.0 entry point for stage-based account positioning. Use it when the user explicitly invokes /eva-positioning, or explicitly asks for self-media account positioning, niche positioning, positioning review, positioning changes, judging an account's main line, or organising a profile around account positioning — finding directions worth investigating from real experience, then forming a positioning that can currently run based on the platform reality the user provides. Supports quick positioning and deep positioning; when there is no qualifying platform evidence, deliver only personal-material directions and customised evidence-gathering tasks, and do not generate positioning candidates. Only when the user explicitly places a topic candidate into the business question of "what the current account positioning or account stage should do first", or arranges a cycle's execution order based on an existing work positioning, does it do the narrow bridging to account topics. Bare "personal branding / account review", general social profile edits, ordinary thinking, generic topic selection, ordinary content calendars, single-content creation, content diagnosis of low-traffic accounts, persona material gathering, product and service gathering, sponsored-post briefs, or third-party account analysis must not be taken over by this entry point.
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
Use when receiving feedback on your work — review findings, user corrections, audit results, external reviewer notes — to triage by authority, adjudicate each point on evidence, integrate without regressions, and close the loop with the source. Evidence flips positions; assertions don't.
This skill should be used when the user asks to "write a chapter", "write prose", "continue the story", "develop a character", "review my chapter", "critique my manuscript", "write a synopsis", "summarize my story", "plan my novel", "outline my book", "check for consistency", or mentions fiction writing, novels, short stories, scenes, or narrative craft.
Set up the Fiddler Everywhere MCP server connection for AI agent tools (Claude Code, GitHub Copilot CLI, GitHub Copilot in VS Code, Cursor, OpenAI Codex CLI). ALWAYS use this skill when Fiddler MCP tools are not available, you cannot see Fiddler tools, get an authentication error connecting to Fiddler, need to configure Fiddler MCP for the first time, or hear "tool not found" errors when trying to use other Fiddler skills. Calls Fiddler's local autoconfigure API to detect existing config and write the correct settings automatically. The only prerequisite is that Fiddler Everywhere is running.
Use only when the user explicitly asks to fix and verify a validated or plausible security vulnerability. Do not use for ordinary bug fixes, correctness or design review findings, general validation, or full PR, commit, branch, patch, or repository scans.
Translate an explicit Figma file, frame, component, or node into production Flutter while preserving the app's design system and verifying rendered parity. Use when the request provides or names a Figma source; use flutter-ui-design instead for art direction without Figma.
Convert Markdown text or Markdown artifacts into professionally formatted .docx files using the formaldoc npm package. Use this skill whenever the user wants to export, download, or save Markdown content as a Word document (.docx), or asks to "generate a docx", "export to Word", "turn this into a Word file", "download as docx", or "save as document". Also trigger when the user has a Markdown artifact and asks for a formatted document version. Always prefer this skill over manual docx generation when Markdown source is available. Available templates: - cn-gov Chinese official document, GB/T 9704 style - cn-general Chinese general-purpose document - cn-academic Chinese academic paper - cn-report Chinese business or work report - en-standard Standard — Times New Roman + Arial - en-business Business — Calibri + Arial, modern - en-academic Academic — APA style, double-spaced - en-legal Legal — Contracts, legal docs
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence. Use for synthesizable HDL, fixed-point arithmetic, handshakes, testbenches, resource tradeoffs, timing closure, and FPGA release or bring-up planning. Do not use for ordinary MCU firmware, generic circuit design, a substitute vendor-tool manual, or unsupported claims of hardware or timing signoff.
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.