Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Move money between an Alpaca brokerage account and the EXTERNAL banking world via the Broker API — ACH relationships, wire recipient banks, classic transfers (deposits/withdrawals), the v1beta funding wallet (international/instant), transfer status lifecycles, and fees. Use when building deposit/withdrawal flows or connecting external bank accounts on Alpaca in any language. For moving cash/shares BETWEEN accounts inside your own omnibus, use journals instead.
Reconcile Amazon's 1099-K against actual deposits, fees, and refunds for tax filing. Explains the gap between gross sales on the 1099-K and what hit the bank, maps the numbers to Schedule C lines, and produces the worksheet the seller or their CPA needs. Use when a user asks about 1099-K, Amazon tax documents, reconciling gross vs net sales, year-end tax prep, or why the 1099-K is higher than their deposits. Trigger phrases: "1099-K", "tax forms", "Amazon tax document", "gross vs net", "Schedule C", "year end". Works with zero tools. the user pastes the 1099-K and Payments summary.
Design a portfolio-level Amazon advertising strategy across Sponsored Products, Sponsored Brands, and Sponsored Display. Sets the TACoS target, splits budget by funnel stage, defines the role of each campaign type, and builds a scaling plan. Use when a user asks how to structure their ad account, allocate ad budget, set ACoS or TACoS targets, decide between SP, SB, and SD, plan a launch vs a scale phase, or fix an ad account that grew without a plan. Trigger phrases: "advertising strategy", "ad budget", "TACoS", "ad portfolio", "SP SB SD", "scale my ads", "ad account structure". Works with zero tools. The user pastes their own ad and sales numbers.
Calculate the full Amazon FBA fee stack and the true net profit and margin for a product, and compare FBA versus FBM on cost. Walks the referral fee, the FBA fulfillment fee by size tier and weight, dimensional weight, monthly and Q4 storage, long-term storage risk, inbound shipping, removal fees, and the optional cost lines, then returns net profit, net margin, and break-even ACoS. Use when a user asks to calculate FBA fees, profit per unit, net margin, break-even, whether a product is profitable, fulfillment cost, shipping cost, dimensional weight, storage fees, inbound shipping, removal fees, or to compare FBA versus FBM. Trigger phrases: "FBA calculator", "FBA fees", "profit per unit", "net margin", "break-even", "is this profitable", "shipping calculator", "fulfillment cost", "FBA vs FBM", "dimensional weight", "storage fees", "inbound shipping", "removal fees". Works with zero tools. The user provides price, cost, dimensions, weight, and rates.
Build or audit Amazon Sponsored Products campaigns, and layer dayparting on mature accounts. Mode A builds a campaign structure from scratch with keyword groups, match types, and starting bids from product margins. Mode B audits existing campaigns from a search term report and returns bid changes, negatives, and a graduation plan. An advanced dayparting appendix schedules bids and budgets by hour and day for accounts with enough data. Use when a user asks to build PPC campaigns, structure Sponsored Products, set ad bids, audit a campaign, fix ACoS, plan an auto and exact campaign structure, or dayparting, bid scheduling, ad scheduling by time of day, peak shopping hours, or wasted ad spend at low hours. Trigger phrases. "PPC campaign", "sponsored products", "campaign structure", "set bids", "audit my ads", "fix my ACoS", "auto and exact campaigns", "dayparting", "bid scheduling", "ad schedule", "time of day bidding", "peak hours", "budget by hour". Works with zero tools. the user provides margins, keywords, or a search term report.
Runs a 25-point quality control test on a supplier sample before mass production. Catches the defects that turn into 18% return rates and stranded inventory. Produces a back-message to the supplier with specific fixes required before greenlighting the PO. Use when a user mentions Alibaba sample, supplier sample, sample QC, or before mass production. Trigger phrases: "Amazon supplier sample", "Alibaba sample evaluation", "sample QC", "before mass production", "supplier quality test". Works with zero tools.
Prevent Amazon account and listing suspensions, and write a Plan of Action to appeal one. Covers the account health metrics that trigger enforcement, the common suspension reasons, and how to structure a Plan of Action that gets reinstated. Use when a user asks about a suspended account or listing, a deactivated listing, account health, a Plan of Action, an appeal, or reinstatement. Trigger phrases: "suspended", "account suspension", "listing deactivated", "plan of action", "POA", "appeal", "reinstatement", "account health". Works with zero tools.
Use when authoring an API specification — the engineering wire contract of an API surface: operations/endpoints, request + response schemas (fields, types, required/optional, constraints), auth, a complete error model, pagination/rate-limits, versioning, and worked examples. Guides the producer through the METHOD, not the outline: rendering the contract in the project's style (OpenAPI for REST, SDL for GraphQL, proto for RPC), typing every field, enumerating the ERROR CASES (not just the happy path), tracing each operation to a feature-spec behavior, and referencing the data-model rather than redefining it — to a bar where a client can call every operation and a server can implement it from the contract alone. Composes with a separate api-spec template tool and a deep-research capability. Assumes the upstream feature-spec (+ architecture-doc + data-model where present) — never a blank page. Not the persistence data-model, the consumer-facing API reference, the implementation, or reviewing a finished api-spec.
Create React loading, processing, selected, current, focus, and pressed states with the border-beam package's animated edge glow. Use when a card, button, input, tab, option, task panel, or agent surface needs a restrained traveling or breathing beam; includes installation, imports, prop selection, state wiring, reduced motion, accessibility, and performance and layout guardrails.
UX writing and interface copy, from voice and button labels to error messages and empty states. Use when writing or reviewing any user-facing text: button and link labels, form errors, placeholders, settings labels, onboarding flows, notifications, or empty states. Triggers on UX writing, microcopy, interface copy, product copy, copywriting, button labels, link text, error messages, empty states, placeholder text, settings labels, capitalization, title case, sentence case, voice and tone.
Use when spawning `Mesh3d` with `StandardMaterial`, writing a custom `Material` with `AsBindGroup` and a `.wesl` shader, enabling `shadow_maps_enabled` / `contact_shadows_enabled` on lights, adding `ContactShadows` or `ScreenSpaceTransmission` to a `Camera3d`, spawning an `Atmosphere` entity, loading glTF `#Material0/std` sub-assets, or fixing `#import` / `#ifdef` shader errors after the WESL switch in Bevy 0.20.
Gmail Commander bot and digest process control - they run unattended in a private Restate deployment, never as workstation launchd jobs. Where they run, how to check them, what not to start locally. TRIGGERS - bot start, bot stop, bot restart, bot status, gmail bot down
Identify and exploit authentication and session management vulnerabilities in web applications. Broken authentication consistently ranks in the OWASP Top 10 and can lead to account takeover, identity theft, and unauthorized access to sensitive systems.
Work a Rust crate's recorded issue file to green — one finding at a time, disciplined and sequential: for each finding, write the failing regression test first, apply the smallest correct fix, run the full crate's `cargo test` and `cargo clippy -D warnings`, then mark the finding FIXED / Deferred / Not-a-bug in the issue file before moving on. Never marks a finding fixed without its verification pass, never batches findings, and never buries a warning under `#[allow]` or swaps a real fix for a comment — the issue file and crate state stay in sync after every fix. Use only when the user asks to fix findings from an existing crate issue file.
Plan and run one mechanical edit across a whole population of records. Use when reformatting, renaming, retagging or stripping a field across dozens or thousands of issues, rows, files or board items, and whenever a mass edit needs a dry run, a rollback or proof that it did not touch anything else.
When the user wants to build buyer personas, map buying committees, understand their champion and blocker profiles, or figure out who's involved in deals. Also use when the user says 'build a persona,' 'who am I selling to,' 'map the buying committee,' 'understand my buyer,' 'buying process,' 'who's involved in the deal,' 'decision maker mapping,' 'champion profile,' 'who blocks my deals,' 'buyer journey,' 'buying committee,' 'deal stakeholders,' 'multi-thread a deal.' For ICP definition, see sales-context. For competitive positioning by persona, see competitive-intel.
When the user wants to debrief a sales call, analyze a call transcript, extract action items, or review what happened on a prospect call. Trigger phrases: 'debrief this call,' 'analyze my call notes,' 'what happened on that call,' 'review this transcript,' 'I just got off a call,' 'how did my call go,' 'call recap,' 'post-call review,' 'grade this call.' For pre-call planning, see discovery-call. For tracking deal health over time, see pipeline-review. For analyzing patterns across closed deals, see win-loss-analysis.
Generate, modify, and explain Cerbos authorization policies — resource and role policies, derived roles, exported variables, CEL conditions, and `*_test.yaml` suites. Use when writing access control rules from requirements or a spec document (including PDFs), changing what an existing policy allows, when a Cerbos policy fails to compile or a policy test fails, or when policies need to reach a PDP through a Cerbos Hub policy store. Not for standing Hub up itself (`cerbos-hub-setup`), nor for extracting rules out of an existing system (`cerbos-authz-migration`).
This skill should be used at the very start of every session and when the user asks to "check my environment", "run a pre-flight check", "validate setup requirements", "is my system ready", or before any cofounder project initialization. It verifies the working directory, dev tools, git state, and remote configuration.
Two-layer automated testing strategy for Go + React web applications. Covers backend unit/integration tests (Go) and frontend component tests (Vitest). Tests are written in tandem with application code — every handler gets a test file, every interactive component gets a test file. Use this skill whenever the user asks to test, run tests, add tests, or verify the application.
Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or developing content strategy. For deep SEO writing optimization, see the seo-content-writer skill.
Implement Convex authentication and authorization patterns with OIDC providers or Convex Auth. Use for auth provider setup, ctx.auth usage, user identity handling, and auth-aware schema patterns. Use proactively when users mention auth, JWT, Clerk/Auth0/WorkOS, or Convex Auth. Examples: - user: "Add auth to Convex" → choose provider and outline setup - user: "Get current user" → use ctx.auth.getUserIdentity and checks - user: "Service-to-service access" → use shared secret pattern
Author, scaffold, and run coding-agent-driven tests: Markdown case files executed by a coding agent against a live environment (browser, API, DB, logs, cloud, telemetry) with an auditable PASS/FAIL/BLOCKED report. Use when a deterministic test would be premature, brittle, too expensive, or too narrow.
Diagnose and fix failing automated tests. Analyzes failures, inspects DOM, identifies root causes, and applies targeted fixes using framework tools and MCP/CLI debug modes. Use when tests fail, are flaky, or behave inconsistently (e.g., pass locally but fail in CI).
Use when exposure, outcome, covariate or eligibility definitions and cutoffs need a citable basis before the protocol. Reads the data dictionary first, then maps each variable to a guideline or published definition and the database columns in a citation-backed table.
End-to-end frontend design engineering workflow for improving React, Next.js, Vite, docs sites, dashboards, component systems, product websites, and studio-style apps. Use when the user asks to make UI/UX/design/frontend/website/docs/app screens more polished, curated, premium, usable, production-grade, responsive, animated, or visually consistent; when editing TSX/JSX/CSS/Tailwind/Fumadocs/shadcn/Radix/lucide interfaces; when choosing design-engineering tools or inspiration resources; or when adding loaders, icons, empty/loading/error states, motion, interaction details, and visual QA.
Reference for the verbose watsonx.data integration SDK for DataStage (batch) flows, with exhaustive stage and property access — the full engine stage catalog. Load this only after the di-agent-flow-lifecycle router has selected the datastage-sdk authoring backend — this is a syntax and stage reference, not a decision about whether to use it. If you have not routed yet, load di-agent-flow-lifecycle instead.
API spec for pyflow, IBM's LLM-optimized Python DSL for authoring DataStage and StreamSets flows. Its compact surface and compile-time validation offer context efficiency, fast feedback, and correctness guarantees. Load this only after the di-agent-flow-lifecycle router has selected the pyflow authoring backend — this is a language reference, not a decision about whether to use it. If you have not routed yet, load di-agent-flow-lifecycle instead.
Docker entry point — provides comprehensive guidance for Docker concepts, architecture, and basic operations. Covers what Docker is, container vs VM comparison, Docker architecture (Client-Server, daemon, registry), installation guidance for Linux/Mac/Windows, and first-container walkthrough. Includes Docker object model (Image/Container/Registry/Engine), CLI basics, and the Docker ecosystem overview. Use when the user asks about Docker basics, needs to understand Docker concepts, is new to Docker, or wants containerization fundamentals. 使用场景:Docker 入门、什么是 Docker、容器概念、Docker vs VM、Docker 安装、docker 基础命令、container basics、Docker 架构。
Gmail Commander email triage—the three-category Haiku prompt and parser in lib/triage.ts, run on demand by the bot's /digest command. The scheduled digest runs in a private deployment with its own implementation. TRIGGERS - email digest, triage emails, digest categories
Capture technical breakthroughs and transform them into actionable, reusable documentation. Use this skill when the user has achieved a significant technical insight, solved a hard problem, discovered a non-obvious solution, or wants to document a breakthrough moment. Also trigger when the user mentions "eureka", "breakthrough", "document this insight", "capture this discovery", or wants to turn a technical win into reusable knowledge.
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.
