Плагины Claude Code
6 078 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
6 078 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceClaude for Account Executives: 32 Claude skills for working named accounts, from account research to win/loss review, in eight stages: know the account with a research brief, a stakeholder map and an account plan; find a true reason to call with a buying signals brief and a talk track; prepare and run the meeting with a call plan and discovery questions; write it up the same day in call notes and a recap email; propose with a brief, the proposal and a quote check; negotiate and close with a negotiation plan and a mutual action plan; run the pipeline and forecast on written evidence; review the deal with MEDDPICC and a win/loss review. For account executives, key account managers and the sales and business development leaders who run them. Claude prepares from public sources and your own notes and you have the conversation; it never invents a contact, a signal, a number or a customer quote, never rates a buyer or a seller, and never contacts anyone for you.
productivityClaude for Consultants · Team in Claude: 39 Claude skills for winning and shaping client work when the client has AI too, from their brief to the signed scope, as eight desks in order: Intake reads the client's brief, qualifies the opportunity and records the bid or no-bid decision; Discovery prepares the call, keeps the notes and sends the recap email; Problem writes the problem statement, the issue tree and the hypothesis test plan; Strategy builds options and the recommendation memo; Pricing shapes good-better-best options, fees and a MoSCoW scope; Proposal writes the consulting proposal, the AI use statement and the statement of work; the Client room prepares the walk-through deck, the AI objection answer and the negotiation plan; Follow-through covers follow-up emails, the mutual action plan and the win/loss review. For independent consultants and partners in advisory practices. Claude structures, drafts and checks; it never invents a reference, a result, a number or a client quot
productivityClaude for Product Builders: 32 Claude skills for taking one idea from a question to a prototype real users can try, and on to a build, change or stop decision, in eight stages: frame it with a problem frame, an idea one-pager and a prototype test card with a dated pass line; spec it with a prototype brief, a screen-by-screen user flow and a prototype spec; build a clickable prototype in Claude Design; make one flow really work in Claude Code; check it is safe to show with a secrets and keys check, a personal data check, an access and sharing check and a pre-share sign-off; test it with five real target users; hand it to engineering with everything faked written down; then get a decision from a named person. For product managers and product designers who want to build a prototype themselves, and founders shaping a first product. Claude builds the prototype, real users test it and engineers own what ships.
productivityClaude for Product Designers: 32 Claude skills for one piece of design work, from the request to the result, in eight stages: frame the problem with a problem framing brief, a user journey map and a HEART metrics plan; explore and decide with design principles, an options trade-off table, a rationale doc and a decision log; design with context through a design system rules file, a product context file, the user flow, the copy deck and every UI state; prototype around one question; critique against a quality bar, ten heuristics and an accessibility review; test with real users; hand off with a spec and a UX debt register; then show the impact in a review deck, a pushback brief, an impact write-up and a portfolio case study. For product designers, UX and UI designers, and designers who do their own research. Claude drafts, checks and explains; you make the design decisions, real users test the work, and nothing is presented as tested, accessible or ready to ship that was not.
productivityClaude Guide for Product Strategy: 32 Claude skills for one product strategy cycle in eight stages: diagnose with the strategic question, a product health read, an issue tree and a hypothesis board; read the market and the customer with competitors, segments by need, an opportunity solution tree and a market size; choose with options that differ in kind, a decision matrix, the bets and the not-doing list; stress-test with scenarios, a red team review and a pre-mortem; put numbers on it with a business case, a north star metric and strategy KPIs; build the Now-Next-Later roadmap and quarterly OKRs; tell it in the strategy document, the one page, the deck and the board memo; then review it each quarter. For product managers and product leaders who own a strategy or a roadmap, and founders and fractional product people who write one for a client. Claude structures the thinking and drafts the documents; a named person makes the choices, and every figure names its source or is marked as an
productivityClaude Guide for Product Interviews: 32 Claude skills for preparing product interviews from the job ad to the offer, in eight stages: read the role with a target role brief, a job ad breakdown and an interview loop map; tell your story with a career evidence inventory, a story bank and resume bullets; prepare the cases for product sense, metrics, prioritisation and execution, and app critique; prepare the conversations with behavioural answers, a portfolio or project walkthrough and a mock interview; show how you work with AI with an AI use plan, a fluency answer and a work sample; get in through people you already know; run each process with a take-home plan, round debriefs and a tracker; then decide with an offer comparison and negotiation prep. For product managers, product owners and product designers with years of shipped work. Claude helps you prepare and practise from work you really did; it never invents a role, a result or a number, and it stays out of the live interview.
productivitySchema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs
Audit and rewrite prose that reads as machine-generated, across READMEs, changelogs, PR descriptions, docs, and blog copy, with detect-only, rewrite, and edit-in-place modes.
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts
Hermes Agent plugin for public X/Twitter research and approval-gated private or state-changing operations through Hermes Tweet
Modern Julia development with Julia 1.10+, package management, scientific computing, high-performance numerical code, and production best practices
ARM Cortex-M firmware development for Teensy, STM32, nRF52, and SAMD with peripheral drivers and memory safety patterns
Drive the Superself `self` CLI: version control for a project's state (goals, decisions, work units, reports) kept outside the code repo, so a session reads context at start, reports with evidence, and the next session picks up where this one left off
Guides developers from brand discovery through iterative design to deployment-ready HTML via Stitch.
Teaching skill: cookbook-style walkthrough for signed audit trails on every Claude Code tool call. Cedar policy, Ed25519 receipts, offline verification, CI/CD integration, SLSA composition. Pairs with the protect-mcp runtime plugin.
Convert common image, audio, video, document, and data formats with installed local tools while preserving originals.
Skills for migrating and upgrading .NET projects across framework versions, language features, and compatibility targets.
AKS operational skills for troubleshooting, advanced cost-efficiency analysis, known issues, GPU inference, and packet capture.
Establish and verify project technical foundations using native stack mechanisms, explicit contracts and safe recovery.
Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.