443 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 443 plugins that match these filters.
nostr-vpn-pluginsmmalmi/nostr-vpn1
overdrive-marketplaceradustefandumitru/overdrive1
estuaryestuary/agent-skills1
apache-magpieapache/magpie1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplace12 working methods for mcp: mcp-authentication, mcp-client-integration, mcp-context-budgeting, mcp-error-handling, and more
14 working methods for python: pytest-mastery, python-asyncio, python-cli-tools, python-concurrency, and more
10 working methods for scripting automation: automation-guardrails, bash-robustness, cli-ux-design, environment-config, and more
Set up and inspect a Nostr VPN private mesh with the nvpn CLI. Use local keys and signed administrator approval instead of a VPN provider account. Connecting requires host networking permissions.
Helper skill and commands for installing and using the full Overdrive CLI skill system.
developer-toolsMaterialization skills for PostgreSQL, Snowflake, BigQuery, Redshift, Databricks, ClickHouse, HubSpot, and any destination connector
This Skill creates a research brief for an area of US employment law. The brief can address a specific question or be a multi-state survey. It'll include citations to primary sources (e.g. statutes, rule, government guidance), and reputable secondary sources like client alerts and multi-state surveys from top law firms and articles from legal publications (e.g. National Law Review).
Draft, adapt, and review contracts and clauses aligned with The Chancery Lane Project's methodology for reducing carbon emissions through legal agreements. Use when Claude needs to: (1) Draft new climate-aligned clauses (e.g., net zero commitments, carbon accounting, supply chain decarbonization), (2) Adapt or modify existing contracts to incorporate climate objectives, (3) Review and analyze clauses for alignment with climate goals and decarbonization strategies, (4) Provide guidance on The Chancery Lane Project's house style and drafting methodology for climate-conscious legal work.
Transforms reading-oriented prose into listening-optimized text for flat, neutral vocal delivery — TTS, podcasts, audiobooks, CLE audio. Carries a legal layer: case citations, section symbols, subsection lettering, Latin terms and footnotes are unspeakable as written, so a brief, opinion, statute, contract or memo needs them expanded, restructured or stripped before it can be listened to — and quoted authority is never rewritten. Use when converting written content for audio, preparing oral argument by ear, producing CLE or client-facing audio, or making a document listenable on a commute. Triggers on "make this listenable," "convert for audio," "optimize for reading aloud," "prepare for TTS," "make an audio version," "podcast script," "read this aloud." Supports English, French, Spanish, Italian, German and Portuguese; outputs plain text, ElevenLabs audio tags, or SSML for Amazon Polly, Google or Azure.
Citable helps make your cite-checking more efficient and accurate. It transforms US court filings and drafts into structured tables that link every citation to pinpoint locations in the record, case law (CourtListener), statutes (Cornell LII), or treaties in a single click. Citable flags when a pincite cannot be located, potentially catching incorrect cites before your check begins. Check every citation from one table: each passage can be read alongside its citations, and clicking a citation opens the cited source. Adjust each citation’s status (check pending / confirmed / partial support / unsupported), and add notes from your review. Revised drafts: when the draft changes, citable rebuilds the table, flags the citations that changed, and carries your saved statuses and notes forward. Citable locates and links sources; the cite-checking judgment stays with the lawyer. It runs on your computer; nothing is stored in the browser or sent elsewhere.
Build a client instruction schedule: a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note. Output is always a .docx draft for solicitor review.
Detects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an AI reads them, so the model is not turned against your client. Checks word by word that the text an extractor hands the model was visibly drawn on the page: white, near-white, covered, clipped, off-page, tiny, transparent and invisible-mode text in PDF (ink test plus OCR); Word formatting resolved as Word does (styles, shading, theme colours, scaling, off-page frames, fallbacks, unused headers); HTML/CSS, RTF, email with attachments and zips, xlsx/pptx and legacy formats. Flags Unicode smuggling, text addressed to an AI and authorities found only in hidden text. Fails closed. Optional Read-tool hook. Use BEFORE any AI summary or analysis of an opposing or third-party document. Triggers: 'scan for injection', 'is this document safe', 'check the other side's skeleton', 'injection guard'.
Screen a client, counterparty, payer or corporate against the sanctions lists published by the designating authorities themselves — the UK Sanctions List (FCDO), OFSI, the UN Security Council, the EU consolidated list and OFAC's SDN and non-SDN lists. Use when onboarding, before taking a payment, before completing a transaction, or whenever a name must be checked against sanctions. Produces candidates and provenance, never a clearance: the record names every list searched with its publication date and count, states what was NOT searched, and ends at a blank decision block. Fails closed — a cache that is missing, damaged, truncated or stale is reported NOT SEARCHED and the process exits non-zero, so nothing can read an incomplete run as clean. Matches across transliteration, diacritics, homoglyphs and initials, because nobody spells a name the way the publisher does. Standard library only; screening opens no network connection.
Takes a skill — a .skill or .zip archive, a bare SKILL.md, a folder, or just a raw idea — and produces a package ready for public distribution on lawve.ai, plus the exact entries for the submission form. Runs a gate first: skills with no plausible legal use, unsafe code, or licensing bars are declined with reasons, and general-purpose skills that could serve legal work are offered a legal adaptation instead. Then applies the standard compliance transforms — structure, metadata, attribution, dependency ladders, orphaned-file repair, limitations disclosure — validates the result, and delivers a zip. Raw ideas are gated first, built (via skill-creator where available), then adapted. Use for "make this Lawve-compliant," "prep this skill for Lawve," "package for lawve.ai," "is this suitable for Lawve," "get my skill ready to publish," or any request to ready a skill for the Lawve catalogue.
Apache Magpie — adversarial review: runs other models' CLIs (Codex, Copilot, Antigravity, Pi, Grok, Goose, Claude) read-only over a change before its PR is created, and merges their findings. Runs from the installed plugin, so no repository needs a copy.
Agent skills for 37signals products, each driving its product's CLI. Bundles the Basecamp skills today; HEY and Fizzy join as their CLIs publish here (see the README).
Guide product managers from idea to launch using the Pragmatic Framework (Foundations, Focus, Build). Every stage ends in a client-ready artifact (Markdown or Word .docx).
product-management9 working methods for apis: api-change-management, api-client-design, api-deprecation, api-design, and more
Agent workflow suite — Karpathy-pattern autoresearch (hill-climbing, multi-agent research) and skill-improver (Claude Code skill optimization loop).
ai-workflowjig repository workflow skills: project setup, develop flow, CLI releases, repository sync, and lifecycle management. Skills are namespaced as /jig:<skill> on Claude Code and jig:<skill> on Codex.
