18 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 18 plugins that match these filters.
lawve-ailawve-ai/awesome-legal-skills2
magnus-agent-skillsmagnus919/agent-skills2
mcpbundler-agent-skills-marketplaceeugenepyvovarov/mcpbundler-agent-skills-marketplace2
lore-pluginandresanemic/lore-plugin1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceLearning & mastery skills: build a roadmap for any skill, remember what you read and study (spaced repetition, active reading), learn by doing, break plateaus, and map your knowledge gaps.
The Chinese parents pack (家长): school entry planning for 幼升小 and 小升初 (timeline, documents, 学区 and 多校划片 questions, marked to confirm locally), polite home-school messages to teachers (家校沟通), an extracurricular plan checked against the 双减 rules, time and budget, and guiding rather than doing a child's homework, written in Chinese
PageRank-based jurisprudential authority analysis for Argentine case law (CSJN, federal courts). Peer-reviewed methodology published in JCLLT (DOI: 10.47852/bonviewJCLLT62027951). Ranks precedents by citation network influence with temporal decay.
Local fine-tuning for your own tasks, except the one doing the training is you. Operate Lore with use-lore, brainstorming-lore, create-area, create-project, create-bot, save-to-lore, transmute-lore, stale-lore, and vespi.
Assistant juridique expert couvrant le droit français, européen (UE et CEDH) et étranger via LegalDataHunter, pour professionnels et chercheurs. Couvre dix tâches : cadrage, recherche juridique, consultation, rédaction d'actes, analyse de pièces, contre-argumentaire, analyse de contrats, veille juridique, vérification de références et harmonisation bibliographique. Règle stricte d'anti-hallucination (Chercher → Trouver → Citer) avec vérification temporelle de chaque texte normatif via OpenLegi. Utilisez cette skill chaque fois que l'utilisateur mentionne du droit français ou européen, demande une recherche juridique, une consultation, la rédaction d'un acte, l'analyse d'un contrat ou d'une pièce, une vérification de citation OpenLegi/HAL/CEDH, ou prépare un dossier de plaidoirie — même sans dire explicitement « assistant juridique ».
Founder persona pack: social engagement, founder-voice AI SDR, warm engager follow-up, and customer plays for founders doing their own sales. Installs with the FirstTouch MCP auto-connected.
salesDownload scientific paper PDFs by DOI (or title) — 7-source fallback chain (Unpaywall, Semantic Scholar, arXiv, PubMed Central, bioRxiv/medRxiv, publisher direct, Sci-Hub), batch mode, idempotent retries, structured JSON envelope, and SSRF-safe downloads
Ai2 Asta MCP — Semantic Scholar academic graph over MCP (no Python). Intent-to-tool routing, safe fields defaults to avoid context blowups, citation traversal, author lookup, snippet evidence retrieval, and DOI/arXiv/PMID via externalIds.
Paper metadata lookup — resolve a DOI, PMID, arXiv id, OpenAlex id, or title into one full record (title, authors, first/corresponding author, publication date, journal + ISO-4 abbreviation, impact factor, volume/issue/pages, DOI/PMID, citation count, abstract) via OpenAlex with Crossref fallback, ISO-4/IF enrichment via sibling journal-abbrev/journal-if skills, batching, and a stable JSON envelope
Use whenever the user mentions Zenodo, depositing or publishing research artifacts (datasets, software, papers, posters) to Zenodo, minting a DOI for a dataset/code release, uploading files to a Zenodo record, creating a new version of a Zenodo deposit, or searching Zenodo records. Covers the full Zenodo REST API workflow (create, upload via bucket API, metadata, publish, version, search) for production and sandbox.
Interact with Figshare via the v2 REST API - search public datasets/articles, batch-download files, and create, update, publish, or multi-part-upload to your own articles (trigger on "figshare", figshare DOIs 10.6084/m9.figshare.*, or figshare.com URLs)
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.
Teach a subject through source-grounded explanations, brief diagnostic tasks, practice, and adaptive feedback. Use when a learner asks to learn, understand, refresh, practice, or be tutored toward an observable goal. Do not use for a standalone factual lookup, doing the task on someone's behalf, life coaching, group-program design, or collecting research without teaching.
Create new agent skills from scratch, modify and improve existing skills, and measure skill performance through evaluation and benchmarking. Use when users want to create a skill, write a skill, build a new skill, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, or optimize a skill's description for better triggering accuracy. Also triggers when users say "turn this into a skill", "make a skill for X", "skill for doing Y", or ask about skill structure, skill format, or SKILL.md files.
Catch AI-fabricated citations: verifyCitation cross-checks a claimed title against the real record at its identifier, detecting the dominant real-DOI + invented-title pattern (Topaz et al., Lancet 2026) that simple DOI resolution cannot catch. Also checks retraction and open-access status, and resolves eight identifier types (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.
Build deep architectural understanding through ultra-granular code analysis. Use when doing security audits, code reviews, or getting oriented in an unfamiliar codebase.
Security audit skill for detecting dangerous APIs, footgun patterns, and vulnerability variants. Use when reviewing code for security issues or doing variant analysis.
WAYD (What Are You Doing?). The scroll break you take while your agent works, without leaving your console. Post short vibes, scroll what other devs are losing their minds over, react and reply, then get straight back to the task.
