Find plugins

by UNCTAD Trade Facilitation Section

One front door for eRegulations work — describe the problem in plain English, or run /eregulations:ereg, and the router sends the request to the right knowledge, resolves which instance and version it concerns, and blocks on unsafe hosts, mismatched Admin/Public branches, and unsupported versions before anything runs.

by Marc Lavallee

Read and write checkable data pages that preserve dataset pitfalls and sanctioned practices.

by prest4u

Portable skills for educational documents, PDF design, presentations, websites, video production, and reliable agent workflows.

by AkaraChen

Collaborative UI and visual design skills for audits, animation, and visual craft.

by Seth Hobson

Error analysis, trace debugging, and multi-agent problem diagnosis

by Seth Hobson

Error analysis, trace debugging, and multi-agent problem diagnosis

by Seth Hobson

Error tracing, root cause analysis, and smart debugging for production systems

by Seth Hobson

Error tracing, root cause analysis, and smart debugging for production systems

by Fernando Raimondi

Capa L4, para automatizar procesos con n8n, Make, Zapier o ManyChat y conectar herramientas: 13 skills (las 7 de n8n de czlonkowski, ManyChat en n8n, patrones de Zapier/Make y de automatización, CI/CD, registrar apps en Microsoft Entra, construir servidores MCP) y 3 agentes (automation-architect, que diseña el flujo; data-engineer, que arma los pipelines de datos; deployment-engineer, para publicar). Pedile a Claude: «automatizá que cuando entra X pase Y».

by Fernando Raimondi

Capa L4, para cuando empezás a desarrollar tus propias herramientas con Claude (vibe coding): 1 skill (research-deep-dive, investigación profunda en 3 etapas) y 5 agentes (code-reviewer y security-reviewer, que revisan tu app entera antes de usarla con clientes; research-analyst, data-researcher y knowledge-synthesizer, que arman research-deep-dive). Los revisores explican en castellano qué puede pasar y en qué orden arreglarlo. Pedile a Claude: «revisá mi app con los dos revisores» o «investigación profunda sobre X».

by Fernando Raimondi

Capa L4, para hacer piezas visuales con Claude: presentaciones, animaciones y videos, prototipos de pantallas, infografías y arte generativo. 20 skills: huashu-design (estudio de diseño: te muestra 3 direcciones antes de hacer nada), el set de video de HyperFrames (10, sin actualizaciones solas; la telemetría se apaga con dos variables, ver requisitos.md), estilo-de-marca, sistemas de diseño de UI (ui-ux-pro-max, ui-design-system, components-build, frontend-ui-engineering) las de arte y gráfica de Anthropic (canvas-design, algorithmic-art, slack-gif-creator) y video-content-strategist (estrategia de video para redes y YouTube). Pedile a Claude: «armame una presentación de X», «animá esto», «prototipá esta pantalla».

by Anthony Adams

Contribute agent time to ending corporal punishment in US schools: district policy scans, claim verification, bill watching, CRDC refresh, legislator dossiers, share kits.

by Tembici

Skills de Transversal — Escrita e rotina para o dia a dia da área. Cobre: Escrita e comunicação · Rotina e produtividade. Inclui Revisão de texto com marcas (redline), Comunicação executiva, Brief de trabalho e Extração de itens de ação, entre outras 14.

by EsepTez

EsepTez — POS and inventory for shops in Kazakhstan: sales, stock, debts, cashier control and goods receipts from a photo of a supplier invoice.

by NotasAI

Esment memory for your AI assistant — recall before you answer, save what matters.

by Esment

Esment memory — persistent, cross-assistant context.

by dobachi

Find the essence of an artifact and strip away what is inessential — the via-negativa counterpart to doc-refactor, across prose/docs, specs & requirements, source code, and diagrams. Separates what is load-bearing for the artifact's ONE purpose and audience from redundancy, gold-plating, decoration, filler, speculative generality, premature detail, and scope creep, then PROPOSES cuts with rationale and a 'what would be lost' note. Deliberately meaning-changing (unlike doc-refactor, which only rearranges): diagnose-first, non-destructive, propose-then-confirm. Anchors every cut to a stated purpose + audience, respects Chesterton's Fence (flag, don't cut, what you don't understand), and preserves correctness/behavior. Hands off the code edit to /simplify or /code-review, the redraw to document-figures, a separate short derivative to document-summary, pure rearrange to doc-refactor. Bilingual JA/EN.

by Lexi James

The estate's eleven Claude Code hook scripts plus a shared gitleaks helper, packaged as a plugin.

by Carsio Eddyo

Quando o uso está alto, a cota perto do fim ou o contexto perto do limite, toca o áudio e chama o subagente John Coffey.

by Ghast AI

Read multi-chain balances, transactions, token transfers and contract data.

by x-mesh

Agent output quality evaluation — multi-rubric scoring, strategy benchmarking, and A/B prompt experiments

by yukineko

Offline golden-regression eval harness for Claude Code plugins: read golden *.jsonl cases (file-content or CLI-output assertions) and exit non-zero when a prompt edit or CLI contract regresses. The offline sibling of condukt's online verifier — runnable as a CI gate with no API key. Subscription-native (one bundled Rust binary).

by haboshi

Stop フックでビルダー（Claude 本体）の完了主張を外部モデル評価者（Codex/Grok、いずれもサブスク認証・API 従量課金なし）が検証する完了ゲート。ビルダー≠評価者の分離（fresh context・別モデル系統）で「完了しました」の安易な着地を根拠つきで差し戻す。diff ハッシュによる決定論事前チェックで変更のないターンは LLM を起動しない。作業ツリー外のブランチ（隔離 worktree → push → PR）も git の ref から検出して証拠に含める。per-project opt-in（既定 OFF）。/evaluator-gate で切替、/evaluate でオンデマンド所見評価。

by dobachi

Design event-driven, asynchronous, and real-time services beyond request/response REST: messaging (queues/streams), async workers, scheduled/round-based jobs, and WebSocket/SSE push, with correctness under concurrency — idempotency, ordering, delivery guarantees, and backpressure.