Productivity plugins

Bentuk tim multi-agent Claude Code dengan alur rancang → kerjakan → review → simpan, planning/, dan kantor 3D. Memasang kantor-3d otomatis sebagai dependensi.

1 skill

Kantor 3D (three.js) di <host>/kerja yang menampilkan agent Claude Code sebuah project bekerja atau istirahat dari transkrip nyata. Dipakai tim-ai; bisa juga dipasang sendiri.

1 skill

Rebuild scanned pages as searchable, newly typeset PDFs with vector diagrams, checked page by page against the scan.

1 skill

Cloudra - an AI agent for chemists

1 skill

Make Egatari lessons with the make skill. No Node.js required.

1 skill

Local checks, builds, parts and video with the studio skill. Install egatari too.

1 skill

Plan a creation cell's week, review artifact evidence, and prepare consent-aware reflections.

1 skill

Real-time monitoring, logging, and observability for Genkit applications with metrics, traces, and alerts

Track, analyze, and optimize AI API costs for Genkit applications with detailed usage reports and budget alerts

Compare and select the best AI models for your use case - analyze cost, speed, quality tradeoffs across Claude, Gemini, GPT, and more

Applies Anthropic's official brand colors and typography to any sort of artifact.

Picks random winners for giveaways, raffles, and contests.

Query Google NotebookLM notebooks for source-grounded answers.

Zero-dependency HTML report generator for professional A4 consulting reports. Features McKinsey/BCG/Bain visual styles, CSS-based charts, print-to-PDF workflow.

Developer helper commands for the Zotero-Cat repository.

Smoke-test plugin for model provider connectivity and stream output.

Mods Toolbox - Function-hook mods (Claude Code 2.1.291+): Clean View, a calm checklist above the prompt for non-technical users that hides tool calls, diffs and command output while showing the plan, the current step and its progress; the Agent Dock, which splits each request across a chosen team of parallel helpers shown as live cards; and the Status Line Dock, which builds Claude Code's status line from blocks with a live preview; one Toolbox popup above the prompt holds the mods' settings and switches Claude's model and effort

Claude Code mod: a live RoadRaven pane showing agents on roadmap nodes (model, effort, current action, tokens), batched UAT sign-off and a backlog you can start or prioritise.

Portable evidence-linked OSINT and forensic skills

161 agent skills, 63 slash commands, 6 subagents for Claude Code, effort-routed for Opus 5.5. Install: /plugin install kenji@kenji

173 skills · 73 commands · 6 agents · 3 MCP servers · hooks

The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.

58 skills · 59 commands · 15 agents · 1 MCP server · hooks

PM leadership toolkit with 53 skills, 5 orchestrator agents, and 6 multi-stage workflows. Covers PRD generation, OKR lifecycle, pricing strategy, AI pricing, competitive intelligence, sales enablement, quarterly planning, cohort migration-readiness, acquisition screening, customer-insight capture into Productboard, prototype-to-Epics derivation, interview synthesis, retention analysis, AI workflow reimagination, roadmap audits, and more. Domain-agnostic via domain-context.md.

59 skills · 5 agents · hooks

AI-powered development workflows with task tracking, skill-based routing, and guaranteed execution hooks

24 skills · 23 commands · 14 agents · 1 MCP server · hooks

The persistent-memory and runtime-discipline layer for Claude Code. It remembers the corrections you already gave, grounds every edit in real facts before it lands, and — through the Mulahazah engine — turns each fix into a reusable instinct, so a lesson learned once is applied automatically next time with no re-teaching. Built on the 7 Laws of AI Agent Discipline (research, plan, verify, reflect, learn) and shipped as 28 bundled skills, instinct-aware hooks, an MCP toolset for recall and reflection, and a GitHub Action transcript linter that feeds real work history back into sharper instincts.

28 skills · 29 commands · 4 agents · hooks

Complete startup operating system: 9 startup advisor skills (CEO, CTO, Product, Marketing, Sales, Finance, Founder, Legal, Engineering) + deep competitive research with imperium-crawl integration + LinkedIn viral posts + PPTX carousels + HTML slides + brand identity system + SOPs/runbooks + video bridge to Remotion + hidden API discovery. 18 skills, 8 agents, 20 commands, 2,019 RAG chunks. Use when the user mentions anything related to startups, strategy, fundraising, marketing, sales, product, finance, engineering, competitive research, LinkedIn, carousels, brand, presentations, SOPs, or any business topic.

19 skills · 20 commands · 8 agents · hooks

Assess, design, and improve organizational practices for AI-powered products and AI-assisted product work.

41 skills · 6 commands

Senior FE judgment + quality loop (/polish), curated tokens, agents, optional /ui /test-ui /design /audit.

34 skills · 5 commands · 3 agents · hooks

페르소나 v6: 45개 관점과 조건부 전문 스킬. 실제 설치와 자동 선택 검증은 별도.

39 skills · 2 commands · hooks

Intelligent git commit helper with semantic commit message generation, change analysis, and atomic commit guidance using conventional commits format

6 skills · 34 commands · 1 agent · hooks

Personal AI infrastructure with learning-enabled assistance for work, travel, and personal tasks

33 skills · 1 command · hooks