google-workspace-dev

Next.js provisioning plugin. Set up shadcn/ui and shadcn studio — component installation, theme configuration, MCP server setup, project scaffolding, and multi-registry component search across 260+ registries from the official directory.

NocoBase v2 development plugin. CLI primary (nb CLI) + REST API fallback (bundled OpenAPI v2.1.0-beta.29, 272 endpoints). Auto-syncs 11 official upstream skills from nocobase/skills weekly via GitHub Action. 5 custom REST-API skills (overview, auth, cli-recipes, api-reference, examples). Env vars: NB_URL + NB_USER + NB_PASSWORD (sign-in) or NB_URL + NB_TOKEN (API Key).

Marketplace

Dify API dev plugin for Agents Store. Complete coverage of the Dify App Service API (chat, completion, workflows, conversations, files, audio, annotations) and the Knowledge Base / Datasets API — auth, endpoints, streaming events, curl examples, and troubleshooting.

n8n instance provisioning plugin. Discover workflows from the official template library (9,166+ templates), GitHub repos, and community platforms, then analyze, import, and batch-deploy them to provision an n8n instance.

Directus + Next.js stack dev plugin. Integrates Directus headless CMS with Next.js App Router for content-driven applications.

Web search and scraping developer toolkit. MCP tool patterns, REST API reference (Firecrawl v2), SDK/CLI usage for Firecrawl, Exa, Perplexity, Jina, Pexels, Unsplash, and Context7. Practical skills for web scraping, documentation search, and media discovery in dev workflows.

DataForSEO data analysis plugin. Keyword research, competitor analysis, backlink auditing, SERP monitoring, on-page audits, content analysis, and AI optimization via 70+ MCP tools.

Turns what a client says into documents they can correct, a machine spec an agent can build from, and a work list somebody can pick up. Keeps the macstack/ folder of a project: macstack.json — the standardized business + technical stack specification, always English — and the six client documents it is written from. OVERVIEW says what the product is and who it is for; USER-CASES carries each case with its UX bar and an addressable acceptance list; UX-UI states what each screen shows and what must never appear on it; AUTOMATION is the trigger -> task -> workflow -> role model; HANDBOOK is how a person actually uses the thing; OPEN-QUESTIONS splits what the client owes from what the team deferred. v3 makes those six pure markdown — headings and bullet lists, nothing else. No YAML blocks, no tables, no change-log sections: the only machine markup is an HTML comment the reader never sees, pointing each entity at its place in the spec. A client can edit the document in any editor and hand it back. Around them: an immutable inbox for anything a client sends, a gated delta/rulings loop that merges it, generated requirements, architecture, test cases and index that carry every id the client documents carry, an append-only ledger with one row per edit and per client comment, tasks reconciled with the team's own tracker, and a review package that shows each statement with its own history and reads the client's answers back into the ledger. Eight commands, one job each — including one that reconciles the whole folder against the source tree in a direction you have to declare: the code is master and every document is corrected through a gate that never silently overrules an answer the client gave, or the documents are master and the gaps become tasks. Every edit is journalled, every finished task sweeps the client documents and not only the generated ones, task statuses move to what the audit actually found — closing what is built and reopening what is not — and every document carries the date it was last checked against the code, so a document that reads perfectly cannot quietly describe a system that no longer exists.

restic backup plugin for Agents Store. Set up encrypted daily backups on any Linux server to S3-compatible storage (Cloudflare R2): server recon + restic install, auto-discovery of all Docker volumes/mounts and databases, R2 repository init, a partial-failure-tolerant backup script with logical DB dumps and retention, timezone-aware systemd/cron scheduling, verification, monitoring/dead-man's-switch, and disaster recovery. File-based knowledge, no MCP, no stored credentials.