Productivity plugins

Structured ideation: generate high-impact feature ideas and run synthetic user-research simulations to decide what to build next.

2 skills

Push Claude Code notifications (turn results, human-in-the-loop alerts) to a shared IM chat room via an AgentX bot. Outbound-only, zero LLM tokens, no Node.js.

1 command · hooks

Measure Claude Code usage-limit blocking across a team from local transcripts: per-developer outage ledger (blocked, reset, resumed, hours lost) plus an API-equivalent cost model. Reads only local files; shares no prompts, paths, or repo names

2 commands

Notion workspace automation tools

2 commands

Local, metadata-only telemetry for Claude Code. A bundled observer records session, tool, and subagent lifecycle events into SQLite on your machine, an optional statusline shows live context and usage, and an OpenTelemetry Collector can forward redacted signals to Grafana, generic OTLP, or PostHog. Prompts, responses, code, tool inputs and results, credentials, and environment values are never stored. Every sink beyond local SQLite is opt-in.

1 skill · hooks

Evidence-backed engineering discipline: acceptance contracts, root-cause fixes, a hook-enforced verification gate, and the shared three-loop stop rule.

1 skill · hooks

Keeps coding work scoped to the requested outcome and enforces the shared three-loop stop rule with a stateful PostToolUse hook.

1 skill · hooks

Answers retrospective questions from the recorded session and closes work with the shared handoff receipt.

1 skill · hooks

Evidence-based health, fitness, nutrition, and longevity guidance for adults 50+

1 agent · hooks

Automatically documents technical projects in Obsidian vaults during Claude Code sessions

1 skill · 1 agent

One line at the bottom of Claude Code: how much of the context window is gone, how much of the weekly budget is spent, and which model is answering. Every figure is read from the payload the harness pipes to the script on stdin, so nothing is host-specific. Needs node and nothing else.

2 skills

Lightweight utility skills for quick answers and idea clarification

2 skills

Retrieving and correctly interpreting recordings, transcripts, and AI notes from a Plaud account. Bundles the official Plaud MCP server and a skill covering the parts that bite: context-heavy responses, a paraphrasing "polished" transcript that must never be quoted, diarization that merges two speakers into one turn, UTC-vs-local timestamp mismatches, and the proper-noun glossary loop that keeps mistranscribed names out of downstream notes.

1 skill · 1 MCP server

AI coding agent instruction file init and retrofit. Builds a single routing chain so every AI tool reads the same source: tool symlink -> AGENTS.md -> .agents/README.md (overview plus top-level directory routing table) -> each top-level <dir>/README.md -> detail files. Sets up AGENTS.md, idempotent symlinks across major AI tools (Claude Code, Cursor, Copilot, Windsurf, Cline, Roo Code, Gemini CLI, Codex, Zed, Antigravity, Amp, Aider, Continue), and a .agents/ meta directory (README, schema, conventions, preset.json, hooks/pre-commit-secrets.sh, local). No agents/ content directory and no team or hub mode branching - the chain is single-mode and AI-first. Bundles a meta-validator companion skill that auto-fixes frontmatter / relations / git timestamps, rebuilds .agents/.tag-index, scans for secrets, and enforces tight length recommendations (AGENTS.md 50/80/120, README.md 80/120/200). Use whenever the user wants to initialize a project, bootstrap AGENTS.md, unify instruction files across AI tools, retrofit an existing project, validate routing READMEs, or make a repo AI-navigable - even if they say 'AI rules', 'agent config', or 'check AGENTS.md'.

2 skills

Markdown knowledge base init and retrofit. Creates .kb/ meta directory plus preset top-level directories (team-docs, research, product, custom, career). Every .md file carries required frontmatter (title, created, updated, summary, tags, status, relations). Phase 0.5 verifies tool dependencies (yq or python+PyYAML, gh for career, optional ripgrep/gitleaks/lychee) with OS-aware install on opt-in. Installs a pre-commit secret-scan hook, and for the career preset (roles, resumes, projects, skills, brag, learning, reviews, goals) also a pre-push hook that blocks pushing to a public repository. Bundles a companion kb-validator skill that syncs timestamps from git log, prunes broken relations, rebuilds .tag-index, enforces README per directory, and flags length recommendations. Use whenever the user wants to initialize a repo as a shared knowledge base, set up a personal career portfolio, retrofit existing docs, prepare docs as a submodule, or make markdown AI-navigable - even if they say 'docs init', 'career portfolio', 'set up wiki', or 'validate kb'.

2 skills

Standalone utility skills independent of any one workflow: searching past Claude Code sessions by topic; running a GitHub Projects v2 board as the single home for a repo's milestones, epics and stories, with ticket templates.

2 skills

Werkzeuge mit ausschließlich expliziter Auslösung: /tools:unslop (KI-Muster aus Text entfernen), /tools:grimm (Sachverhalte ins Verwaltungs- und Anordnungsdeutsch überführen). Nachfolger der Plugins unslop und grimm.

2 skills

Maintain a structured Obsidian vault (Zettelkasten-style) from recent Claude Code sessions: harvest concepts into inbox seed notes, detect orphans, near-duplicates, and MOC gaps — all as a single batched-approval review document.

1 skill · 1 MCP server

Add Gmail access to NanoClaw via gog CLI (Google Workspace CLI). Agents can search, read, and send emails. Shares OAuth credentials with Google Calendar if already configured. Triggers on "add gmail", "gmail setup", "gmail integration", "email setup".

2 skills

Add read-only IMAP email access to NanoClaw agent containers. Supports multiple providers (Gmail, Yahoo, Outlook, any IMAP server). Guides through app password setup and configures environment variables. Triggers on "add email", "add imap", "email integration", "read emails".

2 skills

Add Notion API access to NanoClaw. Enables agents to read and update Notion pages and databases for project management, notes, and tracking. Guides through integration setup. Triggers on "add notion", "notion setup", "notion integration", "notion api".

2 skills

Create or upgrade a reusable skill in the current skills catalog. Use when adding a skill, improving metadata/examples/evals, tightening trigger boundaries, or deciding if guidance belongs in a skill.

2 skills

Bundles the realfavicon-mcp MCP server: generate favicon assets and HTML from a master image, audit a live page's favicon setup, and query the RealFaviconGenerator change-log.

1 skill · 1 MCP server

Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.

1 skill · 1 command

Default bundle: global instructions, the Night City theme and mod (spinner words, status-line reactions), desktop notifications, Context7, and core plugins from claude-plugins-official as dependencies.

1 MCP server · hooks

Generate WeChat/Xiaohongshu article covers and infographic series via the local Codex subscription (built-in image_gen / gpt-image-2, no API key)

2 skills

Harvest a session's learnings into their right homes: a memory, a suggested repo edit (CLAUDE.md/AGENTS.md, docs, or a hook), or a PR that improves one of your own agent skills.

2 skills

Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.

1 skill · 1 command

Connect Activity to Claude, Cursor, and ChatGPT through JoAi's hosted MCP app server.

1 skill · 1 MCP server

Connect AI Calendar to Claude, Cursor, and ChatGPT through JoAi's hosted MCP app server.

1 skill · 1 MCP server