npx claudepluginhub totto2727-org/monorepo --plugin totto2727Skill for creating and referencing Architecture Decision Records (ADR). Use when recording design decisions, reviewing past architectural choices, or checking existing ADRs before implementation. Common triggers: "create ADR", "record design decision", "check ADR", "architecture decision", "design rationale". Do NOT use for: general documentation, meeting notes, code comments, or changelog entries.
This skill should be used when analyzing CSV files with SQL queries. Relevant when the user asks to query CSV data, filter rows, aggregate columns, or explore tabular datasets. Common triggers: "analyze this CSV", "query CSV", "filter CSV data", "count rows in CSV", "summarize CSV".
This skill should be used when creating single-file CLI tools with Deno and TypeScript. Relevant when the user asks to build a CLI tool, create a command-line utility, or set up argument parsing with Effect CLI. Common triggers: "create CLI tool", "build command-line app", "deno CLI", "Effect CLI", "argument parsing".
This skill should be used when researching library or framework documentation. Relevant when the user asks to find docs, look up a library API, check the docs, read documentation, or fetch documentation for a specific package. Common triggers: "look up docs", "find documentation", "API reference", "search docs for", "how does X work in library Y", "check the React docs", "show me the docs for", "what does the API say about".
This skill should be used when persisting development insights, recalling past decisions, building knowledge graphs, or managing AI agent memory. Relevant when the user asks to remember something, recall context, link ideas, or maintain a knowledge base across sessions. Common triggers: "remember this", "recall previous decisions", "store insight", "what did we decide about", "knowledge graph", "exocortex".
Unified git workflow covering Conventional Commits with GPG signing, staging/unstaging/stash rules, safe file deletion via git stash, multi-branch PR splitting, and command execution discipline. Triggers on: commit, add, stash, push, pull, checkout, merge, rebase, reset, rm, diff, log, branch, switch, or any other git operation.
This skill must be loaded before executing any Bash tool command that involves coreutils on macOS (Darwin). On macOS, all coreutils commands (ls, find, sed, awk, grep, cat, cp, mv, rm, sort, head, tail, wc, cut, tr, xargs, stat, readlink, realpath, etc.) require the GNU 'g' prefix (gls, gfind, gsed, etc.). This skill applies whenever the platform is macOS/Darwin and shell commands are being constructed or executed. Always check this skill before writing Bash commands that use coreutils. DO NOT use this skill on Linux — standard coreutils commands work directly without any prefix on Linux/GNU systems.
This skill should be used when analyzing open source repositories on GitHub. Relevant when the user asks to explore a GitHub repository, read source code, understand project structure, check recent issues or PRs, or look up repository documentation. Common triggers: "analyze this repo", "show me the repo structure", "read the source code of", "check recent issues on", "what does this GitHub project do", "explore the repository", "how is this project organized". Do NOT use for: local repository analysis (use file tools directly), library/framework documentation lookup (use doc-search), general web search (use web-search).
This skill should be used when performing path operations across platforms. Relevant when the user asks to calculate relative paths, convert to absolute paths, or resolve symbolic links. Common triggers: "relative path", "absolute path", "resolve symlink", "realpath", "grealpath", "path calculation".
This skill should be used when creating scripts or automation tasks. Relevant when the user asks to write a shell script, create a Deno script, automate a task, or run a one-liner. Common triggers: "write a script", "automate this", "create a CLI script", "shell one-liner", "deno script".
スキル(SKILL.md)の品質レビュー・改善提案を行う。 フロントマター検証、description品質、本文構成、テスト戦略、anti-pattern検出を網羅。 「スキルレビュー」「SKILL.mdチェック」「スキル品質確認」「スキル改善」で起動。 Do NOT use for: スキルの新規作成(skill-creatorを使え)、スキルの実行・呼び出し。
This skill should be used when searching the web or fetching web page content. Relevant when the user asks to search online, find information on the web, retrieve content from a specific URL, or check the latest information about a topic. Common triggers: "search the web for", "look up online", "find on the internet", "fetch this page", "what does this URL say", "check the latest version of", "read this article", "get current information about", "what's new in". Do NOT use for: library/framework documentation lookup (use doc-search), GitHub repository analysis (use oss-analysis).
This skill should be used when managing persistent terminal sessions with zmx. Relevant when the user asks to run background processes, start dev servers, manage long-running tasks, or work with terminal session multiplexing. Common triggers: "run in background", "start dev server", "attach session", "check session output", "list sessions", "kill session", "zmx". Alternative to tmux/screen for session persistence.
A multi-language monorepo (TypeScript + MoonBit) using pnpm workspaces and Vite+.
mbt/: Moonbit Projectsjs/: JavaScript Projectsgo/: Go Projectsapps/: Application projectspackages/: Shared packagesDevbox: https://www.jetify.com/docs/devbox/installing-devboxvite-plus(vp): curl -fsSL https://vite.plus | bashmoonbit: curl -fsSL https://cli.moonbitlang.com/install/unix.sh | bashatlas: curl -sSf https://atlasgo.sh | sh# Enter development environment
devbox shell
# Install dependencies
vp i
CLAUDE.md > Development Commands
Private repository (@totto2727/fp is MIT licensed)
Persistent memory system for Claude Code - seamlessly preserve context across sessions
External network access
Connects to servers outside your machine
Requires secrets
Needs API keys or credentials to function
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.