ワンクリックで
skills
skills には tada5hi から収集した 18 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
Generate a Conventional Commits message for uncommitted changes in the working directory. Use when user wants to "generate commit message", "write commit message", "conventional commit", or before committing staged changes.
Initialize a project with AI agent documentation (CLAUDE.md, AGENTS.md, .agents/*.md). Use when the user asks to "init agent docs", "create Claude docs", "set up for AI coding", or when setting up a new repository for AI-assisted development.
Scaffold a new TypeScript project from tada5hi/typescript-template. Use when the user asks to "init ts project", "create a new typescript library", "scaffold typescript package", or wants to bootstrap a new repository based on the template.
Fetch PR review comments from GitHub, investigate each one against the actual codebase, and fix real issues. Use after a PR review to triage and act on reviewer feedback, or when asked to "check PR comments", "handle review feedback", or "investigate PR".
Propose template improvements to the init-agent-docs skill via pull request to tada5hi/skills. Use when the user asks to "update skill templates", "contribute back to skills", or when a project's agent docs have patterns worth upstreaming.
Audit type boundary mismatches in TypeScript monorepos — detect cases where `as` casts or utility calls like pickRecord() silently hide property name mismatches. Use when asked to "audit types", "check type casts", "find type mismatches", or during naming convention migrations.
Perform cross-package impact analysis for a type, function, or constant in a TypeScript monorepo. Use when asked to "impact analysis", "find all consumers", "who uses this type", "trace imports", or before renaming shared symbols.
Read structured plan files (Markdown with checklists/phases) and report progress by cross-referencing the plan against the current codebase state. Use when asked to "check plan status", "plan progress", "where did I leave off", or "what's next".
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
Break a PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Triage a bug or issue by exploring the codebase to find root cause, then create a GitHub issue with a TDD-based fix plan. Use when user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.
Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
Link skills from skills/ into .claude/skills/ so Claude Code discovers them. Use when a new skill is added, after "link skills", "register skills", or "sync skills".