hrdtbs
20 verified skills
github-cli
Comprehensive interaction with GitHub repositories, issues, pull requests, and releases using the GitHub CLI (gh). Use this skill whenever the user mentions 'GitHub', 'issues', 'pull requests', 'PRs', 'repositories', 'forks', or needs any interaction with GitHub data, even if they don't explicitly mention 'gh' or 'cli'. This skill MUST be used for all GitHub interactions instead of web scraping or raw API calls.
tools
bash-best-practices
Write, review, and debug robust Bash scripts. Make sure to use this skill whenever the user needs help with shell scripts (bash, sh), asks to write a CLI tool in bash, debugs a failing shell script, or needs to ensure predictable behavior in CI/CD or production systems, even if they do not explicitly ask for best practices.
tools
commit
Expert-level commit creation and formatting following Conventional Commits. Make sure to use this skill whenever you need to create a commit message, save changes to git, structure a logical commit history, or when the user mentions 'commit', 'git commit', 'コミット', '変更をコミット', or asks you to push their code.
development
agent-best-practices
The ultimate guide to agent behavior and best practices. Trigger this skill whenever you need guidance on how to act, when to ask questions, how to interact with the file system safely, how to fix bugs efficiently, and general coding guidelines to produce top-tier work. This acts as a comprehensive reference manual for high-quality autonomous agent execution.
testing
comprehensive-code-reviewer
A comprehensive, context-aware code review assistant. Use this skill whenever the user asks to review code, look for bugs, check for security vulnerabilities, or improve code quality, even if they just say "review this diff" or "what's wrong with this file?". This skill systematically analyzes code for logic errors, performance bottlenecks, security flaws, and style adherence, providing actionable feedback in a structured format.
development
create-project
Guide for managing long-running AI agent tasks by persisting implementation plans, task lists, and research notes into project documentation files (docs/PLAN.md, docs/TODO.md, docs/references/). Use this skill whenever the user wants to create a PLAN.md, TODO.md, or reference notes, when starting a new project or planning a new feature, when the user says 'let's plan this out', 'create a plan', 'write down the next steps', or mentions organizing research or design decisions into docs. Also use when the conversation is getting long and the user wants to checkpoint progress into files to save context.
testing
autonomous-execution
Rules for maximum agent autonomy. Trigger this skill IMMEDIATELY when you feel the need to ask the user a permission question or ask for instructions such as: 'Should I push?', 'Should I run tests?', 'What should I do next?', 'Is this correct?', etc. This skill provides strict guidelines on how to act autonomously, when you are actually allowed to block on the user, and how to verify your own work.
testing
comprehensive-nextjs-expert
A comprehensive master skill for modern Next.js development using the App Router, React, TypeScript, and Tailwind CSS. Make sure to use this skill whenever the user asks to build, refactor, or debug Next.js applications, server components, or mentions React, RSC, SSR, SSG, or Tailwind CSS within a Next.js context.
development
general-coding-guidelines
General coding rules across all file types to maintain code quality, consistency, and prevent common errors. Make sure to use this skill whenever the user asks you to write code, refactor code, review code, or suggest architectural changes.
development
go-project
Guide for advancing a project implementation by executing tasks from an existing PLAN.md and TODO.md, and keeping the documentation in sync with actual progress. Use this skill whenever the user wants to continue working on a project, implement the next steps, make progress on planned tasks, or says things like 'let's continue', 'next step', 'implement this', 'do the next task', or references an existing PLAN.md or TODO.md. Also use when the user asks to build, code, or implement something that is already described in docs/PLAN.md or docs/TODO.md.
development
prompt-engineering-expert
Apply prompt engineering best practices to write, refine, and optimize system prompts, user prompts, and agent instructions. Use this skill whenever the user wants to write a prompt, optimize an existing prompt for better results, fix a prompt that is hallucinating or underperforming, or structure prompts for Large Language Models (LLMs). Even if the user just says "help me write instructions for my agent", trigger this skill.
testing
prompt-evaluator
Evaluate and score user-written LLM prompts on a 100-point scale across 5 axes (Clarity, Structure, Information Content, Specificity, Context), providing specific improvement suggestions and a revised prompt. Make sure to use this skill whenever the user asks to evaluate, review, score, or improve a prompt, or when they say things like 'このプロンプトどう？', 'プロンプトを評価して', 'rate my prompt', 'review this prompt', or 'is this prompt good enough?'. This skill focuses on scoring existing prompts, not writing new ones from scratch.
development
plain-text-output
Constrains agent output to plain text only: no emojis, no bold (**/__), no italics (*/_). Prefers noun-ending style (体言止め) in Japanese. Make sure to use this skill whenever the user asks for output in plain text, when generating any documentation, commit messages, PR descriptions, or when responding in an environment that requires unadorned text.
documentation
agent-quiz-generator
Generates an interactive educational quiz via a subagent to test the user's understanding of the previous topic. Use this skill when: (1) the user explicitly asks for a 'quiz', 'learning check', 'test', or 'check my understanding', OR (2) you have just explained a highly complex, multi-step concept and want to proactively ensure they grasped the core mental model before moving on. Keywords: quiz, test, check understanding, learning check, assessment.
testing
create-pull-request
Create a GitHub pull request safely and reliably using project conventions. Make sure to use this skill whenever the user asks to create a PR, submit changes for review, open a pull request, or mentions "PR", "プルリク", or "pull request". It handles commit verification, branch validation, and PR creation using the gh CLI.
tools
infographic-creator
Create beautiful infographics based on provided text content. Make sure to use this skill whenever a user requests to create an infographic, chart, diagram, data visualization, or wants to transform data and information into a visual structure, even if they don't explicitly use the word 'infographic'.
development
plan-self-review
Self-evaluate a plan on a 100-point scale after it is created or updated. Make sure to use this skill immediately whenever you create a plan or update a plan, even if the user does not explicitly ask for a review. This skill ensures that the plan is clear, comprehensive, feasible, and consistent before execution.
testing
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
tools
skill-judge
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
testing
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
testing