s-hiraoku
- 127 skills
- 0 followers
- last month last updated
- ▌ Frontend Design 3 · s-hiraokuGuide for creating distinctive, production-grade frontend interfaces. Covers visual design systems, typography, color, motion, spatial composition, and web interface standards. Use when designing UI, establishing design systems, or reviewing visual quality of frontend code.
- ▌ Pr Guardian 4 · s-hiraokuMonitor a pull request after opening it, fix CI failures and agent or reviewer feedback, push updates, and comment with the outcome.
- ▌ Anthropic Skill Creator 3 · s-hiraoku bundleDesign, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
- ▌ Jotai Expert 3 · s-hiraoku bundleExpert guidance for Jotai state management in React applications. Provides best practices, performance optimization, and architectural patterns. Use when designing atom structures, implementing state management, optimizing re-renders, handling async state, integrating with TypeScript, or reviewing Jotai code for performance issues. Triggers on tasks involving Jotai atoms, derived state, focusAtom, splitAtom, atomFamily, or state management architecture decisions.
- ▌ Review 3 · s-hiraokuReview code changes with a bug-first, risk-focused workflow before merge or release.
- ▌ Bug Fix 3 · s-hiraokuFix bugs with reproduction, minimal changes, regression coverage, and targeted verification.
- ▌ Docs Updater 3 · s-hiraokuUpdate documentation after code or behavior changes while keeping docs concise and relevant.
- ▌ Goal Manager 3 · s-hiraoku bundleManage /goal usage for concrete Codex work, including objective writing, success criteria, done criteria, long-running implementation, verification, PR creation, resumption, and completion decisions.
- ▌ Release Check 3 · s-hiraokuCheck whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.
- ▌ Refactor Safely 3 · s-hiraokuRefactor code without behavior changes using small mechanical steps and verification.
- ▌ Feature Implementation 3 · s-hiraokuImplement a feature safely with planning, focused edits, tests, docs, and verification.
- ▌ Release 2 · s-hiraokuBump version in package.json and auto-generate CHANGELOG.md using standard-version for vscode-sidebar-terminal. Triggered by /release or /version commands.
- ▌ Code Review 2 · s-hiraokuPerform structured code reviews focusing on correctness, readability, security, and maintainability. Use this skill when reviewing pull requests, evaluating code changes, or establishing review standards for a team.
- ▌ Synapse Reinst 2 · s-hiraoku bundleRe-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPSE_AGENT_ID. Triggered by /synapse-reinst command.
- ▌ Code Simplifier 3 · s-hiraokuSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. This skill should be used when code-quality checks pass but the code would benefit from structural cleanup — deduplication, branching simplification, naming improvements, or dead-code removal. Invoked as a subagent from /code-quality or directly via the Task tool.
- ▌ Synapse Manager 2 · s-hiraoku bundleMulti-agent management workflow — task delegation, progress monitoring, quality verification with regression testing, feedback delivery, and cross-review orchestration. Use this skill when coordinating multiple agents on a shared task, monitoring delegated work, ensuring quality across agent outputs, or implementing a multi-phase plan (3+ phases or 10+ file changes).
- ▌ Anthropic Skill Creator 2 · s-hiraoku bundleDesign, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
- ▌ Parallel Docs Simplify Sync 2 · s-hiraokuRuns synapse-docs, /simplify, sync-plugin-skills, and github-pages-sync in parallel for synapse-a2a development workflows. Use when you need doc updates, code simplification, plugin skill sync, and site-docs sync at the same time.
- ▌ Tdd 2 · s-hiraokuDrive implementation through red-green-refactor with isolated test design, minimal implementation, and behavior-preserving cleanup.
- ▌ Deslop 2 · s-hiraokuRemove common AI-generated boilerplate and readability noise from changed code without changing behavior.
- ▌ Fix CI 2 · s-hiraokuDiagnose and repair failing CI checks on the current branch or pull request with focused, reproducible fixes.
- ▌ Adviser 2 · s-hiraoku bundleRoute an independent review-only agent to a stronger model tier or reasoning effort at key decision points, then continue the task in the main agent. Use when the user asks for an adviser, advisor, second opinion, stronger review, or Claude Code /advisor-like behavior; before committing to a consequential approach on a multi-step task; when work is stuck or changing direction; and before declaring substantial work complete.
- ▌ No Slop 2 · s-hiraoku bundleStrip AI slop from prose output and raise its information density — filler openings/closings, restated questions, contentless emphasis, stacked hedges, repeated points, structure that outweighs substance — while preserving every fact, number, caveat, and reason (compression, never omission). This is a composable modifier workflow; it changes how prose is written for the current task, not what work is done. Invoke it alongside another skill or task ("write the report, no-slop", "PR 本文を no-slop で") or on its own to rewrite existing text ("deslop this paragraph"). Use whenever the user asks for concise, dense, non-AI-sounding writing or complains that output is verbose, thin, or padded. For removing slop from code (comments, defensive try/except), use the deslop skill instead.
- ▌ Simplify 2 · s-hiraokuRemove avoidable complexity from changed code while preserving behavior exactly.
- ▌ Autopilot 2 · s-hiraoku bundleRun the PR Guardian workflow when the user explicitly invokes $autopilot to keep a GitHub pull request moving toward merge-ready without merging it. Do not select this skill implicitly for ordinary PR follow-up.
- ▌ Jina Reader 2 · s-hiraoku bundleFetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown. Use when an agent needs to read, summarize, quote briefly, extract facts from, or inspect a public URL that normal browsing, scraping, search snippets, or direct fetch tools cannot read cleanly, including JavaScript-heavy pages, reader-hostile pages, X/Twitter posts and threads, articles, GitHub pages, and PDFs. Trigger when the user asks to use Jina, use r.jina.ai, read an otherwise unreadable site, recover readable text from a URL, read an X/Twitter post by URL, or turn a webpage into Markdown.
- ▌ Kaizen Loop 2 · s-hiraoku bundleRun a continuous product improvement loop: evaluate a product or codebase end to end, identify product-quality improvement opportunities, present prioritized recommendations for user approval, then implement only approved improvements through the plan, goal, UI design, testing, review, PR, and merge-readiness workflow. Use when the user asks Codex to assess an app/product, find what can be improved, run a product evaluation, or iteratively improve a product with approval gates.
- ▌ Pr Guardian 3 · s-hiraoku bundleMonitor or resume GitHub pull requests, fix CI failures and actionable CodeRabbit, Codex, bot, or human review feedback, push focused updates, and stop only when the PR is merge-ready or has a concrete external blocker.
- ▌ Meta Packager 2 · s-hiraokuAnalyze recent Codex work and package repeated patterns as the smallest useful skill, custom subagent, hook, or automation. Use when asked to mine sessions, memories, or recent repeated work for reusable Codex assets.
- ▌ Frontend Design 2 · s-hiraokuGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
- ▌
- ▌ Security Review 2 · s-hiraokuReview a diff for concrete security risks across injection, authn/authz, secrets, supply chain, infrastructure, and business logic.
- ▌ UI Imagegen Director 2 · s-hiraoku bundleDirect high-quality frontend UI work by using Codex Image Gen for visual mockups, then implementing the selected direction in code with browser-based visual QA. Use when the user asks for a better-looking web UI, UI mockup, app screen, dashboard, landing page, visual redesign, or wants Image Gen/GPT Image 2 to guide frontend implementation. Avoid for backend-only work or tiny style tweaks that do not need visual direction.
- ▌ Empirical Prompt Tuning 2 · s-hiraoku bundleMethodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements plateau. Use after creating or revising a prompt or skill.
- ▌ Implement To Merge Ready 2 · s-hiraoku bundleRun an end-to-end implementation delivery workflow from user request to merge-ready pull request. Use when the user asks Codex to implement a change and expects planning, goal tracking, UI design where relevant, code edits, tests, self-review, regular ready-for-review PR creation, CI/review follow-up, and bringing the PR as close to mergeable as possible.
- ▌ Synapse A2a 3 · s-hiraoku bundleSynapse A2A agent communication — sending messages, spawning agents, delegating tasks, sharing memory, and coordinating file edits. Use this skill when: running synapse send/reply/broadcast/interrupt, spawning agents with synapse spawn or synapse team start, managing the task board with synapse tasks, sharing knowledge with synapse memory, locking files with synapse file-safety, checking agent status with synapse list/status, or orchestrating any multi-agent workflow.
- ▌ MCP Builder 2 · s-hiraokuThis skill guides building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when creating MCP servers, designing tool interfaces, or implementing protocol handlers.
- ▌ Skill Creator 2 · s-hiraokuThis skill guides creating Claude skills—modular packages that extend capabilities with specialized knowledge and workflows. Use when creating new skills, packaging skills for distribution, or understanding skill architecture.
- ▌ MCP Integration 2 · s-hiraokuThis skill guides connecting MCP servers to Claude Code plugins for external service integration. Use when configuring MCP servers, setting up authentication, or integrating external tools.
- ▌ Agent Development 2 · s-hiraokuThis skill guides creating autonomous agents for Claude Code plugins using markdown files with YAML frontmatter. Use when building new agents, designing agent system prompts, or configuring agent behavior.
- ▌ Post Impl 2 · s-hiraokuWorkflow: Post-implementation workflow using target: self. Runs docs/simplify/sync in parallel, then release, commit all changes, create PR, and autofix with pr-guardian — all injected back into the current agent's own PTY. Mirrors post-impl-codex but stays in-process instead of spawning a separate agent. . Triggered by /post-impl command.
- ▌ Post Impl Codex 2 · s-hiraokuWorkflow: Post-implementation workflow for Codex agents: docs/simplify/sync in parallel, then release, commit all changes, create PR, and monitor with pr-guardian. Uses /code-simplifier instead of /simplify (Claude Code built-in). . Triggered by /post-impl-codex command.
- ▌ Post Impl Claude 2 · s-hiraokuWorkflow: Post-implementation workflow for Claude Code agents: docs/simplify/sync in parallel, then release, commit all changes, create PR, and autofix with /autofix-pr. . Triggered by /post-impl-claude command.
- ▌ Jotai Expert 2 · s-hiraoku bundleExpert skill for the Jotai state management library. Use when implementing atom-based state management in React applications. Use this skill for: (1) Jotai atom design and implementation (2) Derived atoms, async atoms, atomFamily implementation (3) Refactoring based on Jotai best practices (4) Performance optimization (selectAtom, splitAtom, etc.) (5) Persistence (localStorage/sessionStorage integration) (6) TypeScript type definitions (7) Test implementation Triggered when users ask questions or request implementations related to "Jotai", "atom", or "state management".
- ▌ Ask User Question 2 · s-hiraokuThis skill provides structured question-asking capabilities for gathering user input, clarifying requirements, and making decisions during task execution. Use this skill when needing to present multiple choice questions, gather preferences, or get user confirmation on implementation choices.
- ▌ Canvas Design 2 · s-hiraokuCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
- ▌ Review 2 · s-hiraokuReview code changes with a bug-first, risk-focused workflow before merge or release.
- ▌ Bug Fix 2 · s-hiraokuFix bugs with reproduction, minimal changes, regression coverage, and targeted verification.
- ▌ Pr Guardian 2 · s-hiraokuMonitor a pull request after opening it, fix CI failures and agent or reviewer feedback, push updates, and comment with the outcome.
- ▌ Docs Updater 2 · s-hiraokuUpdate documentation after code or behavior changes while keeping docs concise and relevant.
- ▌ Goal Manager 2 · s-hiraoku bundleManage /goal usage for concrete Codex work, including objective writing, success criteria, done criteria, long-running implementation, verification, PR creation, resumption, and completion decisions.
- ▌ Release Check 2 · s-hiraokuCheck whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.
- ▌ Refactor Safely 2 · s-hiraokuRefactor code without behavior changes using small mechanical steps and verification.
- ▌ Feature Implementation 2 · s-hiraokuImplement a feature safely with planning, focused edits, tests, docs, and verification.
- ▌ Post Impl · s-hiraokuWorkflow: Post-implementation workflow using target: self. Runs docs/simplify/sync in parallel, then release, commit all changes, create PR, and autofix with pr-guardian — all injected back into the current agent's own PTY. Mirrors post-impl-codex but stays in-process instead of spawning a separate agent. . Triggered by /post-impl command.
- ▌ Post Impl Codex · s-hiraokuWorkflow: Post-implementation workflow for Codex agents: docs/simplify/sync in parallel, then release, commit all changes, create PR, and monitor with pr-guardian. Uses /code-simplifier instead of /simplify (Claude Code built-in). . Triggered by /post-impl-codex command.
- ▌ Post Impl Claude · s-hiraokuWorkflow: Post-implementation workflow for Claude Code agents: docs/simplify/sync in parallel, then release, commit all changes, create PR, and autofix with /autofix-pr. . Triggered by /post-impl-claude command.
- ▌ Synapse A2a 2 · s-hiraoku bundleThis skill provides comprehensive guidance for inter-agent communication using the Synapse A2A framework. Use this skill when sending messages to other agents via synapse send/reply commands, understanding priority levels, handling A2A protocol operations, managing task history, configuring settings, or using File Safety features for multi-agent coordination. Automatically triggered when agent communication, A2A protocol tasks, history operations, or file safety operations are detected.
- ▌ Code Simplifier 2 · s-hiraokuSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. This skill should be used after implementing features or bug fixes to clean up code, when refactoring for readability, or when reducing unnecessary complexity. It launches the code-simplifier subagent provided by the code-simplifier@claude-plugins-official plugin.
- ▌ Handover · s-hiraokuGenerate a HANDOVER.md shift-change report summarizing the current session for the next Claude. Use when the user types /handover, asks to "create a handover", "write a handoff document", "save session context", or wants to capture what was done, decisions made, and next steps before ending a session. Do not use for general documentation, READMEs, changelogs, or git commit messages.
- ▌ Jina Read Url · s-hiraoku bundleRead, summarize, inspect, or extract content from a public URL through Jina Reader. Use when the user asks to use Jina Reader, read a note.com/blog/article/X/Twitter/GitHub/page URL, recover Markdown from a URL that normal browsing cannot read cleanly, or make a URL readable in ChatGPT-like agent sessions with tool access.
- ▌ Retrospective Codify · s-hiraoku bundleConvert review feedback, CI failures, bug fixes, or task retrospectives into a durable project feedback ledger, then make future implementation work consult that ledger before planning.
- ▌ Land · s-hiraoku bundleLand a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.
- ▌ Pull · s-hiraokuPull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.
- ▌ Push · s-hiraokuPush current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.
- ▌ Debug · s-hiraokuInvestigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.
- ▌ Code Quality · s-hiraokuRun code quality checks (ruff, mypy, pytest) and optionally simplify code. This skill should be used when the user wants to check code quality, run linters, run tests, or simplify recently modified code. Triggered by /lint, /check, or /code-quality commands.
- ▌ Vscode Tdd Expert · s-hiraoku bundleThis skill provides expert-level guidance for Test-Driven Development (TDD) in VS Code extension development following t-wada methodology. Use when writing tests before implementation, creating comprehensive test suites, implementing Red-Green-Refactor cycles, or improving test coverage for extension components like WebViews, terminal managers, and activation logic.
- ▌ Vscode Test Setup · s-hiraoku bundleThis skill provides comprehensive guidance for setting up and configuring test environments for VS Code extension projects. Use when initializing a new test infrastructure, configuring test runners (Vitest), setting up CI/CD test pipelines, integrating coverage tools (v8/c8), or troubleshooting test configuration issues.
- ▌ Sync Plugin Skills · s-hiraokuThis skill synchronizes plugin skills (plugins/synapse-a2a/skills/) with the current implementation, README.md, and guides folder. Use this skill when implementation changes have been made, new features added, or documentation updated, to ensure plugin skills stay up-to-date. Triggered by /sync-plugin-skills command or when significant code changes are detected.
- ▌ Vscode Extension Expert · s-hiraokuThis skill provides expert-level guidance for VS Code extension development. Use when implementing new extension features, debugging extension code, designing WebView UIs, implementing Language Server Protocol features, or optimizing extension performance. Covers activation events, contribution points, VS Code API patterns, security best practices, testing strategies, and publishing workflows.
- ▌ Tdd · s-hiraokuDrive development with red-green-refactor using isolated test-writer, implementer, and refactorer subagents so tests reflect intent rather than anticipated implementation.
- ▌ Deslop · s-hiraokuRemove AI-generated boilerplate (vague comments, unused try/except, defensive validation, restated docstrings) from changed code without changing behavior.
- ▌ Fix CI · s-hiraokuDiagnose and repair failing CI checks on the current PR by parsing logs, reproducing locally when possible, and pushing focused fixes in batches.
- ▌ Review · s-hiraokuReview code changes with a bug-first, risk-focused workflow before merge or release.
- ▌ Adviser · s-hiraoku bundleRoute an independent, review-only Claude process to a deterministically stronger model or effort when native Advisor is unavailable. Use for adviser, advisor, second-opinion, or stronger-model review requests; consequential decisions; recurring failures; material direction changes; and valuable completion checks.
- ▌ Bug Fix · s-hiraokuFix bugs with reproduction, minimal changes, regression coverage, and targeted verification.
- ▌ No Slop · s-hiraoku bundleMODIFIER skill that removes AI slop from prose without losing source facts or uncertainty. Use with any writing task or to rewrite text; for code slop, use deslop instead.
- ▌ Simplify · s-hiraokuReview changed code on the current branch for reuse, clarity, and dead complexity, then propose or apply minimal cleanup without changing behavior.
- ▌ Autopilot · s-hiraoku bundleExplicitly keep a GitHub pull request moving until it is merge-ready by delegating to PR Guardian. Invoke manually with /autopilot; Claude must not start it automatically.
- ▌ Jina Reader · s-hiraoku bundleFetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown. Use when an agent needs to read, summarize, quote briefly, extract facts from, or inspect a public URL that normal browsing, scraping, search snippets, or direct fetch tools cannot read cleanly, including JavaScript-heavy pages, reader-hostile pages, X/Twitter posts and threads, articles, GitHub pages, and PDFs. Trigger when the user asks to use Jina, use r.jina.ai, read an otherwise unreadable site, recover readable text from a URL, read an X/Twitter post by URL, or turn a webpage into Markdown.
- ▌ Kaizen Loop · s-hiraokuRun a continuous product improvement loop: evaluate a product or codebase, present prioritized recommendations for approval, then implement only approved improvements through verification and PR follow-up.
- ▌ Docs Updater · s-hiraokuUpdate documentation after code or behavior changes while keeping docs concise and relevant.
- ▌ Goal Manager · s-hiraoku bundleManage durable task goals for long-running Claude Code work using the project ledger, including objective writing, success criteria, resumption, and completion decisions.
- ▌ Meta Packager · s-hiraokuAnalyze recent Claude Code work and package repeated patterns as the smallest useful skill, custom subagent, slash command, hook, or automation. Use when asked to mine prompts, sessions, shell history, or recent repeated work for reusable Claude Code assets.
- ▌ Release Check · s-hiraokuCheck whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.
- ▌ Teach Session · s-hiraokuTeach the human everything that happened in this session until they can demonstrably explain it, using an incremental checklist, restate-first probing, and AskUserQuestion quizzes. Use after a non-trivial change, debugging session, or hand-off when the goal is the human's understanding, not just a working result.
- ▌ Refactor Safely · s-hiraokuRefactor code without behavior changes using small mechanical steps and verification.
- ▌ Review Briefing · s-hiraoku bundlePrepare a verdict-first, read-only HTML briefing that helps a human review a pull request quickly and well. Use with a PR number or URL; opens in the browser with a terminal fallback.
- ▌ Security Review · s-hiraokuRun a multi-pass security review over the current diff using parallel specialist subagents focused on injection, authn/authz, secrets, supply-chain, and infrastructure-as-code risks.
- ▌ Finish Pr Feedback · s-hiraoku bundleCompatibility alias for pr-guardian. Use pr-guardian for stalled pull requests, CodeRabbit/Codex review feedback, CI failures, unresolved review conversations, and merge-ready PR follow-up.
- ▌ UI Imagegen Director · s-hiraokuDirect high-quality frontend UI work by using image-generated mockups when useful, translating the chosen direction into code, and verifying the rendered UI in a browser.
- ▌ Feature Implementation · s-hiraokuImplement a feature safely with planning, focused edits, tests, docs, and verification.
- ▌ Empirical Prompt Tuning · s-hiraokuIteratively improve a skill or prompt by having a fresh subagent execute it against fixed scenarios, scoring two-sided (executor self-report + a pre-frozen requirements checklist), and looping until improvements plateau. Use after authoring or revising any skill, slash command, or CLAUDE.md addition.
- ▌ Implement To Merge Ready · s-hiraokuRun an end-to-end Claude Code delivery workflow from user request to merge-ready pull request, including planning, implementation, tests, self-review, ready-for-review PR creation, CI/review follow-up, and final status.
- ▌ Long Running Orchestrator · s-hiraokuRun multi-hour or multi-session work safely by combining the ledger, checkpoints, cost-ceiling guard, and resumable progress notes so context loss does not erase progress.
- ▌ Jotai Expert · s-hiraoku bundleJotai状態管理ライブラリのエキスパートスキル。Reactアプリケーションでのatomベースの状態管理を実装する際に使用。以下の場合にこのスキルを使用: (1) Jotaiのatom設計・実装 (2) 派生atom、非同期atom、atomFamilyの実装 (3) Jotaiのベストプラクティスに基づくリファクタリング (4) パフォーマンス最適化（selectAtom、splitAtom等） (5) 永続化（localStorage/sessionStorage連携） (6) TypeScript型定義 (7) テスト実装 ユーザーが「Jotai」「atom」「状態管理」に関する質問や実装依頼をした場合に発動。
- ▌ Canvas Design · s-hiraokuCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
- ▌ Ask User Question · s-hiraokuThis skill provides structured question-asking capabilities for gathering user input, clarifying requirements, and making decisions during task execution. Use this skill when needing to present multiple choice questions, gather preferences, or get user confirmation on implementation choices.
- ▌ MCP Builder · s-hiraokuThis skill guides building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when creating MCP servers, designing tool interfaces, or implementing protocol handlers.