claude-resources

Open the current PR in the web browser.

Prepare a git worktree for development on a GitHub issue.

Calculate Z coordinates for stacking/merging objects in Bambu Studio.

Copy current working directory to clipboard using pbcopy.

Output the full absolute path of a file mentioned in the previous message.

Queue the next task to do after the current one finishes

code reviewer

Frontend developer agent for implementing code changes. Applies TDD for logic and pragmatic testing for UI. Works autonomously with clear communication.

Frontend developer agent that works inside a git worktree as part of an agent team. Implements features, commits, pushes, and creates PRs targeting the base branch. Reports back to the manager when done.

markdown file generator for creating markdown formatted text files based on user-provided context. It handles file management, URL formatting, and follows strict guidelines for markdown generation.

markdown writer

Git pull-push sync agent for a single repository. Handles fetch, pull with rebase, conflict resolution, and push.

researcher

text fix agent.

Write articles for zpaper (personal blog) at the zpaper repository. Receives a detailed writing brief and produces a complete article following zpaper conventions.

Write articles for CodeGrid at the takazudo-codegrid-writing repository. Receives a detailed writing brief and produces a complete article following CodeGrid conventions.

Write articles for esa (internal blog) at the takazudo-esa-writing repository. Receives a detailed writing brief and produces a complete article following esa conventions.

Create and validate ASCII circuit diagrams with automatic rule checking and iterative refinement. Use when the user requests circuit diagrams in ASCII/text format, or when creating technical documentation with embedded schematics. Ensures golden rules (no line crossings without junctions, no lines crossing labels, proper component connections, correct polarity). Includes preview validation using monospace rendering.

Guide for setting up before-push validation (b4push) and CI checking. Covers analyzing project structure, creating run-b4push.sh, adding package.json entry, creating project-specific b4push skill, setting up GitHub Actions CI. Use when: (1) User says 'set up b4push', 'add CI', 'before push checks', (2) Setting up a new project's validation workflow, (3) User wants CI + local validation.

Plan implementation by breaking work into one epic GitHub issue + child sub-issues. Use when: (1) User says '/big-plan', (2) User wants to plan an implementation before coding, (3) User wants to split a feature into small issues for parallel agent team work, (4) User references existing issues (e.g. 'implement issue #123', 'plan all open issues', 'plan recent 3 open issues'). Auto-reads project-scope l-lessons-* skills (from /retro-notes) before planning. Supports -co/-gco/-gcoc flags for second opinions and post-creation verification (runnable in parallel). Large scope is kept in ONE epic and sequenced into dependency waves run via /x-wt-teams --stay. Planning only — no code changes.

Share Claude Code resources (memories, settings, skills, hooks, etc.) across projects via the centralized claude-settings repo. Use when: (1) User says 'share claude resource', 'sync settings', or 'export to claude-settings', (2) User wants to copy .claude/* files to the central repo, (3) Reusing memory or skills across projects, (4) Backing up local Claude config to the global repo.

Refactor and optimize CLAUDE.md files in a repository. Analyzes the existing setup, explores repo structure, proposes splitting CLAUDE.md into a hierarchical directory-scoped structure. Use when: (1) User wants to optimize CLAUDE.md, (2) Root CLAUDE.md is too large, (3) User wants to split CLAUDE.md into directory-scoped files, (4) User mentions 'refactor CLAUDE.md', 'split CLAUDE.md', or 'organize CLAUDE.md'.

Get a second opinion from OpenAI Codex CLI on a plan or approach. Use when: (1) During planning phase of /x-as-pr or /x-wt-teams to validate the approach, (2) User says 'codex 2nd', 'second opinion', or 'codex opinion', (3) Wanting an alternative perspective before committing to a plan. Sends context and plan to codex, returns feedback. Called automatically by /x-as-pr and /x-wt-teams during planning.

Web research using OpenAI Codex CLI (codex exec). PREFERRED over general web research. Use when: (1) User says 'research', 'codex research', 'look up', or 'investigate', (2) Researching libraries, APIs, best practices, or technical topics, (3) Gathering information from the web. Codex performs research, Claude Code synthesizes. Falls back to Claude Code researcher subagent if codex unresponsive.

Code review using OpenAI Codex CLI (codex exec review). PREFERRED over /light-review for code review. Use when: (1) User says 'review', 'code review', or 'codex review', (2) After implementation when quality check is needed, (3) Child agents self-reviewing. Runs multiple codex review instances in parallel. Falls back to Claude Code if codex unresponsive.

Translation using OpenAI Codex CLI (codex exec). PREFERRED for translation. Use when: (1) User says 'translate', 'codex translate', 'translation', or 'codex translator', (2) Translating between languages (Japanese, English, etc.), (3) Translating documentation, comments, or UI strings. Codex drafts, Claude Code reviews and writes. Falls back to Claude Code if codex unresponsive.

Document writing using OpenAI Codex CLI (codex exec). PREFERRED over general writing tasks. Use when: (1) User says 'write document', 'write docs', 'codex write', or 'codex writer', (2) Writing README, documentation, or technical content, (3) Drafting text content. Codex drafts, Claude Code reviews and writes. Falls back to Claude Code if codex unresponsive.

Enable automatic committing mode. From now on, commit changes automatically without asking for permission. Use when: (1) User says 'commits auto', 'auto commit', 'commit automatically', (2) User wants hands-off development.

Disable automatic committing. From now on, do NOT make commits unless the user explicitly asks. Used during try-and-error development. Use when: (1) User says 'commits forbid', 'no auto commit', 'don't commit automatically', (2) User wants to experiment without committing.

Commit necessary changes with appropriate separation. Use when: (1) User says 'commit', 'commits', or 'save changes', (2) Claude has made changes that need committing, (3) User wants commits with proper grouping and conventional messages. Handles .gitignore updates, file selection, logical grouping, clean commit messages.

Generate or update .github/copilot-instructions.md for GitHub Copilot. Use when: (1) User wants to create Copilot instructions, (2) User asks to update existing Copilot guidelines, (3) User mentions 'copilot instructions', 'copilot guidelines', or 'copilot config'. Explores codebase for tech stack, file conventions, import patterns, code style, testing. Creates actionable instructions with code examples.

Create and manage custom slash commands in Claude Code. Use when: (1) User wants to create a new slash command, (2) User asks about /commands or custom commands, (3) User wants to automate frequent prompts, (4) User says 'create global command' or 'create local command', (5) User mentions 'command-creator'. Covers creation (global/local), command anatomy, frontmatter, arguments, bash, file references, namespacing, command vs skill comparison.

Deep code quality review focused on structure, refactoring, and best practices. Use when: (1) User says 'review', 'deep review', or 'code review', (2) After implementation when a quality check is needed, (3) Before marking a PR as ready. Default backend is /gcoc-review (zero Premium). Opt into Claude reviewers with -haiku|-so|-op (auto-detects PR vs full-project mode). Supports -co|-gco|-gcoc external backends. Default team-fix mode (-t) delegates fixes to /x-wt-teams --no-review --stay; pass -nt/--no-team for inline fixes.

Comprehensive dependency update workflow for resolving Dependabot alerts and PRs. Use when: (1) User wants to update dependencies, (2) User mentions 'dependabot', 'security vulnerabilities', or 'dependency updates', (3) User asks to run security audit, (4) User wants to create a deps-update PR. Analyzes Dependabot issues, runs pnpm audit, applies updates, runs quality checks (typecheck, lint, test, build), handles Playwright Docker image sync, creates PR with changelog.

Add self-hosted runner support with automatic fallback to GitHub-hosted runners in GitHub Actions workflows. Use when: (1) User wants to add self-hosted runner support, (2) User says 'self-hosted runner', 'add self runner', 'self-hosted fallback', (3) User wants to save GitHub Actions minutes.

Add IFTTT webhook notification to a GitHub Actions CI/CD workflow. Use when: (1) User wants CI deploy notifications via IFTTT, (2) User says 'add IFTTT notify', 'CI notification', or 'deploy notification', (3) User wants webhook notifications for build/deploy status.

Set up Cloudflare Pages deployment with GitHub Actions workflows. Use when: (1) Deploying a static site to Cloudflare Pages, (2) User says 'cloudflare pages', 'deploy to cloudflare', 'cf pages setup', (3) User wants CI/CD workflows for Cloudflare Pages with PR previews, (4) Setting up wrangler deployment pipelines.

Create a before-push validation script (b4push) and project-level b4push skill. Analyzes the project, identifies check steps (quality, build, test, doc site, e2e), generates scripts/run-b4push.sh, adds package.json entry, creates .claude/skills/b4push/skill.md. Use when: (1) User says 'create b4push', 'add b4push', 'before push script', (2) Setting up a new project's CI/validation workflow.

Electron app development patterns for thin wrapper apps around dev servers. Use when: (1) Building Electron apps as thin wrappers around web apps, (2) Managing dev server processes in Electron, (3) Handling nodenv/anyenv PATH issues in spawned processes, (4) Packaging with electron-builder, (5) Sharing modules across multiple Electron apps (extraResources), (6) Dynamic project root resolution in packaged apps, (7) Opening external links in default browser.

Capture web pages and send them to Figma as editable design files. Use when: (1) User wants to capture a webpage to Figma, (2) User says 'figma capture', 'send to figma', 'capture to figma', (3) User provides URLs to convert to Figma designs

Provide Figma capture script installation guidance for web projects. Use when: (1) User wants to set up Figma capture in a web dev project, (2) User says 'figma script install', 'add figma capture', 'figma setup', (3) User wants to enable browser-to-Figma capture in their dev environment

Create a GitHub Actions workflow that auto-merges a production branch into a documentation branch. Use when: (1) Setting up auto-sync from production to doc branch, (2) User mentions 'doc auto merge', 'auto sync docs', 'document branch sync', (3) User wants docs to stay up-to-date with production automatically.

Add IFTTT webhook notification to a GitHub Actions workflow for mobile push notifications on deploy success/failure. Use when: (1) Adding deploy notifications to CI/CD, (2) Setting up IFTTT webhook in GitHub Actions, (3) User mentions 'IFTTT notify', 'deploy notification', 'push notification for CI'.

Develop npm packages with Node.js and TypeScript following modern best practices. Use when: (1) Creating a new npm package, (2) Setting up package.json exports (dual ESM/CJS or ESM-only), (3) Configuring TypeScript for library authoring (Bundler or Node16 moduleResolution), (4) Building/publishing with tsup or tsc, (5) Creating CLI tools with bin field, (6) Testing with vitest, (7) CI/CD for npm publishing, (8) ESM/CJS interop issues. Keywords: npm package, publish to npm, library development.

Audit project dependencies and replace CLI-only tools with npx/pnpm dlx to reduce installed packages. Use when: (1) User wants to reduce dependencies, (2) User says 'npxify', 'dlxify', 'reduce deps', (3) User wants to clean up package.json, (4) User asks which deps can use npx/pnpm dlx.

Organize and maintain package.json and npm config (.npmrc) for readability and security. Use when: (1) Reorganizing scripts section or adding separators, (2) Extracting multi-process commands into shell scripts, (3) Setting up multi-environment dev commands (local/preview/prod), (4) Handling pnpm "Ignored build scripts" warnings, (5) Configuring .npmrc security (strictDepBuilds, allowBuilds, ignoredBuilds), (6) Managing pnpm via corepack and packageManager field, (7) Adding predev port cleanup. Keywords: package.json, npm scripts, .npmrc, pnpm, build scripts, supply chain, corepack, packageManager, predev, kill port, port in use.

Big-bang move a repository to a new remote, stripping commit history and purging private info. Use when: (1) User says 'bigbang move', 'repo move', or 'move repo', (2) User wants to move a repo to a new remote while cleaning out client/private information, (3) User needs to start fresh in a new repo without commit history.

Add Open Graph (OGP) and Twitter Card meta tags for social media link previews. Use when: (1) User says 'add OGP', 'og tags', 'social preview', 'link preview', (2) Setting up SEO meta tags for a new site, (3) User wants og:image or Twitter cards, (4) User mentions 'OGP', 'Open Graph', 'twitter:card', 'social sharing'.

Tweak serve/dev commands in package.json. Use when: (1) User says 'tweak serve', 'dev tweak serve', or 'tweak-serve', (2) User wants to add port-kill before dev/serve (--kill), (3) User wants :net LAN-accessible variants of dev/serve (--net). Flags: --kill adds predev port cleanup, --net adds 0.0.0.0 host variants.

Download KiCad footprints and symbols from LCSC/EasyEDA for JLCPCB PCBA projects. Use when: (1) User asks to download KiCad footprints or symbols from LCSC, (2) User provides LCSC part numbers (e.g., C3975094, C2927029), (3) User is setting up a KiCad project for JLCPCB assembly, (4) User needs exact symbol-footprint combinations for PCBA, or (5) User is working on hardware/PCB projects requiring component libraries from JLCPCB.

Read the currently selected Figma element and work with it. Use when: (1) User says 'figrefer', 'figma refer', 'check my figma selection', (2) User wants to implement or analyze a design selected in Figma desktop app, (3) User says 'what am I selecting in figma', 'implement this figma design'

Format markdown (.md) and MDX (.mdx) files using @takazudo/mdx-formatter. Use when: (1) User wants to format markdown files, (2) User mentions 'format md', 'prettify markdown', or 'fix markdown formatting', (3) Markdown/MDX files need consistent formatting. Features: remark-based AST formatting, MDX (JSX, imports/exports), Japanese text, HTML→md conversion, Docusaurus admonitions, GFM (tables, strikethrough, task lists).

Get a second opinion from GitHub Copilot CLI on a plan or approach. Use when: (1) Planning phase of /x-as-pr or /x-wt-teams to validate the approach, (2) User says 'gco 2nd', 'copilot 2nd', or 'copilot opinion', (3) Wanting an alternative perspective before committing to a plan.

Web research using GitHub Copilot CLI. Use when: (1) User says 'gco research', 'copilot research', or 'copilot look up', (2) Researching libraries, APIs, best practices, or technical topics, (3) Gathering information from the web. Copilot performs research, Claude Code synthesizes. Falls back to Claude Code researcher subagent if Copilot unavailable.

Code review using GitHub Copilot CLI. Use when: (1) User says 'gco review' or 'copilot review', (2) After implementation for quality check, (3) Child agents self-reviewing. Runs Copilot to review the diff, synthesizes findings. Falls back to Claude Code if Copilot unavailable.

Stack trace / error analysis using GitHub Copilot CLI. Use when: (1) User says 'read stack trace', 'debug this error', 'what does this trace mean', (2) User pastes a stack trace or error output, (3) User provides a file path with an error log. Passes the trace to Copilot for structured debugging pointers. Diagnostic only — no fixes. Falls back to Claude direct analysis if Copilot unavailable.

Translation using GitHub Copilot CLI (free GPT-4.1 tier). PREFERRED when Codex quota is low. Use when: (1) User says 'gco translate', 'copilot translate', or '/gco-translate', (2) Translating between languages (Japanese, English, etc.), (3) Translating documentation, comments, or UI strings with zero token cost. Copilot drafts, Claude Code reviews and writes. Falls back to Claude Code if Copilot rate-limited.

Run GitHub Copilot CLI as a read-only sub-agent from Claude Code. Use when: (1) User says 'gco', 'copilot', or 'ask copilot', (2) Delegating code review or research to Copilot, (3) Getting a second opinion on code or architecture. Read-only mode (no file writes), claude-opus-4.6 model.

Second opinion from GitHub Copilot CLI cheap mode — same as /gco-2nd but forces the free gpt-4.1 model. Use when: (1) User says 'gcoc 2nd' or 'copilot cheap 2nd', (2) Premium quota is exhausted, (3) Plan is simple enough that gpt-4.1 feedback suffices.

Web research using GitHub Copilot CLI cheap mode — same as /gco-research but forces the free gpt-4.1 model. Use when: (1) User says 'gcoc research' or 'copilot cheap research', (2) Premium quota is exhausted, (3) Research topic is simple and doesn't need opus reasoning.

Code review using GitHub Copilot CLI cheap mode — same as /gco-review but forces the free gpt-4.1 model. Use when: (1) User says 'gcoc review' or 'copilot cheap review', (2) Premium quota is exhausted and you want zero Premium consumption, (3) Diff is small/simple.

GitHub Copilot CLI cheap mode — same as /gco but forces the free gpt-4.1 model. Use when: (1) User says 'gcoc', 'copilot cheap', or 'ask copilot cheap', (2) Premium quota is low/exhausted, (3) Task doesn't need opus reasoning — simple lookups, quick reviews, translations. Read-only (no file writes).

GitHub Actions workflow best practices and pitfalls reference. Use when: (1) Writing or reviewing .yml workflows, (2) Setting up CI/CD pipelines, (3) Debugging slow, expensive, or stuck workflow runs, (4) User says 'gh actions', 'github actions', 'workflow best practices', (5) Before creating or modifying any .github/workflows/ file. Keywords: GitHub Actions, CI/CD, workflow, timeout, concurrency, security, caching.

Fetch a GitHub issue with all attachments (images, screenshots) downloaded locally so Claude can read them. Use PROACTIVELY when: (1) User provides a GitHub issue URL, (2) User asks to read/view/check a GitHub issue, (3) User references an issue number, (4) User asks about issue screenshots or images. Ensures Claude can see issue-embedded images that are otherwise inaccessible via API.

Create GitHub issues with embedded images via CLI. Uploads images as GitHub release assets and embeds them in the issue body. Use when: (1) Creating an issue that needs screenshots, (2) Programmatically attaching images without browser UI, (3) User says 'issue with images', 'gh issue with imgs', or 'create issue with screenshots'.

Filtered squash merge: take only matching paths (e.g., doc/) from a source branch and apply them to a target branch via squash merge, PR creation. Use when: (1) User says 'filtered merge', 'sync doc to develop', 'cherry-pick directory', (2) User wants to sync a subset of changes between branches, (3) User needs to apply only specific directory or file changes from one branch to another.

Clean up both local and remote git branches that have been merged. Use when: (1) User says 'prune branches', 'clean up branches', or 'delete merged branches', (2) User wants to clean both local and remote branches at once, (3) After a round of PR merging when stale branches accumulate.

Clean up local git branches that have been merged into main/master. Use when: (1) User says 'prune local branches' or 'clean local branches', (2) User wants to delete only local merged branches without touching remote.

Clean up remote git branches that have been merged into origin/main. Use when: (1) User says 'prune remote branches' or 'clean remote branches', (2) User wants to delete only remote merged branches without touching local.

Sync all personal repos across machines via git pull & push. Use when: (1) User says 'globalsync', 'sync repos', 'pull push all', (2) User wants to sync their daily resources across machines, (3) User starts or ends a work session and needs repos up to date.

Convert KiCad exported BOM and position files to JLCPCB PCBA order format. Use when: (1) User has KiCad BOM CSV and .pos files, (2) User needs to prepare files for JLCPCB PCBA ordering, (3) User mentions converting KiCad exports for JLCPCB, (4) User asks about CPL (Component Placement List) format. Handles BOM conversion (Designation→Comment, sorting), CPL conversion (negating Y, adding mm suffix), integrates with jlcpcb-component-finder for LCSC numbers.

Download or update the JLCPCB electronic components database for the jlcpcb-component-finder skill. Use when: (1) User says 'update jlcpcb db', 'download jlcpcb database', 'refresh parts database', (2) The jlcpcb-component-finder skill reports database not found, (3) User wants to get the latest component data from JLCPCB/LCSC, (4) User says 'update db', 'update parts db'. Downloads ~11 GB split-zip database from yaqwsx.github.io/jlcparts.

Search the JLCPCB electronic components database (~7M parts) for hardware projects. Use when: (1) Finding components (resistors, capacitors, inductors, ICs, connectors, diodes, transistors, MOSFETs, op-amps, microcontrollers, sensors, LEDs, voltage regulators, audio jacks, etc.), (2) Looking up part numbers, LCSC (C-prefix), or manufacturer part numbers, (3) Finding alternatives/equivalents, (4) Checking stock at JLCPCB/LCSC, (5) Getting specs (package, footprint), (6) Searching SMD or through-hole parts. Keywords: JLCPCB, LCSC, PCB parts, SMT, PCBA, BOM, component sourcing.

Edit and create KiCad schematic (.kicad_sch) files. Use when user says 'edit schematic', 'modify kicad', 'add component', 'change resistor value', 'update schematic'. Capabilities: (1) Modify schematics (change values, add/remove components, update connections), (2) Create new schematic content from specs or ASCII diagrams, (3) Analyze structure. KiCad 6+ S-expression format. Generated schematics may need GUI layout adjustment.

Fix SVG files for KiCad PCB import. Handles compound paths with holes (splits into separate paths), Illustrator DPI scale correction (72 to 96 DPI), and style cleanup. Use when: (1) User wants to import SVG into KiCad, (2) SVG has shapes with holes/cutouts that KiCad mangles, (3) SVG from Illustrator imports at wrong scale, (4) User says 'fix svg', 'kicad svg', 'svg import', or 'svg fix'.

Build and install the CCResDoc Tauri app locally. Use when: (1) User says 'build ccresdoc', 'rebuild ccresdoc', 'install ccresdoc', or 'l-ccresdoc-build', (2) User wants a fresh CCResDoc.app after changing Rust, frontend loading page, or doc site code under $HOME/.claude/doc/. Runs cargo clean -p, cargo tauri build, kills running app, replaces /Applications copy, clears quarantine.

Enable autonomous testing and verification mode where Claude thoroughly tests its own work. Use when: (1) User says 'lazy dev', 'test your own work', or 'verify it yourself', (2) User is busy and wants Claude to autonomously test and iterate, (3) User wants hands-off development where Claude finds and fixes issues.

Lightweight code review. Dispatches to GitHub Copilot CLI (/gcoc-review) by default, or to Claude / Codex / Copilot-Opus depending on flags. Use when: (1) Quick review of a small change, (2) Child agents self-reviewing before reporting to manager, (3) User says 'light review' or 'quick review', (4) Review is needed but /deep-review is overkill. Always operates in PR/diff mode.

Run Lighthouse audits on a project's built site, create a GitHub issue with findings, then optionally fix via /x-wt-teams. Use when: (1) User says 'lighthouse audit', 'lighthouse', 'performance audit', or 'audit website', (2) User wants to improve performance, accessibility, SEO, or best practices. Optional URL argument; default flow builds project and serves locally.

Record the current Claude Code conversation as a markdown file under $HOME/cclogs/{slug}/ for later reuse (memos, blog drafts, esa). Use when: (1) User says 'log conversation', 'record conversation', 'log-conversation', 'start logging', 'stop logging', (2) User invokes /log-conversation directly with args like -a, --all, -e, --end, or a number, (3) User wants to snapshot the chat to articlify or quote later.

Browse and read recent logs and artifacts from $HOME/cclogs/{slug}/. Use when: (1) User wants to see recent agent logs, (2) User says 'logrefer', 'show logs', 'recent logs', (3) User wants to read a specific log file from a previous session.

Use proactively whenever generating Mermaid diagram code in any context (markdown blocks, .md files, docs). Covers flowcharts, sequence, class, state, ER, gantt, pie, mindmaps, timelines, and all Mermaid types. Applies strict syntax rules to prevent rendering errors (HTML tags, style directives, invalid escapes). No explicit request needed — load automatically when Mermaid syntax is being produced.

GitHub Actions workflows that deploy to Netlify with netlify-cli, or running 'netlify dev' / 'netlify functions:serve' locally. Covers monorepo 'Projects detected' errors, pnpm workspace deploys, deploying pre-built directories, capturing deploy URLs, GitHub secrets setup, netlify.toml inheritance with branch deploys, isolating sub-site deploys, netlify dev with --filter, pnpm 10.x trust store errors, CLI crash workarounds. Keywords: netlify deploy, github actions netlify, netlify-cli, monorepo deploy, pnpm workspace netlify, netlify dev, netlify functions serve.

Combine multiple PDF files into a single PDF. Use when: (1) User wants to merge PDF files, (2) User mentions 'combine PDFs', 'merge PDFs', or 'join PDFs', (3) User has multiple PDFs that need to be consolidated. Respects file order: when given a directory, files are sorted alphabetically; when given specific file paths, the order provided is preserved.

Complete a pull request by monitoring CI checks and merging when ready. Use when: (1) User says 'complete pr', 'merge pr', or 'finish pr', (2) PR is reviewed and ready but CI may still be running, (3) User wants to wait for CI and auto-merge.

Review current PR and make improvement edits without committing. Use when: (1) User says 'suggestion edit', 'suggest improvements', or 'review and edit', (2) User wants code quality improvements as unstaged edits for selective PR creation. Companion to /pr-make-suggestion-to-pr.

Create separate suggestion PRs from unstaged edits, each based on the current PR branch. Use when: (1) User says 'suggestion to pr' or 'create suggestion PRs', (2) After /pr-make-suggestion-edit has left unstaged changes that need to be turned into separate PRs by topic.

Recreate a PR with clean commit history when it has too many messy commits. Use when: (1) User says 'recreate pr' or 'clean up pr history', (2) A PR has accumulated try-and-error commits and needs a fresh start, (3) User wants to squash messy history into clean logical commits.

Update an existing PR's title and description to reflect the full implementation. Use when: (1) User says 'revise pr', 'update pr description', 'pr revise', (2) Additional work was done after the PR was created and the title/body no longer matches, (3) User wants to sync PR metadata with the branch state.

Split a multi-feature pull request into smaller, focused PRs. Use when: (1) User says 'split pr' or 'break up pr', (2) A PR contains multiple independent features that should be reviewed separately, (3) User wants to decompose a large PR.

Create a pull request with intelligent base branch detection. Use when: (1) User says 'create pr', 'make pr', or 'open pr', (2) User wants to create a PR from the current branch, (3) User has finished work on a feature branch and needs a PR. Auto-detects base branch from conversation, git history, or repo default.

Scan the repo for private/confidential information and remove, rename, or replace it. Use when: (1) User says 'purge private info', 'check for secrets', or 'scan for credentials', (2) Before making a repo public, (3) User wants to ensure no client names, passwords, or personal info are exposed.

Enable automatic pushing mode. From now on, push to the remote automatically after committing. Use when: (1) User says 'push auto', 'auto push', or 'push automatically', (2) User wants commits pushed immediately without asking.

Disable automatic pushing. From now on, do NOT push to the remote automatically. Use when: (1) User says 'push forbid', 'no push', or 'stop pushing', (2) During sequential large development to save CI costs, (3) User wants to control when changes are pushed.

Refer another project while protecting sensitive information. Use when: (1) User says 'refer project', 'copy from project', or 'look at another repo', (2) User wants to reference patterns or setup from another codebase, (3) User needs to learn from another project's structure without leaking private data.

Capture AI-readable postmortems after a dev attempt resolves into a project-scoped lessons file that future /big-plan runs can read. Use when: (1) User says 'retro-notes', 'retro', 'capture lessons', 'fail-notes', 'postmortem', (2) A dev session wrapped up that took longer than expected, changed approach mid-way, or had non-obvious gotchas. Reader is a future planning agent.

Iterative code review loop running /deep-review multiple times, fixing issues each round. Finds bugs and quality issues through repeated passes. Use when: (1) User says 'review-loop', 'review loop', or 'review repeat', (2) User wants continuous review+fix cycles, (3) User wants thorough multi-pass review before finalizing code, (4) User says 'review 5 rounds' or similar.

Generate professional circuit diagrams using schemdraw Python library. Creates vector graphics (SVG/PDF/PNG) from natural language descriptions. Components: resistors, capacitors, inductors, diodes, transistors, opamps, ICs, logic gates, etc. Use when: (1) User requests circuit diagrams or schematics, (2) User wants publication-quality output, (3) User needs SVG/PDF for documentation, (4) Complex circuits with ICs/opamps/digital logic, (5) User mentions schemdraw or wants alternative to ASCII circuits.

Guide for creating effective Claude Code skills (specialized knowledge, workflows, tool integrations). Use when: (1) User wants to create a new skill, (2) User wants to improve an existing skill, (3) User asks 'how to make a skill' or 'create skill for X'. Covers skill anatomy (SKILL.md, scripts/, references/, assets/), progressive disclosure, frontmatter, bundled resources, init_skill.py, iteration workflow.

Fix, improve, or update existing Claude Code skills. Use when: (1) User reports a skill isn't working or triggering incorrectly, (2) User wants to adjust skill behavior, (3) User says 'fix skill', 'update skill', 'tweak skill', 'skill not working', 'skill triggers too often'. Edits SKILL.md frontmatter and body, scripts/references/assets, debugs trigger issues.

Load screenshot images or other files from Dropbox screenshots directory. Use when user invokes /ss directly. NEVER manually list/read files from the screenshots dir — this skill handles Dropbox sync delays, freshness checks, retry logic that manual reads miss. Supports: /ss 2 (latest 2), /ss latest3, /ss filename.png (exact/substring), /ss full-path. Also non-image files (e.g., /ss pattern-4-variations.html).

Create new Claude Code custom agents (subagents). Use when: (1) User wants to create a new custom agent, (2) User says 'create agent', 'new agent', 'make subagent', (3) User wants a specialized agent for delegation. Covers agent file format, YAML frontmatter, tool restrictions, model selection, permission modes, persistent memory, placement.

Fix, improve, or update existing Claude Code custom agents (subagents). Use when: (1) User reports an agent isn't working well, (2) User wants to adjust agent behavior, tools, or model, (3) User says 'fix agent', 'update agent', 'tweak agent', 'agent not working'. Edits agent frontmatter, tool restrictions, prompts.

Force-sync current branch into a remote target branch by deleting and re-pushing. Creates a backup PR before overwriting so the old state can be restored via GitHub's 'Restore branch'. Use when 'sync-to' failed due to conflicts, or when user says 'sync force to', 'force sync to', 'force push to branch'.

Merge current branch into a target branch and return. Use when user says 'sync to', 'merge into', 'push changes to branch', or wants to sync their work branch into another branch without leaving the current branch.

Add or update wording rules (表記ルール) in the w repo's vocabulary-rule.md files. Use when: (1) User says 'add wording rule', 'update wording rule', '表記ルール追加', (2) User wants to add a kanji/hiragana usage rule, (3) User provides a rule like 'X should be Y' with examples.

Watch GitHub PR CI checks in the background and notify on completion. Use when: (1) User wants to monitor CI/CD status, (2) User says 'watch CI', 'check CI', 'monitor checks', or 'wait for CI', (3) User wants to know when checks pass or fail. Runs a background gh polling shell loop (NOT a subagent — near-zero token cost), sends macOS notification on completion. Also handles merged PRs by watching the target branch CI.

Start a development workflow as a draft PR. Creates a NEW branch from the current branch, empty start commit, draft PR targeting the current branch, then implements. ALWAYS creates a new branch by default — produces a nested PR-on-PR when the current branch already has one. Use when: (1) User says 'dev as pr', (2) User wants a PR-first workflow before coding, (3) User passes -s/--stay to reuse the current branch instead of nesting, (4) User passes a GitHub issue URL to implement, (5) User passes --make-issue/--issue to create an issue first. Logs progress via issue comments when an issue is linked.

Parallel multi-topic development using git worktrees, base branches, and Claude Code agent teams. Use when: (1) User wants to work on multiple related features in parallel, (2) User mentions 'worktree', 'base branch', 'parallel development', 'split into topics', or 'multi-topic'. FULLY AUTONOMOUS — creates worktrees, spawns teams, coordinates everything. Also supports Super-Epic child mode for [Epic] issues from /big-plan with '**Super-epic:** #N' markers (targets the super-epic base branch instead of main).

Facade for development workflows. Routes to /x-as-pr (single-topic) or /x-wt-teams (multi-topic parallel). Use when: (1) User says '/x' followed by dev instructions, (2) User wants to start development without choosing between /x-as-pr and /x-wt-teams, (3) User says 'dev', 'implement', or 'build' with a task. Default options: -l -v (review-loop + verify-ui).

Spreadsheet creation, editing, and analysis. Use when working with .xlsx, .xlsm, .csv, .tsv files for: (1) Creating spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Data analysis and visualization, (5) Recalculating formulas.

Fetch transcript/caption text from YouTube videos using youtube-transcript-api. Use when: (1) User wants text from a YouTube video, (2) User provides YouTube URLs and needs transcripts, (3) User says 'fetch youtube text', 'get captions', 'youtube transcript'. Outputs plain text saved to $HOME/cclogs/{slug}/.

Add or remove zeno.zsh snippet shortcuts in $HOME/.config/zeno/config.yml. Use when: (1) User says 'zeno-tweak', (2) User wants to add or remove a zeno snippet shortcut.

Apply Takazudo's zpaper blog writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's zpaper style, (2) User says 'apply voice', 'zpaper voice', 'zpaper文体で', 'zpaper風に書いて', 'ブログ文体を適用', (3) User provides text to transform to zpaper style. Reads writing-style.md and vocabulary-rule.md from the zpaper repo and applies the rules.

Convert conversation context into a zpaper blog article via the zpaper-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write zpaper article', 'zpaper記事', 'zpaperに書いて', 'articlify for zpaper', or /zpaper-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.

Apply Takazudo's CodeGrid writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's CodeGrid style, (2) User says 'apply voice', 'codegrid voice', 'codegrid文体で', 'codegrid風に書いて', '文体を適用', (3) User provides text to transform to CodeGrid style. Reads writing-style.md and vocabulary-rule.md from takazudo-codegrid-writing repo and applies the rules.

Convert conversation context into a CodeGrid article via the zudocg-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write codegrid article', 'CodeGrid記事', 'codegridに書いて', 'articlify for codegrid', or /zudocg-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.

Apply Takazudo's esa writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's esa style, (2) User says 'apply voice', 'esa voice', 'esa文体で', 'esa風に書いて', '文体を適用', (3) User provides text to transform to esa style. Reads writing-style.md and vocabulary-rule.md from takazudo-esa-writing repo and applies the rules.

Convert conversation context into an esa article via the zudoesa-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write esa article', 'esa記事', 'esaに書いて', 'articlify for esa', or /zudoesa-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.