claude-resources

Sweep open GitHub issues — optionally narrowed by label — and drive each to completion via `/big-plan -m -a`. Collects candidates, triages out work that needs careful human judgment, confirms once, then handles the rest autonomously one issue at a time. Use when: (1) User says '/issue-sweep', 'sweep issues', 'sweep open issues', 'handle the open issues', 'clear the issue backlog', or 'do the issues', (2) The user wants to batch-process a label's worth of issues (e.g. `agent-found`, `mac`), (3) After a work round that left a pile of follow-up issues. Options: "`-f`/`--filter LABEL` keeps only issues carrying that label; `-ex`/`--exclude LABEL`" drops issues carrying it; with no options it sweeps ALL open issues. Locally-checkable "verify X" tasks are verified directly and closed (not run through `/big-plan`). Skips issues that need careful human judgment (huge multi-major version bumps, super-big epics, design calls); verification tasks that can't be auto-verified locally (auth/deploy/external/subjective) are

Generate or redesign raster images (PNG mockups, illustrations, photos, UI design polish) from inside Claude Code by driving Codex CLI's built-in $imagegen, billed to ChatGPT-included usage instead of per-image OpenAI API charges. Use whenever the user wants to create/generate an image, make a mockup or illustration, produce a photo, polish or redesign a UI from a screenshot, or get a PNG out of a session — even if they don't mention Codex or "imagegen". This is the preferred image-generation path because Anthropic models cannot generate raster images and this route avoids API billing.

Iterative visual design-polish loop for an existing or WIP web UI. Each round: capture the live page as screenshots, judge it from the rendered pixels, and apply CSS polish toward a better-looking target using /css-wisdom's tight-token strategy — then re-capture and compare. The target direction is set by codex-imagegen 'north-star' mockups generated from the current screenshot, so the loop pursues a genuinely better look instead of nudging the existing one in place. Use when: (1) user says 'design-polish-loop', 'polish loop', 'polish this page/design/UI', (2) user wants to level up / upgrade the look of a current design or WIP project, (3) user wants AI-proposed redesign directions applied to a real rendering page, (4) user calls a design plain, dated, flat, or unpolished and wants it improved. Main use case: improving the current design of a WIP project. It polishes what already renders — not brand-new-from-scratch pages.

Bump every `@takazudo/*` registry dependency in the current project to its newest version, resolving each by the channel it currently tracks. Use when: (1) User says '/dev-bump-zudo-deps', 'bump zudo deps', 'bump the @takazudo packages', 'update zfb', 'update zudo-doc', or 'update the takazudo toolchain to latest', (2) A new `@takazudo/*` prerelease or release has shipped and this project should adopt it, (3) Routine first-party dependency-update rounds. Resolution rule: a dep currently on the `next` prerelease line (`0.1.0-next.N`) → newest `next` release; a dep on the literal `latest` tag → `dist-tags.latest`; a plain stable semver → newest stable. Skips `workspace:`/`file:`/`link:` specs and leaves operator style (exact / `^` / `~`) and prerelease channel intact. A bundled script does the discovery + semver resolution; this skill drives install + verify + report.

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. Codex (-co) is the DEFAULT Step 5 plan reviewer — it runs even when no reviewer flag is passed; -op/-gco add more second opinions (runnable in parallel). Use -a/--auto to run the chain autonomously: skip the Step 6 confirmation wait (pausing only when something needs careful consideration), auto-create the issues, then auto-invoke the implementation skill in the same session — /x-wt-teams for a multi-sub-issue plan, /x-as-pr for a single-sub-issue plan — forwarding -a so multi-wave plans auto-chain wave after wave. Use -m/--merge to also merge the final PR i

Purge GitHub Actions caches across every non-archived repo for one or more GitHub owners (users or orgs). Use when (1) the user says "purge gh cache", "clear actions cache", "delete CI cache", or invokes /dev-purge-gh-cache, (2) the user wants to free up GitHub Actions cache storage for an account/org, (3) the user names one or more GitHub owners (e.g. "Takazudo", "zudolab") and asks to wipe their Actions caches. Handles fan-out across all repos, parallel survey, bulk delete, and real-time verification.

Report bugs and improvement ideas found in Takazudo's own upstream packages as GitHub issues on the upstream repo. The current project depends on packages built by the user under github.com/takazudo and github.com/zudolab (e.g. zudolab/zudo-doc, Takazudo/zudo-front-builder, the @takazudo/* npm scope). Use when: (1) User invokes /dev-upstream-report — with a description to report something now, or with no args to enable upstream-watch mode for the rest of the session, (2) During development a bug, limitation, or missing feature is traced to one of these upstream packages rather than the current project, (3) User says 'report upstream', 'upstream issue', 'file it on the package repo', or blames one of these packages for a problem.

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).

Render→look→diagnose→fix loop for visual/UI design work, so you judge layout from the ACTUAL rendered pixels instead of from CSS class names and design tokens. Use this whenever you are refining how a web UI LOOKS — spacing, grouping, visual hierarchy, balance, alignment — and especially whenever a user says a layout looks "tight", "cramped", "too dense", "loose", "too much space", "off", "unbalanced", or "doesn't breathe". Use it after implementing any UI/CSS/layout change that needs to look right (not just pass tests), and whenever you are about to judge a layout from tokens or class strings without seeing it rendered. ALSO use it in reference-match mode — whenever the user hands you a concrete visual reference (an annotated screenshot, a mockup, a marked-up capture with drawn lines or "green = must have / red = must not", or "make it match this"): there the reference bitmap IS the spec, and success is a pixel diff of your render against it (presence AND absence — added elements the reference never showed a

Read files from a PUBLIC GitHub repo that the Claude Code web/remote environment reports as out-of-scope for its GitHub MCP tools. Use when (1) running in the web/remote container (claude.ai/code, NOT a local Mac/terminal session), AND (2) a `mcp__github__*` call fails with "Access denied: repository ... is not configured for this session", AND (3) the repo is public. Triggers: "can't see that repo", "access denied repository not configured", "read a public repo that's not in scope", "clone a public repo to read it".

End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.

Set up and use the committed `_temp-resource/<issue>-<topic>/` convention for handing scratch resources (prototypes, design references, fixtures, sample data) from one Claude Code session to a LATER session through git — not Dropbox/cclogs. Use when: (1) setting up `_temp-resource/` in a repo, (2) a planning or dev session must delegate files a later session will need — especially `/big-plan` → `/x-wt-teams`, or any handoff to Claude Code web where Dropbox/cclogs is unavailable, (3) deciding where to put prototype output (e.g. from `/prototype-first-wisdom`) that you've decided a downstream session should reuse, (4) reading resources a prior session left under `_temp-resource/`. Keywords: _temp-resource, temp resource, delegate resources, share prototype across sessions, web Claude Code handoff, "use this PR as base".

Bootstrap a project so Claude Code on the web loads your shared config (skills/agents/commands from the public claude-resources mirror). Use when: (1) User says '/dev-setup-webenv', 'set up web env', 'enable my skills on web' for a project, (2) A repo should pull the web profile at SessionStart. Runs LOCALLY (Mac/terminal) — it only writes/commits a bootstrap into the target project; the actual loading happens later inside the web container. Offers two targets: a committed .claude/settings.json hook (solo repos) or an env-setup-script snippet to paste into the web UI (team repos, commits nothing). Defaults to the non-intrusive choice.

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.

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.

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 /codex-review. Opt into Claude reviewers with -haiku|-so|-op (auto-detects PR vs full-project mode). Supports -co|-gco external backends. Default team-fix mode (-t) delegates fixes to /x-wt-teams --no-review --stay; pass -nt/--no-team for inline fixes. Unfixed findings become agent-found GitHub issues by default (-nori to suppress).

Reclaim disk space on a Mac dev machine by deleting regenerable dev caches (Cargo/zfb build output, node_modules, pnpm/npm caches, OS/app caches) and thinning APFS local snapshots so the space actually frees. Manual-only — invoke with /dev-clean-mac when a Mac is low on disk.

Reclaim disk space on WSL2 by purging dev caches and orphaned build artifacts, then guide the user through compacting the ext4.vhdx from Windows. Use when: (1) the user says 'dev-clean-wsl', 'clean wsl', 'wsl disk full', 'free disk space', 'reclaim space', 'purge caches', or 'disk almost full' on a WSL machine; (2) a build or tool fails with ENOSPC / no space left; (3) the user wants to shrink the WSL virtual disk. Covers cargo target/registry, pnpm/npm caches, node_modules, and the vhdx-compaction step that actually returns space to the Windows C: drive.

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, (9) Choosing a versioning / dist-tag / release-channel strategy — especially the pre-1.0 (0.x) ruling for what `latest` vs `next` should point at, how to tag prereleases, and avoiding the stale-`latest` footgun. Use this whenever the user mentions dist-tags, `latest`/`next`, prerelease tagging, 0.x versioning, or 'what version/release strategy should we use', even if they don't explicitly say 'npm package'. Keywords: npm package, publish to npm, library development, dist-tag, latest vs next, prerelease tagging, 0.x versioning, release strategy, semver channel.

Set up a dev server that auto-rotates to the next free port instead of killing whatever holds the preferred one. Ships a drop-in port-probe helper + launcher template. Use when: (1) User invokes /dev-port-rotation-serve, (2) User wants `dev` to walk to the next free port (+1, +2, ...) rather than kill-port, (3) User says 'port rotation', 'rotate ports', 'don't kill the port', 'auto-shift port', or wants a non-destructive dev launcher. NOT for adding a predev kill-port one-liner — that is dev-tweak-serve-package-json (--kill) / dev-package-json.

Lightweight code review. Dispatches to OpenAI Codex CLI (/codex-review) by default, or to Claude / Copilot 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.

Iterative code review loop running /deep-review multiple times, fixing issues each round. Each round: review (safe fixes applied inline by the reviewer) → big-but-decidable findings are fix-planned, implemented, and merged back via an in-session /big-plan -m -a chain → next round reviews the improved code. Only findings needing a genuine human decision are deferred into GitHub issues (-nori to suppress). Use when: (1) User says 'review-loop', 'review loop', or 'review repeat', (2) User wants continuous review+fix cycles, (3) User wants autonomous review → fix → improve passes before finalizing code, (4) User says 'review 5 rounds' or similar.

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.

Facade for development workflows. Routes on two axes: plan-first vs implement-now (escalates to /big-plan -a when the request needs research / decomposition / has unclear scope — the appended -a makes the plan chain into implementation in-session), then single vs multi on the ready-to-build fast paths (/x-as-pr single-topic, /x-wt-teams multi-topic parallel). Use when: (1) User says '/x' followed by dev instructions, (2) User wants to start development without choosing the workflow skill, (3) User says 'dev', 'implement', or 'build' with a task. Default option: -v (verify-ui). Review-loop (-l) is opt-in — without -l the downstream skill runs a single /deep-review pass. Forwards -a (autonomy/auto-chain) and -m (merge at the end + cleanup + CI watch) through every route; auto-fix of raised findings (-f) and issue-raising (-ri) are downstream defaults, with -nf/--no-fix and -nori/--no-raise-issues as the forwarded opt-outs. -a and -m are orthogonal — full hands-off end-to-end is -a -m.

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.

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.

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), gpt-5.4 model.

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.

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 ~0.6 GB split-zip (~5 GB installed) from yaqwsx.github.io/jlcparts.

Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.

Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.

Solve a complex bug or design problem by building a tiny isolated prototype first, instead of patching the production system in place. Trigger PROACTIVELY when (1) the same bug has resisted 2+ in-place fix attempts (fail-retry loop), (2) the user mentions "minimal prototype", "from zero", "from scratch", "simple script", "sandbox", "standalone", "isolate", "play around", or "try a sandbox version", (3) you find yourself ranking a list of suspects and ruling them out via source-grep on a runtime/visual bug, (4) the user is brainstorming many design options for a UI surface and wants speed (e.g., "make 20 patterns of the top page"), (5) the next reasonable step would be "instrument the existing complex code" — pause and consider this skill instead. Build the prototype in the repo-scoped Dropbox-synced cclogs dir (`$DROPBOX_CCLOGS_DIR/<repo>/<descriptive-name>/`) so it survives switching between Mac and WSL; the exception is a prototype that must import the repo's production code or use its workspace/Vite toolin

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.