mizchi

mizchi/chezmoi-dotfiles

Command

A one-question-at-a-time command that checks understanding with four-choice quizzes and explains wrong or unknown answers before trying again.

mizchi/chezmoi-dotfiles

Command

Release a MoonBit CLI project. Argument: minor or patch (default: patch).

mizchi/chezmoi-dotfiles

Command

A review command that examines recent tasks and turns reusable lessons into ast-grep rules, skills, or CLAUDE.md instructions. ast-grep is a tool for finding code by its structure rather than only by exact text.

mizchi/chezmoi-dotfiles

Command

A learning command that explains an item's public API or export surface, then checks and strengthens the user's understanding in a loop.

mizchi/chezmoi-dotfiles

Skill Claude CodeCodex

Use when working on github.com/mizchi/pkspec, especially release readiness, version bumps, GitHub Actions/Nix release checks, adapter DSL work, or the experimental Playwright/Vitest coverage presets. Covers the repo's spec gates, pkfire release flow, pkl CLI dependency gotchas, and what is intentionally still…

mizchi/lsmcp

Command Claude Code

This command uses the LSMCP (Language Server MCP) tools to perform rapid semantic code analysis, leveraging language server capabilities for more accurate results than traditional grep/search approaches.

mizchi/lsmcp

Command Claude Code

A command for finding TypeScript code that cannot be reached from specified entry files; tsr is the tool that performs this check.

mizchi/lsmcp

Command Claude Code

Split complex tasks into sequential steps, where each step can contain multiple parallel subtasks.

mizchi/lsmcp

Command Claude Code

This document outlines the verification steps to be performed before releasing lsmcp. The primary focus is to ensure that lsmcp-dev MCP functionality works correctly.

mizchi/lsmcp

Command Claude Code

When I need to refactor TypeScript code in this project, follow these steps.

mizchi/lsmcp

Settings file Claude Code

Agent settings declaring 6 allowed tools.

mizchi/lsmcp

Instructions file

Instructions for mizchi/lsmcp, covering critical: prioritize lsmcp tools for code analysis, 📋 recommended workflow, 🎯 when to use each tool, 📊 detailed workflow examples and when to use fallback tools.

mizchi/skills

Instructions file

Claude Code instructions for mizchi/skills, covering skills repository — maintainer notes, when editing a skill in this repo, what is not in this repo, before committing and language policy.

mizchi/skills

Skill Claude CodeCodex

Review screenshots or other images with OpenRouter vision models via bundled Deno scripts. Use for quick VRT sanity checks, invalid-image screening, or CI gates. scripts/review-image.ts returns freeform feedback; scripts/review-image-ci.ts returns strict pass|fail JSON and exits non-zero on fail.

mizchi/skills

Skill Claude CodeCodex

Entry-point for the @mizchi/vlmkit toolkit — VLM-driven frontend kit covering visual regression (snapshot / diff / regression-watch), markup synthesis from screenshots, design-token / theme / a11y / i18n audits, and a 2-stage VLM + LLM CSS auto-repair loop. Use when a coding agent has edited HTML/CSS and needs to know…

mizchi/skills

Skill Claude CodeCodex

ECS blue/green deployment patterns. Recommends ALB-native weighted target groups as the simpler default; covers CodeDeploy as a reference for teams that already use it or need pipeline-integrated rollback. Use when choosing or debugging ECS blue/green infrastructure.

mizchi/skills

Skill Claude CodeCodex

Troubleshooting guidance for IPv6 connection failures between Amazon ECS services. ECS is AWS’s container service, Fargate runs those containers, and Service Connect provides service names and networking between them.

mizchi/skills

Skill Claude CodeCodex

OpenTofu/Terraform pattern for GitHub Actions OIDC trust with AWS IAM. Covers the non-obvious jobworkflowref condition (vs just sub for repo+branch), the Bedrock inference profile ARN patterns, required aws-marketplace permissions alongside Bedrock, and the ReadOnlyAccess + explicit Deny pattern for AI agent roles.…

mizchi/skills

Skill Claude CodeCodex

Guidance for using aws-vault and the AWS command-line tools when AWS requires multi-factor authentication for identity-management actions. It also covers FIDO2 passkeys, a type of security key or device-based sign-in method.

mizchi/skills

Skill Claude CodeCodex

One-shot Cloudflare Access self-hosted application provisioning via the API — app + email allowlist policy + service token. Use when you want to gate a Worker behind Access without a full Pulumi stack.

mizchi/skills

Skill Claude CodeCodex

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

mizchi/skills

Skill Claude CodeCodex

Bundle a Cloudflare Worker that combines MoonBit core code with a TypeScript entry. Use when wrangler must ship a moon-built JS module alongside hand-written TS, with FFI rewrites and a post-build bundle check.

mizchi/skills

Skill Claude CodeCodex

Cloudflare Worker telemetry at the fetch boundary — OTLP traces / metrics / logs + utels error tracking + D1 Proxy that emits slow-query warnings. Use when adding observability to a Worker without touching handler code.

mizchi/skills

Skill Claude CodeCodex

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI'…