mazrean

Operate the official grafana/mcp-grafana server from an agent. Use when the conversation has Grafana MCP tools available and you need to query Prometheus/Loki/Pyroscope, search or edit dashboards, manage alert rules, or generate Grafana deeplinks. Covers tool…

Analyzes an existing ISUCON-style application, designs an optimal infrastructure and architecture redesign that respects every ISUCON rule, and emits the proposal as a self-contained Agent Skill that another Claude session can read and execute. Use when…

Decomposes the apply-skill produced by designing-isucon-architecture into atomic tasks, materializes one Claude Code subagent per task, and emits a dispatcher slash command that fires the subagents in dependency order (parallel where the graph allows). Use…

Runs Visual Regression Testing (VRT) locally to prevent disqualification in Web Speed Hackathon. Captures screenshots, compares against baselines, updates snapshots, and validates visual integrity after performance optimizations. Use when optimizing WSH apps,…

Analyzes a Web Speed Hackathon project, researches each improvement topic in depth, stores research as Agent Skills, and generates executable Claude Code commands for each optimization. Use when starting WSH optimization, creating an optimization roadmap, or…

Ports an ISUCON-style Rust reference implementation to Go (Echo) using parallel subagents. Use when the contest provides a Rust reference but the team wants to compete in Go, or when the user asks to migrate a Rust web app to Go Echo endpoint by endpoint.…

Optimizes web applications for ISUCON (Iikanji ni Speed Up Contest), a Japanese 8-hour performance tuning competition. Use when participating in ISUCON, practicing past problems (private-isu, isucon-workshop), or aggressively tuning a Go/Node.js/Ruby/PHP web…

Optimizes deliberately slow web applications for maximum Lighthouse scores in Web Speed Hackathon (CyberAgent). Use when participating in WSH or performing aggressive frontend performance optimization on React/Node.js apps with SQLite backends. Covers bundle…

Crok AI chat rendering optimization — SSE debouncing, ChatMessage memoization, Markdown re-render prevention

DM page and flow optimization — afterSave hook, message rendering, unread count queries for WSH 2026

Home page performance optimization — Post defaultScope, SSR data reduction, lazy media hydration for WSH 2026 CaX app

Lazy loading modal containers and route components to reduce initial bundle size — CrokContainer, NewPostModalContainer

SSE streaming optimization — batching char-by-char events and debouncing React re-renders for Crok AI chat performance

Runs Visual Regression Testing (VRT) locally to prevent disqualification in Web Speed Hackathon. Captures screenshots, compares against baselines, updates snapshots, and validates visual integrity after performance optimizations. Use when optimizing WSH apps,…

Optimizes deliberately slow web applications for maximum Lighthouse scores in Web Speed Hackathon (CyberAgent). Use when participating in WSH or performing aggressive frontend performance optimization on React/Node.js apps with SQLite backends. Covers bundle…

Code splitting strategies for WSH 2026 — React.lazy, Suspense, splitChunks, and route-based splitting for the CaX app.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/isucon. Use when bootstrapping or auditing an ISUCON contest workspace's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/terraform. Use when bootstrapping or auditing a Terraform repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/common. Use when bootstrapping or auditing a repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/terraform-gcp. Use when bootstrapping or auditing a Terraform-on-GCP repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/android. Use when bootstrapping or auditing an Android repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/go. Use when bootstrapping or auditing a Go repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/cloudflare. Use when bootstrapping or auditing a Cloudflare Workers repo's mise.toml.

Lists the CLI tools that must appear in mise.toml for any repo depending on apm-plackage/frontend. Required for E2E testing via Playwright CLI and for browser debugging via chrome-devtools-mcp.

Applies the REV2 architecture redesign in docs/isucon-arch/DESIGN-REV2.md to the isunarabe-train-2026 (nrb2026) implementation. REV2 is layered on top of REV1 (applying-isucon-arch-isunarabe) — REV1 must already be merged. Use when the REV1 dispatcher is…

Applies the architecture redesign decided in docs/isucon-arch/DESIGN.md to the isunarabe-train-2026 (nrb2026) Go implementation in migrate/go/. Use when ready to execute the planned topology, schema, cache, and endpoint changes for this ISUCON practice…

ISUNARABE 合同演習 2026 (nrb2026) アプリケーションのドメイン知識リファレンス。クラウドファンディング型グループ購入「キャンペーン」を中心に、ユーザー・参加・課金・タグ保存検索・Webhook 通知の不変条件と整合性ルールをまとめる。Use this skill when reading or modifying the contest webapp (Rust 参考実装 `migrate/rust/`、Go 移植先、SQL…

Kessoku compile-time DI with parallel initialization for Go. Use when writing or debugging kessoku providers/injectors, enabling async dependencies, migrating from google/wire, or fixing go:generate/codegen issues in Go services.

Goプロジェクト内でDBアクセス（CRUD）が発生している関数・テーブルをisucrudで解析し、コーディングエージェントが「どの関数からどのテーブルにINSERT/UPDATE/DELETE/SELECTが行われるか」を把握するためのスキル。キャッシュ対象の判断、N+1の特定、DBアクセスを伴う関数の影響範囲調査、リファクタリング前のCRUD確認などに使用する。Go (database/sql, sqlx 等) で書かれたプロジェクトが対象。

Launches and verifies local dev environments using dockportless with worktree-unique project names. Use when starting docker compose services, checking service accessibility via proxy, enabling TLS/HTTPS routing, or when developing across multiple git…

Query isutools (isucon-go-tools) metrics via PromQL on a Prometheus server. Use when the user wants to analyze ISUCON performance — slow endpoints, slow SQL queries, cache hit rate, DB connection pool, lock contention, queue depth, object pool usage, or…

Extends your capabilities by discovering and installing Agent Skills from skills.sh. Use proactively whenever you lack specific knowledge, specialized workflows, or domain expertise to handle a task well — not only when the user explicitly asks for a new…