Explore skills

ローカル変更をデフォルトブランチと比較してセルフレビューする。Issue 番号があれば要件適合もチェックする。ユーザーが「レビューして」「変更確認して」「/smart-review」「/smart-review #123」と言ったら起動する。

Implement AIUC-1 controls in AI systems. Provides concrete technical guidance, implementation patterns, policy templates, and evidence artifact generation for each requirement.

Create and modify APIs using WunderGraph Cosmo Connect. Covers gRPC plugin development (Go/TypeScript), standalone gRPC services, schema-to-proto workflows, CLI commands (wgc), local router setup, graph.yaml composition, field resolvers, batching, federation entities, and deployment. Use when building Cosmo Connect subgraphs, plugins, gRPC services, or setting up a local Cosmo Router.

Adaptive summarization — output length scales with input length for comfortable reading. Triggers: "summarize", "summarize this", "tldr", "too long", "sum up", "key points", "give me summary", "eli5", "explain like I'm 5", "explain simply". NOT FOR: translation (just ask), content creation (use content-humanizer). Produces: summary at optimal compression ratio based on input length.

Adversarial red team — find security holes, logic bugs, wasted resources. Triggers: "critic", "red team", "attack this", "what's wrong", "find flaws", "challenge this". NOT FOR: code review before merge (use review), debugging (use systematic-debugging). Produces: prioritized list of flaws with severity and remediation steps.

Use when the user explicitly asks to research the scope of a requirement or proposed change against the current codebase — e.g. "research the scope of this requirement", "what would adding X touch in this codebase", "do scope research on this spec", "/scope-research". Surveys the codebase to surface concrete facts about which files/areas a change would touch and the relevant facts about each touch

Evaluate a shared AI skill or skill repository before installing or copying patterns.

Switch between small local skill profiles: all, coding, writing, or minimal.

Use when the user explicitly asks for an "AB", adversarial, two-sided, or "red-team" code review of code changes they have made — e.g. "AB review my diff", "do an AB review of my changes", "red-team this code change", "have two reviewers argue about my code". Dispatches two opposing sub-agents — one building the evidence-based case that the change is mergeable, one building the case that it must n

Use when about to present long or complex AI-generated markdown to the user — typically >150 lines, >5 H2 sections, or content like code reviews, implementation plans, specs, research reports. Also use when the user explicitly asks to convert a markdown source into a readable HTML report. Produces a single self-contained HTML report (TL;DR hero, sticky TOC with importance stars, semantic-color cal

Use when the user explicitly asks to reflect on, review, or learn from the current Claude Code session — e.g. "review this session", "reflect on this session", "why did that take so many tries", "what went wrong this session", or asks to turn this session's mistakes into project rules. Reads the session transcript, finds where Claude's output was rejected or required correction, distills the root

Structure and interpret a cohort analysis to understand retention, engagement, or behavior patterns over time. Use this skill when a team needs to understand how different user groups behave across their lifecycle.