スキルを探す

Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Use this skill whenever you are designing AI systems, tackling Sim2Real transfer, deploying machine learning in the physical world, or evaluating reinforcement learning architectures. Trigger this skill for questions about domain randomization, reward design, bootstrapping real-world AI, robotics hardware assumptions, or shifting from hard-coded rules to data-driven deep learning. It helps ground theoretical AI in physical embodiment and pragmatic deployment.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and research strategy. Reach for this skill whenever discussing machine learning paradigms, the limits of compute and data, AGI timelines, superintelligence safety, or deciding between hardcoding vs. learning. Trigger this skill for questions about next-word prediction, reinforcement learning efficiency, generalization gaps, and transitioning from brute-force scaling to fundamental research, even if the user doesn't explicitly name him.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the engineering and research philosophies of Jeff Dean, Chief Scientist at Google DeepMind and Google Research. Reach for this skill whenever you are designing large-scale distributed systems, optimizing latency and energy efficiency, or making architectural decisions about machine learning infrastructure. It should trigger automatically for topics involving hardware-ML co-design, model distillation, sparse activation, massively multi-task models, or scaling systems by 5x to 10x. Use this skill to evaluate system bottlenecks, transition from specialized to unified models, and optimize experimental velocity. Apply his mental models to avoid premature 100x scaling and to treat AI models as reasoning engines rather than memorization databases.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill whenever you are reasoning about large-scale scientific projects, genomics, bioethics, data infrastructure, or long-term medical translation. Eric S. Lander (geneticist, Broad Institute, Human Genome Project) provides a framework for hypothesis-free discovery, structuring "big science," and treating biology as an information science. Reach for this when the user is discussing open science, collaborative ecosystems, CRISPR/gene editing ethics, managing massive datasets, or setting realistic timelines for technological breakthroughs. Apply his principles to avoid the "lone genius" myth, prevent overpromising, and build foundational infrastructure that serves the broader community.

日本語の概要は準備中です。原文の説明を表示しています。

Suede Thought Graph shipping search for a multi-file repo change. Use when competing implementation plans need one evidence-gated selection before any build. Halts on hazards, collisions, budget exhaustion, or no safe winner. Reads production; never deploys. NOT FOR: bulk independent work (use a separate private worker-fleet pass); findings-only diff review (use suede-code-review); CI or branch-protection wiring (use suede-ci-gate); copy-only shipping (use suede-ship-copy).

日本語の概要は準備中です。原文の説明を表示しています。

Axone deployment workflows with cargo-make, cw-orch, and Abstract. Use when publishing modules, installing them on accounts, running local chain tasks, or inspecting deployments.

日本語の概要は準備中です。原文の説明を表示しています。

Structured planning mode for AI agents working on coding and development tasks. Produces a comprehensive plan BEFORE any code is written or changed, including task decomposition, architecture decisions, risk assessment, and approval gates. Use this skill whenever the user says "/plan", "plan mode", "plan first", "think before coding", "make a plan", or asks the agent to plan before executing. Also trigger when the user describes a complex multi-step development task and would clearly benefit from structured planning before implementation — especially for tasks involving new features, refactors, migrations, infrastructure changes, or multi-file edits. When in doubt, plan. A few minutes of planning prevents hours of rework.

日本語の概要は準備中です。原文の説明を表示しています。

Review a codebase and generate or update its README.md according to best practices. The skill performs static analysis of the project structure, dependencies, scripts, and existing documentation, then produces a comprehensive, accurate README. **Triggers — use this skill when:** - User asks to "review", "update", "improve", or "generate" a README - User says "create a README for this project" - User mentions "document this repo", "add documentation" - User asks to "fix my README" or "make my README better" - User provides a codebase and asks for documentation help **Covers:** Any project type — Node.js, Python, Rust, Go, Java, Ruby, PHP, monorepos, static sites, CLI tools, libraries, APIs, Docker-based projects, and more. Works with both new READMEs (from scratch) and existing ones (update/improve).

日本語の概要は準備中です。原文の説明を表示しています。

Expose the user's local AionUi WebUI to the public internet with a near-zero-effort flow. Detects whether the WebUI is running, guides the user to switch it on if needed (the only manual step), self-installs cloudflared cross-platform, opens a Cloudflare quick tunnel, verifies the public URL actually works, then explains the limitations honestly (temporary/random URL, must stay running, password is the only protection, traffic transits Cloudflare). Use whenever the user wants to reach their AionUi from outside the LAN, over the internet, or share a public link. Distinct from aionui-webui-setup (which covers manual LAN / Tailscale / server config through the settings UI): this skill produces a one-click public link via an automatic tunnel.

日本語の概要は準備中です。原文の説明を表示しています。

OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant. Can diagnose issues, create bots, execute automated tasks, etc. Use when users need to install OpenClaw, configure Gateway, set up Channels, create Agents, troubleshoot issues, or perform OpenClaw-related operations.

日本語の概要は準備中です。原文の説明を表示しています。

AionUi WebUI configuration expert: Helps users configure AionUi WebUI mode for remote access through the settings interface. Supports LAN connection, Tailscale VPN, and server deployment. Use when users need to set up AionUi WebUI, configure remote access, troubleshoot WebUI issues, or deploy AionUi on servers.

日本語の概要は準備中です。原文の説明を表示しています。

Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port mapping, SQLite database backup, and platform capabilities (collections, tags, GitHub import). For deploying and operating the Skill Base platform itself only.

日本語の概要は準備中です。原文の説明を表示しています。

ALWAYS activate when the user's query involves Docker in any way — even if it also matches other skills. If the words docker, Dockerfile, docker-compose, compose.yml, container, or image appear in the query, this skill MUST be used. Covers: writing or editing Dockerfiles and compose files, adding services (postgres, redis, etc.) to compose, volume mounts and data persistence, docker build failures (layer caching, npm install issues), healthchecks and service startup ordering (depends_on), environment variables in containers, port mapping, container crashes and exit codes (OOM/137), non-root users, multi-stage builds, image optimization, .dockerignore, and deploying to container runtimes. Takes priority over general implementation or debugging skills when Docker infrastructure is the subject.

日本語の概要は準備中です。原文の説明を表示しています。

Syncs Claude config between prime repo and target projects. Trigger on 'sync', 'prime-sync', 'push config', 'pull config', 'update prime', 'sync claude config'. Push mode deploys to targets; pull mode imports changes back.

日本語の概要は準備中です。原文の説明を表示しています。

Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any "why did this change?" or "why is this happening?" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.

日本語の概要は準備中です。原文の説明を表示しています。

Generate structured 8-section validation reports with verdict (GOOD/BAD/NEEDS MAJOR WORK), strengths, critical flaws, blindspots, and concrete path forward. Use after strategic-cto-mentor has completed validation analysis and needs to produce final deliverable.

日本語の概要は準備中です。原文の説明を表示しています。

Recommend technology stacks based on project requirements, team expertise, and constraints. Use when selecting frameworks, languages, databases, and infrastructure for new projects.

日本語の概要は準備中です。原文の説明を表示しています。

Infrastructure and development cost estimation for technical projects. Use when planning budgets, evaluating build vs buy decisions, or projecting TCO for architecture choices.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the diff adds, upgrades, re-sources or re-pins a dependency - manifests, lockfiles, go.mod replace, Docker base images, GitHub Actions uses, Terraform modules, submodules, vendored or generated code, curl-pipe-sh installs - or changes what goes into a package or image, how releases are signed and verified, or how an updater or plugin loader trusts what it installs

日本語の概要は準備中です。原文の説明を表示しています。

Use when a model is served online (FastAPI, BentoML) or scored in batch, when changing how a model artifact is loaded or versioned, or when adding drift, quality or prediction monitoring and a rollout plan for a new model

日本語の概要は準備中です。原文の説明を表示しています。

Use when ordering board tasks - set priority/blocked_by/deploy_depends_on by severity and dependency, split MoSCoW within a feature, and use RICE/ICE only for a genuine "what next" call across several features

日本語の概要は準備中です。原文の説明を表示しています。

Use when a release reaches awaiting_verdict (or you are woken for an incident) - how to read runtime logs, error groups, health and smoke evidence for the release's component and decide finish, re-check, roll back or hand to a human

日本語の概要は準備中です。原文の説明を表示しています。

Use when you need the end-to-end merge -> deploy -> watch -> verdict sequence for a delivery mode, or a tool result you did not expect (refusal, park, tag exists)

日本語の概要は準備中です。原文の説明を表示しています。

Use when adding logging to Go code - the repository's logger with structured fields, request-scoped correlation, correct levels, no secrets or double-logging

日本語の概要は準備中です。原文の説明を表示しています。