インフラ・DevOpsのスキル

What this project has already learned the hard way, and where any new such fact belongs. Two jobs. (1) Routing: this project keeps NO per-project Claude memories — read this before writing anything down, and pick a durable home from the list here. (2) An index, by area, of non-obvious facts worth knowing before you guess: debugging rigs and measurements that lie, iOS/WebKit and the tethered iPhone, the Windows app, production and deployment, and general codebase traps. Use before setting up a browser- or server-driven debugging session, when a bug reproduces only on iPhone, in Safari or in the Windows app, before changing deployment configuration or reading store/crash data, when something behaves unexpectedly and you are about to guess why, and whenever you are tempted to record a fact for later.

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 user is done evolving and wants to finalize, clean up, tag the result, or push the optimized agent.

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。

Guide for creating new skills in Kai's personal AI infrastructure. Use when user wants to create, update, or structure a new skill that extends capabilities with specialized knowledge, workflows, or tool integrations. Follows both Anthropic skill standards and PAI-specific patterns.

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。

Query historical and real-time crypto market data from 0xArchive across two venues: Hyperliquid and Lighter. Lighter has two deployments: mainnet at /v1/lighter and Robinhood Chain at /v1/rh-lighter (USDG-quoted, e.g. BTC, AAPL-USDG). Hyperliquid includes HIP-3 builder perps (/v1/hyperliquid/hip3), HIP-4 outcome markets (/v1/hyperliquid/hip4), and Spot (/v1/hyperliquid/spot, e.g. HYPE-USDC). Covers orderbooks, trades, candles, funding, open interest, liquidations, account positions, outcome markets, TWAP, CVD, breadth, webhooks, and data quality; data types are route-specific. WebSocket support is channel-specific and GET /v1/capabilities lists it per venue and data type: Lighter orderbook, trades, open interest, and funding stream live on both deployments; Lighter candles and L3 are replay-only; L4 channels replay on Hyperliquid core, HIP-3, HIP-4, and Spot. Use in Claude Code, Codex, and SKILL.md-compatible agents for market data, orderbooks, trades, candles, funding, prices, positions, real-time streams, prediction markets, or spot pairs on Hyperliquid, HIP-3, HIP-4, Hyperliquid Spot, Lighter, or Lighter on Robinhood Chain.

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。

Complete guide to vibe coding with the CodyMaster skill kit — from idea to deploy. Covers the full workflow, skills used at each phase, and common use cases. Read this first if you are new; reference it whenever you're unsure which skill to invoke.

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 setting up deployment infrastructure for any project - establishes multi-gate deploy pipeline with test gates, build verification, frontend safety checks, and rollback strategy before code reaches production

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。

[Deprecated] deploy safety merged. Use `cm-safe-deploy` instead.

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。

[Deprecated] quality gate now covers tests + canary. Use `cm-quality-gate` instead.

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。

Track and manage tasks across multiple AI coding agents (Codex, Google Antigravity, Cursor, Gemini CLI, Claude Code) through the Mission Control web UI at http://localhost:6969. Use when you need a visual kanban for multi-agent work, dispatching tasks, monitoring agent activity, or syncing task state from a CLI agent.

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。

Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.

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。

Complete guide to vibe coding with CodyMaster — from idea to deploy. Read this first if you are new.

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 setting up deployment infrastructure or enforcing a gated release path. Routes to deploy gates, setup, or rollback based on the current deployment stage.

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。

Knowledge base from the SD-22 DMSMS Guidebook (DSPO, FY24 working draft). Use for managing Diminished Manufacturing Sources and Material Shortages (DMSMS) and obsolescence across a long-lived system's life cycle: the five-step process (Prepare, Identify, Assess, Analyze, Implement) plus the Strategize overlay; standing up a DMSMS Management Team (DMT) and Management Plan (DMP); risk-based monitoring and surveillance (the risk cube, predictive tools, vendor surveys, GIDEP/DLA PDNs, critical-materials analysis); health assessments and resolution timing; costing and selecting resolutions (life-of-need buys, substitutes, redesign, technology refreshment) by AoA/BCA; and budgeting/executing resolutions through modification funding and the ECP process. Defense-sustainment / DoD-acquisition framing throughout. Does NOT teach general systems engineering, parts-management standards, or contracting law in depth, and does not reproduce DoD policy text or the source's tables and figures.

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。

Knowledge base from the DoD M&Q BoK (the Manufacturing and Quality Engineering Body of Knowledge), v3.0 of July 2025, published by OUSD(R&E). Use for the manufacturing-and-quality view of the defense acquisition life cycle: what M&Q engineers do across the Adaptive Acquisition Framework phases (Pre-MDD, Materiel Solution Analysis, Technology Maturation and Risk Reduction, Engineering and Manufacturing Development, Production and Deployment, Operations and Support); the twelve M&Q threads (A–L) built on the '5 Ms'; manufacturing feasibility and producibility; Manufacturing Readiness Levels and assessments; Key/Critical Characteristics and process capability (Cp/Cpk, SPC); the standards stack (AS6500, AS9100/ISO 9001, AS9103, AS9145); technical reviews (ASR/PDR/CDR/PRR) and milestone gates; DCMA surveillance; industrial base and supply chain; and sustainment (LCSP, IPS, ILA, ISR). Scope is DoD acquisition M&Q practice on the Major Capability Acquisition path — it is a best-practice compilation, not policy, and is thin on detailed shop-floor process engineering, contract law, and the full text of the cited industry standards (which it names but does not reproduce).

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。

Knowledge base from EU Artificial Intelligence Act — Regulation (EU) 2024/1689. Use for AI system classification (high-risk vs prohibited vs general), conformity assessment procedures, GPAI model obligations, transparency and disclosure requirements, governance structure (AI Office / AI Board), penalty tiers, value-chain operator obligations, post-market monitoring, and Annex III use-case analysis. Does not cover EU liability rules for AI (separate proposed directive) or implementation guidance documents issued after July 2024.

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。

GCP best practices: IAM, secrets, networking, security, compute, IaC, ops. Use when building, reviewing, or modifying GCP resources.

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。

Docker best practices: image security, build efficiency, runtime hardening, Compose, local tooling (Colima, OrbStack). Use when writing or reviewing Dockerfiles and Compose files.

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。

Terraform best practices: state, security, modules, workflow, testing, tooling. Use when writing or reviewing Terraform code.

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。

AWS best practices: IAM, secrets, networking, security, compute, IaC, ops. Use when building, reviewing, or modifying AWS resources.

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。

Kubernetes best practices: security, workloads, networking, config, operations, GitOps. Use when writing or reviewing K8s manifests and configurations.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CI/CD, registry, dependency drift, artifact provenance, image build, release pipeline, and runtime consumer challenges. Use when the user asks to trace dependency drift, registry pulls, malicious packages, build or release tampering, CI execution, artifact signing, or which shipped artifact the runtime actually consumes. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Linux credential artifacts, service tokens, SSH material, cloud and container secrets, socket-level trust, and host-to-host pivot chains. Use when the user asks to trace Linux auth artifacts, accepted token or key replay, socket or service-account trust edges, sudo or capability abuse, or explain lateral movement across Linux challenge nodes. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kubernetes API analysis, service-account trust, RBAC edges, admission and controller behavior, cluster secrets, workload mutation, and namespace-scoped drift. Use when the user asks to inspect kube API permissions, service-account tokens, RoleBinding or ClusterRoleBinding edges, admission webhooks, controller-created pods, secret exposure, or why live workloads differ from manifests. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries, prompts, hosts, or identities that should be treated as sandbox-internal by default and Codex needs to choose, route, and load the right downstream analysis path with concise evidence.

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。