Create a framing document from conversation transcripts. Use when the user has transcripts (VTT, call notes, etc.) and wants to produce a frame that captures the problem worth solving and why it was chosen over alternatives.

Upgrade groq-sdk versions and handle Groq model deprecations. Use when upgrading SDK versions, detecting deprecated models, or migrating to new Groq model IDs. Trigger with phrases like "upgrade groq", "groq migration", "groq breaking changes", "update groq SDK", "groq deprecated model".

State-machine driven iterative planning and execution for complex coding tasks. Cycle: Explore → Plan → Execute → Reflect → Pivot. Filesystem as persistent memory. Use for multi-file tasks, migrations, refactoring, failed tasks, or anything non-trivial.

Deploy applications to Kubernetes with production-ready manifests. Supports Deployments, Services, Ingress, HPA, ConfigMaps, Secrets, StatefulSets, and NetworkPolicies. Includes health checks, resource limits, auto-scaling, and TLS termination. Use when working with creating kubernetes deployments. Trigger with 'creating', 'kubernetes', 'deployments'.

Validate API schemas against OpenAPI, JSON Schema, and GraphQL specifications. Use when validating API schemas and contracts. Trigger with phrases like "validate API schema", "check OpenAPI spec", or "verify schema".

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.

Review an Architecture Decision Record for completeness, correctness, and quality. Use when user types /review-adr or asks to review an ADR.

Start working on next Linear issue. Use when user types /pick-issue or asks to pick up the next task from the backlog.

Address PR review comments systematically. Use when user types /resolve-pr or asks to fix/address PR feedback, review comments, or requested changes.

Refresh a Linear issue to align with current docs and code state. Use when user types /refresh-issue BT-XX or asks to refresh/sync an issue with the codebase.

Execute a refactoring epic on a single branch, implementing all issues sequentially with CI verification after each. Use when user types /do-refactor or asks to execute a refactoring plan.

Break an accepted ADR into implementation issues with an Epic. Use when user types /plan-adr or asks to plan implementation of an ADR.

Research a problem and draft an Architecture Decision Record. Use when user asks to design/draft/write an ADR or make an architectural decision.

Operate the joelclaw gateway daemon — the always-on pi session that receives events, notifications, and messages. Use the joelclaw CLI for ALL gateway operations. Use when: 'restart gateway', 'gateway status', 'is gateway healthy', 'push to gateway', 'gateway not responding', 'telegram not working', 'messages not going through', 'gateway stuck', 'gateway debug', 'check gateway', 'drain queue', 'test gateway', 'stream events', or any task involving the gateway daemon.

Guides Claude from idea to working prototype using frameworks from OpenAI, Figma, and Airbnb. Use when starting new product features, planning MVP scope, making build-vs-buy decisions, or guiding users from concept to shippable prototype. Applies AI-first thinking (Kevin Weil), simplicity forcing functions (Dylan Field), and complete experience design (Brian Chesky).

Distinguishes strategic vs tactical work during development using Shreyas Doshi's frameworks and Marty Cagan's empowered teams principles. Use when making architectural decisions, choosing what to build, preventing "product theater", or applying the LNO framework (Leverage, Neutral, Overhead). Helps avoid feature factory and build work that compounds.

Builds features with A/B testing in mind using Ronny Kohavi's frameworks and Netflix/Airbnb experimentation culture. Use when implementing feature flags, choosing metrics, designing experiments, or building for fast iteration. Focuses on guardrail metrics, statistical significance, and experiment-driven development.

Drafts executive memos and stakeholder communications using Amazon's 6-pager structure, Stripe's memo format, and SCQA framework. Use when writing board updates, executive summaries, or strategic documents.

Quantum Position Engine 仓位计算引擎指南。覆盖 Decimal 精度计算、跨币种汇率换算、保证金杠杆检查、回撤熔断等核心风控逻辑。当需要计算仓位、检查风控参数、调试仓位引擎时使用此 Skill。