全部能力

Generate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.

Git workflow helper for conventional commits, confidence-scored code review (lens fan-out: security, bugs, data-loss, performance, guidelines), PR description generation, pull request creation, and branch lifecycle. Use when committing changes, reviewing code, creating PRs, merging branches, or when ready to commit / push / open a PR / finish a branch. Triggers: "commit this", "create a commit", "code review", "review this PR", "review this diff", "push this", "ready to push", "create PR", "open a pull request", "summarize changes", "finish branch", "merge branch", "merge PR", "cleanup branch". Not for acceptance-criteria verification, visual design review, or session wrap-up.

Use when analyzing Xiaohongshu competitors, studying creator strategies, identifying content gaps, or finding market opportunities

MLflow experiment tracking via Python API. TRIGGERS - MLflow metrics, log backtest, experiment tracking, search runs.

Hexagonal architecture layering for Java services with strict boundaries. Trigger: When structuring Java apps by Domain/Application/Infrastructure, or refactoring toward clean architecture.

Use when implementing drag and drop, copy/paste, ShareLink, or ANY content sharing between apps or views - covers Transferable protocol, TransferRepresentation…

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures,…

Autonomous goal execution — give a goal, get a plan, confirm, execute, report. You steer, Claude drives.

Use this skill when building computer vision applications, implementing image classification, object detection, or segmentation pipelines. Triggers on image classification, object detection, YOLO, semantic segmentation, image preprocessing, data augmentation, transfer learning, CNN architectures, vision transformers, and any task requiring visual recognition or image analysis.

Expert product demonstration specialist for SaaS and B2B software. Use when preparing demos, structuring demo presentations, tailoring to stakeholders,…

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or…

Creates and registers Tambo components - generative (AI creates on-demand) and interactable (pre-placed, AI updates). Use when defining components, working…

Use when planning revenue streams, diversifying income, or scaling creator business

Detect unused/unreachable code in polyglot codebases (Python, TypeScript, Rust). TRIGGERS - dead code, unused functions, unused imports

Systematic 4-phase debugging: (1) understand the failure by reading the complete error and reproducing it, (2) find working examples to compare against, (3) test one hypothesis at a time with a single change, (4) fix the root cause and verify with tests. Includes the Three Strikes Rule (escalate after 3 failed fix attempts) and the Iron Law (no fixes without investigation). Activate when tests fail unexpectedly, errors occur, behavior is wrong, something that worked before is now broken, or a user reports a bug. Triggers on: "debug", "why is this failing", "test failure", "unexpected error", "bug", "broken", "investigate this error", "fix this bug", "tests are failing", "weird behavior", "something broke", "track down this issue". Also activates when multiple bugs need systematic investigation (one at a time, not batch-fixed). NOT for: writing new tests from scratch (use tdd), or general code review (use code-review).

Guide for building Apple-platform applications with Apollo iOS, the strongly-typed GraphQL client for Swift. Use this skill when: (1) adding Apollo iOS to a Swift Package Manager or Xcode project, (2) configuring `apollo-codegen-config.json` and running code generation, (3) configuring an `ApolloClient` with auth, interceptors, and caching, (4) writing queries, mutations, or subscriptions from SwiftUI views, (5) writing tests against generated operation mocks.

Use this skill whenever writing, reviewing, debugging, or refactoring TypeScript code that uses the Effect-TS library. Trigger when you see imports from `effect`, `effect/*`, or any `@effect/*` scoped package (schema, platform, sql, opentelemetry, cli, cluster, rpc, vitest). Trigger on Effect-specific constructs: Effect.gen generators, Schema.Struct/Schema.Class definitions, Layer/Context.Tag/Service patterns, Effect.pipe pipelines, Data.TaggedError/Data.Class error types, Ref/Queue/PubSub/Deferred concurrency primitives, Match module, Config providers, Scope/Exit/Cause/Runtime patterns, or any code using Effect's typed error channel (E parameter). Also trigger when the user asks about Effect patterns, migration from Promises/fp-ts/neverthrow to Effect, or how to structure an Effect application. Covers the full ecosystem: core Effect type, Schema validation, error management, concurrency (fibers, queues, semaphores, pools), streams/sinks, services and layers (DI), resource management, scheduling, observability, platform APIs, and AI integration. Do NOT trigger for React's useEffect, Redux side effects, or general English usage of "effect" unless the context clearly involves the Effect-TS library.

Receive and verify GitHub webhooks. Use when setting up GitHub webhook handlers, debugging signature verification, or handling repository events like push, pull_request, issues, or release.

Answer questions about Module Federation (MF) — configuration, runtime API, build plugins (Webpack/Rspack/Rsbuild/Vite), framework integration…

Set up Biome (default) or ESLint + Prettier, Vitest testing, and pre-commit hooks for any JavaScript/TypeScript project. Uses Bun as the package manager. Use…