AgentShield を使用して、Claude Code の設定（.claude/ ディレクトリ）のセキュリティ脆弱性、設定ミス、インジェクションリスクをスキャンします。CLAUDE.md、settings.json、MCP サーバー、フック、エージェント定義をチェックします。

Comprehensive documentation synchronization - scan local git changes and propagate updates to ALL design docs, task lists, specs, diagrams, and planning artifacts. Use when finishing a feature, after merging, or when design docs are out of date.

Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures.

Configure mutual TLS (mTLS) for zero-trust service-to-service communication. Use when implementing zero-trust networking, certificate management, or securing internal service communication.

Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.

Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal at Recurrence-Count >= 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use `self-healing` instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.

Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.

Work with Dynatrace notebooks - create, modify, query, and analyze notebook JSON including sections, DQL queries, and visualizations.

Optimize test suites using mutation testing to maximize mutation kill rate with minimal tests. Use when you need to reduce test suite size while maintaining quality, identify redundant tests, improve mutation coverage, or validate test effectiveness. The skill analyzes test coverage, execution intervals, and redundancy using mutation operators, selects or generates a minimal subset of tests that maximizes mutation kill rate, and outputs an optimized test suite with detailed reports showing killed and surviving mutants. Supports multiple programming languages and mutation testing frameworks.

Compare behavior across multiple versions of programs or repositories. Use when you need to analyze how functionality changes between versions, identify regressions, compare outputs and exceptions, or validate upgrades. The skill compares execution behavior, test results, outputs, exceptions, and observable states across versions, generating detailed reports showing behavioral divergences, potential regressions, added/removed functionality, and areas requiring validation. Supports multiple programming languages and can work with test suites or execution traces.

Generate bytecode classes from DSL scripts (MAL, OAL, LAL, Hierarchy). Runs the compiler and dumps .class files for inspection.

当任务需要写代码实际获取A股数据时使用——拉取行情/K线(mootdx+腾讯+百度)、研报(东财+同花顺+iwencai)、信号(热点/北向/龙虎榜/解禁/行业)、资金面(融资融券/大宗/股东户数/分红/资金流)、新闻、财务三表/F10、公告(巨潮)、打板(涨停池/连板/炸板率/重点监控池/日内异动)、ETF期权(T型报价/希腊字母/IV)、舆情互动(互动易/热榜/人气榜)等真实数据。十层数据源·47端点(含3官方备胎)·内嵌全部可运行代码，自包含零依赖外部文件；优先用通达信(mootdx)/腾讯(不封IP)，东财接口已内置限流防封，主源被封可查「备用源速查」降级。仅在需要调用数据接口取数时使用：A股概念解释、投资观点讨论、策略问答等无需取数的话题不要加载本skill。

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Get current weather and forecasts (no API key required).

Implements RESTful API design with versioning and request specs. Use when building APIs, adding API endpoints, versioning APIs, or when user mentions REST, JSON API, or API design.

Use when the user wants to create a visual code review on a Miro board from a pull/merge request (GitHub, GitLab, or any forge), local uncommitted changes, or a branch comparison — produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR.