发现 Skills

Thorough codebase search

Systematic debugging framework: symptom capture, evidence analysis, hypothesis generation, bisection strategy, log analysis, instrumentation, and minimal reproduction design. Transforms ad-hoc debugging into structured investigation with ranked hypotheses and concrete investigation plans. Triggers on: "debug this", "why is this failing", "root cause", "investigate", "diagnose", "this error", "this exception", "this stacktrace", "not working", "broken", "unexpected behavior", "bisect", "narrow down", "isolate the issue", "help me debug". Use this skill when confronted with a bug, error, or unexpected behavior in any codebase.

Evaluates RAG (Retrieval-Augmented Generation) pipeline quality across retrieval and generation stages. Measures precision, recall, MRR for retrieval; groundedness, completeness, and hallucination rate for generation. Diagnoses failure root causes and recommends chunk, retrieval, and prompt improvements. Triggers on: "audit RAG", "RAG quality", "evaluate retrieval", "hallucination detection", "retrieval precision", "why is RAG failing", "RAG diagnosis", "retrieval quality", "RAG evaluation", "chunk quality", "RAG pipeline review", "grounding check". Use this skill when diagnosing or evaluating a RAG pipeline's quality.

Analyze GitHub repository security alerts and generate remediation plans. Use when the user asks to review security alerts, fix vulnerabilities, check dependabot alerts, review code scanning issues, or address secret scanning findings for a GitHub repository. Triggers on requests mentioning GitHub security, repo security review, vulnerability remediation, or security audit.

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or when you need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.

AST-aware code search and refactoring using ast-grep (sg). Use INSTEAD of grep/ripgrep for searching code structure. Finds functions, classes, patterns, anti-patterns across Go, Python, Bash, Terraform/HCL codebases. Triggers on "ast-grep", "sg", "find function", "find class", "find method", "find all usages", "where is X used", "search for pattern", "find anti-pattern", "code smell", "refactor pattern", "structural search", "AST search", "find error handling", "find imports", "find decorators", "find struct", "find interface", "search code", "locate function", "grep for function", "find definition". PROACTIVE: Use for ANY code search task; prefer over grep/ripgrep for code files.

MCP server that enforces architectural constraints and prevents AI agents from breaking codebases via RAG-powered semantic search. Use when setting up RAG for code search, when agents ignore API contracts or architectural patterns, when your existing RAG is unreliable, or when you need constraint enforcement (not just code search). Triggers on "set up RAG", "agents keep breaking my architecture", "build constraint enforcement", "my RAG keeps breaking", or "prevent agents from guessing".

MCP server that enforces architectural constraints and prevents AI agents from breaking codebases via RAG-powered semantic search. Use when setting up RAG for code search, when agents ignore API contracts or architectural patterns, when your existing RAG is unreliable, or when you need constraint enforcement (not just code search). Triggers on "set up RAG", "agents keep breaking my architecture", "build constraint enforcement", "my RAG keeps breaking", or "prevent agents from guessing".

Automate Ambient Weather tasks via Rube MCP (Composio). Always search tools first for current schemas.

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

Testing best practices for the frontend. Emphasizes E2E tests over unit tests, minimal mocking, and testing behavior over implementation details. Use when writing tests or reviewing test code.

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

Use for Slurm, sbatch, squeue, sacct, logs, quotas, scratch/work storage, micromamba, and HPC job debugging.

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. I...

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architec...

Automatically reviews data pipelines, optimizes SQL queries, and ensures data quality. Activates when you mention: data pipeline, ETL, SQL optimization, query performance, data quality, schema design, Airflow DAG, database index, slow query. Provides: Pipeline design patterns, SQL query optimization, index recommendations, data validation strategies, schema improvements. Supports: PostgreSQL, MySQL, SQLAlchemy, Prisma, Spring Data JPA

Use this skill when the user asks to 'write an email', 'draft a message', 'status update email', 'meeting follow-up', 'formulate in German', 'wie formuliere ich', or needs help with German business communication such as emails, status updates, and meeting notes.

Use when user has complex multi-agent workflows, needs to coordinate sequential or parallel agent execution, wants workflow visualization and control, or mentions automating repetitive multi-agent processes - guides discovery and usage of the orchestration system

Follow the end-of-session git checklist before handing off.

Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend Markdown, modify HTML, or add custom functionality

Standardize mapping (DTOs/contracts/persistence models) using source-generated mappers and explicit boundary conversions.

Use when setting up or optimizing local development environments for fast feedback loops. Applies to any project where iteration speed matters. Covers hot reload, incremental builds, test filtering, IDE optimization, and multi-service local development patterns.

Use when you see memory warnings, 'retain cycle', app crashes from memory pressure, or when asking 'why is my app using so much memory', 'how do I find memory leaks', 'my deinit is never called', 'Instruments shows memory growth', 'app crashes after 10 minutes' - systematic memory leak detection and fixes for iOS/macOS

Create formal specifications for a component or behavior using TLA+, SysML, or state machines. Intended for safety-critical systems.