Навыки: Тестирование

将 Java 项目转换为标准 Maven 结构，自动重组目录、转换包名（test→example）并生成 pom.xml。当用户需要将非 Maven Java 项目转换为 Maven 项目、重构现有项目为 Maven 标准结构，或请求 Ma...

Sanity-check & validation specialist for COMAP MCM/ICM Problem C. Use when you need to check whether results are plausib...

MCP (Model Context Protocol) integration for EPCI v4.0. Manages 4 servers (Context7, Sequential, Magic, Playwright) with...

Read-only diagnostic that scans Claude Code session transcripts to surface which MCP servers and tools you actually use,...

Per-case mocked MCP override smoke skill used by skill-up e2e tests.

Find, review, and add MCP servers to the reviewed catalog that lagune.ai serves to Lagune Code. Use when asked to look f...

Validate MCP configuration and suggest improvements

Build and consume MCP well — tool design, transports, auth, injection-safe tooling, contract tests.

MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.

Manage MCP (Model Context Protocol) servers - discover, analyze, execute tools. Use for external service integrations, b...

Use when changing the MCP server in internal/mcp, its handlers or tools, [[mcp_servers]] configuration, MCP schemas, or...

Create mock MCP client for server testing with request/response simulation.

MCP mocked marker smoke skill used by skill-up e2e tests.

Use when optimizing MCP server usage to reduce token overhead. Helps select appropriate servers based on task type.

Verify an MCP server before release by exercising a real protocol session, comparing runtime capabilities with source an...

Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege...

Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, to...

MCP stdio marker smoke skill used by skill-up e2e tests.

Automated testing with Chrome DevTools MCP server ALWAYS in incognito mode to avoid cache issues

Use for stealth browser automation that bypasses bot detection. Undetected ChromeDriver for web scraping, anti-detection...

Evaluates the reliability of micro-benchmarks in preserving pairwise model rankings compared to full benchmark performan...

EU MDR 2017/745 regulation specialist and consultant for medical device requirement management. Provides comprehensive M...

Roleplay as the "Armchair Executioner" — a maximally destructive, minimally accountable peer reviewer. Use when the user...

Use intention-revealing names that explain what a variable holds or what a function does Use when enforcing code quality...

Write a SLICE's measure lens as a grounding doc (measure.md) — the delivery-measurement focus, the metrics that prove it...

Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational...

Load this skill when speed, memory, or size is the task: something is slow, a benchmark is written or read, or a change...

Define practical success measures for an initiative, including baselines, metric definitions, meaningful targets, and sa...

Review measurement instruments and results — LLM-as-instrument content scoring AND hand-tuned composite/weighted scoring...

Executes another MetaSkill, which must be located in

Build and evaluate medical text and vision applications with Google MedGemma, including MedGemma 1.5 workflows for CT, M...

Section-by-section media planning and generation. Image generation (GPT Image 2 primary, built-in fallback), logo/icon g...

Create a concise media pitch from a genuinely newsworthy angle, audience relevance, credible evidence, spokesperson or s...

Design and document a mediation guide with structured process, quality checks, and system integration

Run TTS canary tests, measure audio quality/latency, and rollback on threshold breaches. Use before rolling out new voic...

Turn one bounded meeting transcript into evidence-bound decisions, action items, a reviewable follow-up message, and pro...

Search, read, create, edit, and maintain knowledge in a Memex KB via the `mx` CLI. Use when the user asks to search the...

Expert skill for JavaScript memory leak detection using Facebook MemLab. Configure MemLab scenarios, execute memory leak...

Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what...

Embedded memory analysis, optimization, and leak detection

Audit embedded code for stack overflow risks, heap fragmentation, static allocation patterns, and memory leaks. Use when...

Avoid creating unnecessary intermediate objects in hot paths Use when optimizing code performance. Performance category...

Detect memory leaks in desktop applications through heap analysis and object tracking

Identify and diagnose memory leaks in web applications using heap snapshots, allocation timelines, and automated leak de...

Node.jsアプリケーションのメモリ監視とリーク検出パターン。PM2、V8ヒープ分析、メモリプロファイリングを活用した効率的メモリ管理を提供。 Anchors: • Observability Engineering / 適用: メモリ...

Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quan...

Run E2E memory pipeline test — embed text, store in Qdrant, search and retrieve. Use to validate the memory system is wo...

OCaml memtrace profiling for allocation hotspot analysis. Use when Claude needs to: (1) Add memtrace instrumentation to...