全部能力

Provide comprehensive techniques for penetration testing AWS cloud environments. Covers IAM enumeration, privilege escalation, SSRF to metadata endpoint, S3…

使用 Model Studio DashScope Qwen TTS 模型（qwen3-tts-flash、qwen3-tts-instruct-flash）生成拟真语音音频。适用于将文本转换为语音的场景，…

Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin).…

多仓库集群代理技能 - 使用 $agent-multi-repo-swarm 调用

基础模板生成器代理技能 - 使用 $agent-base-template-generator 调用

用于身份验证的 Agent 技能 - 使用 $agent-authentication 调用

How to use the Readwise CLI — access highlights, documents, and your entire reading library from the command line

Checks bootstrap initialization, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Use when auditing app lifecycle.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language…

Audits physical architecture structure: modules, domains, layer layout, junk drawers, and framework placement. Use for structure drift.

Fixes tasks in To Rework by applying reviewer feedback, then returns to To Review. Use when task was rejected during review.

Sets up linters, pre-commit hooks, and test infrastructure. Use when adding code quality tooling to a project.

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when…

Scores each test by portfolio value and returns KEEP/DELETE/MERGE/REWRITE. Use when pruning test-suite cost.

Master Java concurrency - threads, executors, locks, CompletableFuture, virtual threads

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Write point-by-point rebuttals to reviewer comments. Extract concerns from reviews, generate evidence-based responses, and format as a structured rebuttal…

Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Use when auditing build health.

Creates core project docs (requirements, architecture, tech stack, patterns catalog). Use for any project regardless of type.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling…