AI Agent Skills

Bypass an LLM's safety/guardrails to make it produce restricted output or ignore its policy. Load when testing an AI product's content controls, "jailbreak", "guardrail…

Unbounded-consumption / denial-of-wallet attacks on LLM apps — force runaway tokens, cost, or latency. Load when testing an LLM product's limits/billing, on "LLM DoS", c…

Extract or steal an ML/LLM model's parameters, training data, or system prompt via query access — model stealing, membership inference, training-data extraction. Load wh…

Test gRPC / Protocol Buffers APIs — reflection, method enumeration, authz, and injection. Load on gRPC services (HTTP/2, content-type application/grpc, .proto files, por…

A fast, ordered methodology for assessing an API end to end — REST/GraphQL/gRPC/SOAP — so nothing gets skipped. Load when the target is an API (or recon found one), on "…

Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior,

Orchestrates the test-first implementation planning workflow for feature implementation and spec changes. Use this skill whenever plan mode is active and the ta

Reviews existing test code for conformance to the test-designing-guide and test-writing-guide, then applies the refinements. Use this skill when the user wants

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "…

Write a clear, reviewable audit workpaper documenting procedures, evidence, and conclusions. Use when an auditor says "write a workpaper", "document this audit procedure…

Create a requirements traceability matrix linking requirements to design, test, and delivery. Use when the user says "traceability matrix", "RTM", "requirements traceabi…

后室 / 梦核专属空间生成 Skill。用户上传一张人物、角色、宠物或场景图片后，通过 4 个沉浸式选择题提取空间倾向，再结合参考图主体与 Backrooms Level 0 视觉语法，产出可社媒分享的专属后室切片：空间档案卡、AI 配图需求、可选 BGM 方向，并可继续生成真实摄影感后室图片或图生视频。触发词包括：后室测试、我的后室、…

Design and implement vLLM features. Given user requirements (feature description, related PRs, reference materials), produces (1) core code implementation — NO test case…

Use when a user asks for or clearly wants to be grilled, interviewed, or to stress-test a plan or design, including when they mention "grill me". Resolve material decisi…

Use when the plan rests on an unproven assumption that could be tested cheaply before committing serious effort — will people turn up, will anyone donate, does this mess…

Use before committing to a plan or significant action, when something external changes, or to stress-test reasoning. Red-teams the plan for adversarial and non-adversari…