テスト設計、脆弱性診断、品質保証（1.3万 件）
概要と使いどころ
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
日本語の概要は準備中です。原文の説明を表示しています。
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
日本語の概要は準備中です。原文の説明を表示しています。
Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the user asks to scan, audit or check code with Claude Security, to scan their changes with Claude Security, or to fix or patch Claude Security findings.
日本語の概要は準備中です。原文の説明を表示しています。
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head. Use when asked to monitor, babysit, retry, or fix PR CI for lint.yml, pr-test.yml, pr-test-extra.yml, AMD, or other named workflows; classify failures as PR-related versus flaky or infrastructural, auto-fix and push only small clean fixes, rerun failed jobs only up to 10 times, and ignore unselected workflows.
日本語の概要は準備中です。原文の説明を表示しています。
Workflow for upgrading/integrating cache-dit in SGLang diffusion (multimodal_gen): DBCache, DMD calibrator, TaylorSeer, SVDQuant DQ; porting upstream PRs and resolving conflicts against the per-request knob system; adding new cache knobs; building the sglang generate CLI test matrix; precision validation (PSNR / log evidence); troubleshooting environment issues (wheel ABI, svdq extension, flashinfer conflicts). Use when upgrading or integrating cache-dit in sglang diffusion, porting cache-dit PRs with conflicts, adding cache knobs, running the sglang generate CLI test matrix, or validating precision (PSNR) for DBCache/DMD/SVDQuant(DQ) paths.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock testing, and test placement. Always read test/README.md for the full CI layout, how to run tests, and extra tips. Use when creating new tests, adding CI test cases, writing unit tests, or when the user asks to add tests for SGLang features.
日本語の概要は準備中です。原文の説明を表示しています。
Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations. Use with add-jit-kernel, add-sgl-kernel, and write-sglang-test for placement and migration checks.
日本語の概要は準備中です。原文の説明を表示しています。
Audit the existing test tree and CI configuration for improvements, using a catalog of patterns previously applied in this repo. Use when asked to audit tests or CI, shrink CI time or cost, find redundant or misplaced tests, clean up a test group, or review whether a CI change follows established practice.
日本語の概要は準備中です。原文の説明を表示しています。
Investigate consistently failing SGLang CI tests by extracting the failure signature from scheduled or rerun workflows, bisecting the passing/failing commit window, checking runner or hardware specificity, and optionally reproducing on a remote GPU host.
日本語の概要は準備中です。原文の説明を表示しています。
Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)
日本語の概要は準備中です。原文の説明を表示しています。
How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing against it. Load this before touching server_args, model overrides, module-level state, or per-forward state in sglang.
日本語の概要は準備中です。原文の説明を表示しています。
Generate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.
日本語の概要は準備中です。原文の説明を表示しています。
Audit SGLang startup logs, save evidence, and propose cleanup for user review. With no arguments, run Qwen3-8B at TP1 and TP2 plus gpt-oss-20b at TP1.
日本語の概要は準備中です。原文の説明を表示しています。
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a divergence to a single operator. Use when adding a KL test to a model, picking or defending a kl_div threshold, or investigating a KL number that is too high.
日本語の概要は準備中です。原文の説明を表示しています。
当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 `cdp_port`）；`headed` 控制是否显示窗口，`private_mode` 保留用于兼容、不再改变默认行为，`browser_args` 传入额外的 Chromium 启动参数，`executable_path` 指定自定义浏览器可执行文件路径。
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit `cdp_port` to let another local tool attach); `headed` controls whether the window is visible, and `private_mode` is kept for backward compatibility and no longer changes the default.
日本語の概要は準備中です。原文の説明を表示しています。
Maps topics and keywords from user questions to QwenPaw official documentation paths and common source code entry points, reducing blind searching. Intended for the built-in QA Agent to quickly identify which files to read when answering questions about installation, configuration, skills, MCP, multi-agent, memory, CLI, etc.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever you need the allowed_tools / skills preset for a sub-agent role before calling spawn_subagent. Trigger especially when user mentions: "role", "spawn_subagent", "allowed_tools", or any OMP role name (executor, architect, analyst, critic, security-reviewer, code-reviewer, qa-tester, planner, explore, debugger, verifier). Also use when a /ultrawork, /ralph, /autopilot, /ultraqa, or /team workflow step asks for role tool/skill configuration.
日本語の概要は準備中です。原文の説明を表示しています。
将用户问题中的主题、关键词映射到 QwenPaw 官方文档路径与常见源码入口，减少盲目搜索。适用于内置 QA Agent 在回答安装、配置、技能、MCP、多智能体、记忆、CLI 等问题时快速选定要读的文件。
日本語の概要は準備中です。原文の説明を表示しています。
Risk measurement and stress testing — VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario stress testing.
日本語の概要は準備中です。原文の説明を表示しています。
Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets using mokutil, efi-readvar/dbxtool, CHIPSEC, sbverify/pesign, and Windows Confirm-SecureBootUEFI. Use when auditing fleet dbx rollout after a bootkit advisory or hunting for pre-OS persistence on a suspected-compromised endpoint.
日本語の概要は準備中です。原文の説明を表示しています。
Detect and prevent QR code phishing (quishing) attacks that embed malicious URLs inside QR code images to bypass link-based email security, using image-based threat detection, OCR/QR decoding, and mobile-side scanning (Microsoft Defender for O365, Proofpoint TAP, Barracuda Multimodal AI). Use when configuring gateway rules against QR phishing or investigating suspicious emails containing QR codes.
日本語の概要は準備中です。原文の説明を表示しています。
Scans GitHub Actions workflows and CI/CD pipeline configurations for supply chain attack vectors including unpinned actions, script injection via expressions, dependency confusion, and secrets exposure. Uses PyGithub and YAML parsing for automated audit. Use when hardening CI/CD pipelines or investigating compromised build systems.
日本語の概要は準備中です。原文の説明を表示しています。
Detect RDP brute force attacks by parsing Windows Security Event Logs (EVTX files, via python-evtx) for failed logon patterns (Event ID 4625, Logon Type 10/3), correlating with successful logons (Event ID 4624), and analyzing NLA failures and source IP frequency. Use when investigating exposed RDP endpoints, building SIEM detection rules for credential guessing, or confirming whether a compromised account followed a brute-force pattern.
日本語の概要は準備中です。原文の説明を表示しています。