3,073 件 ・ 関連度順
概要と使いどころ
Analyzes malicious VBA macros embedded in Microsoft Office documents (Word, Excel, PowerPoint) to identify download cradles, payload execution, persistence mechanisms, and anti-analysis techniques. Uses olevba, oledump, and VBA deobfuscation to extract the attack chain. Activates for requests involving Office macro analysis, VBA malware investigation, maldoc analysis, or document-based threat examination.
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。
Analyzes malicious Linux ELF (Executable and Linkable Format) binaries including botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure. Covers static analysis, dynamic tracing, and reverse engineering of x86_64 and ARM ELF samples. Activates for requests involving Linux malware analysis, ELF binary investigation, Linux server compromise assessment, or container malware analysis.
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。
Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access. Builds threat detection rules from audit event patterns. Use when investigating Kubernetes cluster compromise or building k8s-specific SIEM detection rules.
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。
Diagnose and fix the bug described on this card
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。
Computer Use Agent — autonomous browser control via Steel, Browser Use, and Browserbase cloud providers. Supports headful CDP sessions, CAPTCHA solving, proxy rotation, live view, session recording/replay, Playwright/Puppeteer integration, and LLM-driven visual browsing. Use when asked about computer use, browser automation, web scraping, Steel sessions, cloud browsers, headful browsing, CAPTCHA solving, or autonomous web navigation.
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 and register a new Learning Hub article (Nuxt Content markdown under content/learn) with valid frontmatter, navigation entry, route list entry, and accurate product details. Use when adding or substantially rewriting a learn guide, reference, or tip.
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。
Add a new interactive design tool under /tools (like the color converter or contrast checker) — component, page, navigation, route lists, SEO, and tests. Use when building a new utility tool.
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。
Add a new component showcase, block, or template preview page and register it everywhere it must appear (navigation, command palette, route lists, SEO, source view). Use when adding anything under /components, /blocks, or /templates.
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。
Correlate events across multiple log files from different sources, systems, or time periods. Build unified timelines, identify causal relationships between events, and highlight anomalies that span multiple data sources. Supports timezone normalization and gap detection. Use when analyzing logs from multiple systems (frontend, backend, database, infrastructure), investigating distributed system failures, or building event timelines across services. Triggers: "correlate these logs", "build timeline from multiple logs", "cross-system analysis", "find related events across logs", "multi-source log analysis", "distributed trace analysis"
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。
管理会計ナビゲータースキル。ユーザーの相談内容を管理会計12領域に自動分類し、 適切な分析手法・実行スキルへルーティングする。予実差異分析、CVP分析、原価管理、 KPI設計、月次決算早期化など、管理会計の全領域をカバーする入口として機能。 COSO/IMA管理会計フレームワークに準拠。日英両言語対応。 Use when: ユーザーが管理会計に関する質問・相談をしたとき、どの分析手法を使うべきか 判断する入口として使用。「予算と実績の差が大きい」「原価を下げたい」「損益分岐点を知りたい」 などの相談を適切なスキルへ誘導する。 Triggers: "管理会計", "予実差異", "原価計算", "損益分岐点", "CVP", "KPI設計", "月次決算", "内製外注", "make or buy", "標準原価", "配賦", "ABC", "management accounting", "budget variance", "cost accounting", "break-even"
既存コード・既存関数・既存モジュールの暗黙契約を抽出するスキル。 戻り値型、副作用、例外、前提条件、境界条件、環境依存挙動を確認し、 reuse前のリスクを可視化する。名前やコメントではなく実際の挙動から 契約を読み取り、不一致を分類し、再利用可否を判定する。 Use when reusing legacy code, verifying actual behavior of existing functions, or extracting implicit contracts before implementation. Covers: hidden contract, implicit contract, reuse risk, legacy behavior, 暗黙契約, 既存資産調査. Analyzes return types, side effects, exceptions, preconditions, boundary conditions, and environment-dependent behavior.
Android device offensive security, forensic extraction, and mobile app exploitation. Use this whenever the user needs to: break into or bypass the lock screen of an Android phone, extract data from a seized Android device for evidence, analyze or reverse-engineer an APK to find vulnerabilities, intercept communications on an Android device, exploit Android apps via deeplinks, steal crypto wallets or app data, set up rogue WiFi to target a phone, or plan any mobile device investigation or penetration test. Also trigger when the user mentions Android forensics, mobile pentesting, law enforcement phone extraction, device exploitation, WhatsApp or Telegram extraction from a phone, Android app reversing, CVE research for Android, or needing a chain of custody for mobile evidence. Even if the user describes the scenario casually or in another language, if they need to gain access to or pull data from an Android phone, use this skill.
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。
Typosquat and malicious-package detection across installed dependencies (or a single prospective addition) — cross-checks AI-malware family intelligence, package-name similarity to known popular packages, low maintainer-health signals. Use when auditing a freshly-onboarded repo, vetting a single suspicious package, gating CI on supply-chain risk, or investigating an incident.
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。
Analyze Codex provider rollout JSONL and ego-benchmark-harness run artifacts to identify slow or failed individual tasks, tool retries, token/cost anomalies, and differences in agent execution paths. Use when users ask to analyze a Codex session or rollout, explain why a Codex task was slow or failed, inspect a Codex provider execution trace, compare Codex runs, count function_call or tool output events, or investigate agent-home/.codex/sessions.
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。
Analyze pi (coding-agent) session JSONL and ego-benchmark-harness run artifacts to explain slow or failed individual tasks, compare execution-path differences between agents or browser tools, and count tool calls and error types. Use this skill whenever users ask to analyze a pi session, explain why a task was slow or failed, compare two runs, investigate an error, locate the session corresponding to tasks.jsonl, inspect an agent execution path, count tool calls, analyze a run ID, or perform any forensic or retrospective analysis of JSONL under ~/.pi/agent/sessions/ or agent-home/.pi/agent/sessions/.
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 when the user starts a non-trivial coding/building task in Claude Code (e.g. "帮我做个 X", "help me build Y", "add feature Z", "搭一个 Z"). Layers an AI-native pedagogical coat over normal coding work — surfaces implicit assumptions in user intent, annotates non-trivial design decisions inline with brief concept-scaffolding for terms the user may not know, and replaces "should I run it?" handoffs with rigorous AI self-verification plus a clean list of what only the user can verify. Skip for pure Q&A, single-line edits, read-only investigation, or refactoring along an existing 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。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
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。
Govern Clawix accessibility changes across screen reader behavior, keyboard navigation, focus order, contrast, reduced motion, text scaling, timed interactions, and agent-generated UI.
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。
Load for Blazor/MudBlazor UI changes involving forms, dialogs, focus, keyboard navigation, landmarks, ARIA, color contrast, RTL-safe styling, or WCAG 2.2 AA tests; not for backend-only changes.
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。
Load when a task asks to research, verify, compare, or look up framework/package behavior, release notes, standards, RFCs, CVEs, or unfamiliar APIs; use repository evidence first, then official docs, and not for codebase navigation alone.
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。
Load when diagnosing a bug, exception, regression, wrong result, failing flow, or unknown root cause in repository code using callers/callees, execution flows, recent changes, and impact analysis; not for implementing a known fix without investigation.
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 code quality focusing on deep modules, naming, model hygiene, and architectural clarity. Use after a burst of development, when codebase structure needs assessment, or to make code more agent-navigable.
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。
Work with Graphite (gt) for stacked PRs. Use when creating, navigating, submitting, or managing PR stacks, or when the user mentions gt, Graphite, or stacked diffs.
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。
Time-boxed throwaway investigation to answer one hard question. Use when facing technical uncertainty before committing to a frontier item or scoped slice — the output is knowledge, not production code.
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。