「window」の検索結果

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

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 the Crabbox wrapper for OpenClaw remote validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

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。

Run a marketing objective to completion over hours, days, or weeks — not a single deliverable. Takes a business outcome ("40 qualified demos a month from organic by Q4", "cut blended CAC below $90", "launch the product in September"), decomposes it into work items with declared ECO floors, executes them across context windows with resumable state, and stops only when an independent gate returns SHIPPED or CLOSED. Use when the request is an outcome rather than an artifact, when work must continue in the background or across sessions, or when the user says "goal", "run this until", "keep working on", "autonomous", "long-running", "over the next month", or "get us to <number>".

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。

Participate in DojoZero prediction games, including NBA and FIFA World Cup trials. Use when user wants to find games, join them, check scores/odds, place bets or prediction-window picks, or view leaderboards.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for race windows, ordering bugs, idempotency failures, lock gaps, concurrent worker drift, and state inconsistencies that produce decisive effects. Use when the user asks to reproduce timing-sensitive bugs, concurrent state corruption, duplicate actions, stale reads, or privilege or balance drift caused by request ordering. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries, prompts, hosts, or identities that should be treated as sandbox-internal by default and Codex needs to choose, route, and load the right downstream analysis path with concise evidence.

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 the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for LSASS-resident secrets, Windows logon sessions, Kerberos ticket caches, DPAPI-backed material, SSP artifacts, and replayable credential extraction. Use when the user asks to inspect LSASS memory, recover tickets or logon sessions, trace DPAPI or SSP material, distinguish which credential artifacts are replayable, or connect host-resident credential material to an accepted pivot or privilege edge. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DPAPI masterkeys, vault blobs, browser credential stores, protected secrets, domain backup keys, and secret-to-acceptance replay chains. Use when the user asks to inspect DPAPI blobs or masterkeys, recover browser or vault credentials, trace DPAPI context or backup-key use, or explain how protected Windows secrets become accepted access or privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

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。

Search and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use, vision, streaming, batch), Agent SDK (Python and TypeScript), prompt engineering, and all Anthropic platform docs. Use this skill whenever the user asks about Claude Code features (hooks, MCP servers, skills, plugins, settings, permissions, keybindings, sub-agents), the Anthropic API or any of its SDKs (Python, TypeScript, Go, Java), the Agent SDK (sessions, hooks, custom tools, MCP), model capabilities (context windows, extended thinking, pricing, rate limits, vision), prompt engineering best practices, or troubleshooting any Claude-related error. This skill provides instant access to official documentation files without web searches — always prefer it over web lookups for Claude and Anthropic topics.

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。

Strategic analysis gate for existing products — multi-dimensional evaluation (tech, product, design, business) using Design Thinking + 9 Windows (TRIZ) + Double Diamond. Outputs 2-3 qualified options with recommendations. Use BEFORE cm-planning for complex initiatives and enhancements on existing codebases.

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。

Bubble Tea is a powerful Go framework for building terminal user interfaces based on The Elm Architecture. Developed by Charmbracelet, it supports inline, full-window, and mixed TUI applications with a high-performance cell-based renderer and declarative views.

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。

A source-backed ASE skill for Beekeeper Studio, the SQL editor and database manager for Linux, macOS, and Windows. It fits workflows that need a real client for querying, browsing tables, and working across PostgreSQL, MySQL, SQLite, SQL Server, and other supported databases.

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。

ActivityWatch is a privacy-first, open-source automated time tracker that records application usage, browser activity, and AFK status across Windows, macOS, and Linux. With 16k+ GitHub stars, it provides detailed productivity analytics without sending data to external servers.

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。

Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered sources. Skip one file, one function, a single needle, or a one-page PDF conversion. Triggers: long context, context rot, large codebase, many files, all files, big document, multi-document, PDF, aggregate, summarize everything, codebase-wide, multi-hop, recursive, sub-agents, map-reduce.

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。

Shell and session operations after an attack module already established command execution, a raw shell, webshell channel, container/runner shell, or remote session. This module does not own exploitation and should not pull SSH/WinRM/RDP authentication or vulnerability-to-shell chains out of Web/AD/Cloud/K8s/CI-CD/Service/Phishing. Use it to bootstrap a usable callback from existing command execution, stabilize Linux PTY, upgrade Windows sessions with ConPTY where applicable, manage listeners, recover fragile sessions, and exchange files for continued operations.

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。

Credential operations: secret discovery, classification, extraction, conversion, offline cracking of hashes the operator already has as a credential job, policy-aware spraying, NetNTLM capture, generic SMB relay, and Windows/Linux harvest. Do not hijack an in-progress /ad-attack Kerberoast/AS-REP chain (that module cracks and uses the ticket itself). Do not DCSync, read LAPS LDAP, or escalate cloud IAM. Usable credentials are recorded; the operator chooses the next module.

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。

OS post-exploitation after a stable host foothold: quiet host recon, host-native persistence (Windows Run/tasks/services/COM/WMI and Linux SSH/cron/systemd/SUID), long-term C2 (Sliver primary, Mythic/Havoc optional), targeted collection and exfil, and engagement cleanup. Does not own AD/cloud/K8s native persistence, Ligolo pivoting, LSASS dumping, or EDR bypass. Operator selects objectives; success is a live callback, verified persistence, delivered loot, or restored host — not generating an unused implant.

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。

Active Directory reconnaissance with or without credentials: user/group/computer enumeration, ACL/delegation, ADCS, modern Windows LAPS, BloodHound, Server 2025/dMSA/Ghost SPN candidates, and trust mapping. Recon only — do not exploit Kerberoast-to-DA, DCSync, or change passwords. Operator may select /ad-attack after cards are ready.

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。

Reference patterns for search, optimization, and greedy algorithms. Covers binary search (classic and on-answer), two pointers, sliding window, greedy strategies, prefix sums, merge intervals, and monotonic stack. Use when solving problems that involve searching sorted data, optimizing over constraints, processing subarrays/substrings, or reducing range queries.

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。

Synthesizes DCM market activity with new issue spreads, fund flows, and market technical analysis for issuance timing. Use when analyzing debt market windows, timing bond issuance, or assessing market receptivity.

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。

Initiate a session handoff to transfer context and pending actions to a new terminal session. Executing this skill safely drains tasks and launches a new cross-platform window natively.

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。

Token-range severity zones (Green/Yellow/Orange/Red/Critical) with detection checklist, early warning indicators, and corrective routing actions for context window degradation

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 when agents are stuck in repetitive action loops using a rolling 20-action window with escalating nudges — replan after 3 similar actions, explore after 5, force-done after 8.

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。