1,975 件 ・ 関連度順
概要と使いどころ
Apply Karpathy-inspired coding behavior guidelines — think before coding, prefer simplicity, make surgical changes, and execute toward verifiable goals. Reduces wrong assumptions, overengineering, and unintended side-effects.
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。
Çok katmanlı encoding çözme — Base64, Hex, ROT13/47, Caesar, XOR, Morse zinciri
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。
Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".
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。
直近N日（デフォルト1日）のPRレビューで繰り返し指摘されている観点のうち「実際に修正すべき」と判断できるものを集約し、リポジトリルートのCODING_GUIDELINES.mdを生成・更新したうえで、commit-push + create-prでPRを作成する。サイズが膨らみすぎないよう既存ルールとの統合・圧縮も行う。
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
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。
Dense methodology covering DNS exfiltration (dnscat2, iodine, dns2tcp), HTTPS tunneling (domain fronting, CDN abuse, legitimate service channels), ICMP tunneling (icmpsh, ptunnel-ng), cloud storage dead drops (S3 presigned URLs, Azure Blob SAS tokens, GCS signed URLs), email-based exfil (SMTP, EWS, draft method), steganography (image, audio, document metadata), encoding/encryption (base64 chunking, XOR, AES), covert channels (custom protocol tunneling, HTTP header encoding, timing channels), and data staging (compression, splitting, encryption). Tools: dnscat2, iodine, dns2tcp, PacketWhisper, chisel, stunnel, icmpsh, ptunnel-ng, steghide, zsteg, OpenStego. MITRE ATT&CK: T1048 (Exfiltration Over Alternative Protocol), T1041 (Exfiltration Over C2 Channel), T1567 (Exfiltration Over Web Service), T1029 (Scheduled Transfer), T1030 (Data Transfer Size Limits), T1132 (Data Encoding), T1001 (Data Obfuscation). Use when planning or executing data exfiltration during authorized red team engagements or post-exploita...
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。
WAF bypass techniques checklist: encoding bypass (URL/HTML/Unicode/double encoding), case variation, comment injection, HTTP header manipulation, chunked encoding, IP rotation, timing attacks, and payload obfuscation per WAF vendor. Use when WAF is blocking payloads during web app tests.
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。
ローカルにある複数のAI開発エージェントのログを集計し、トークン数やAPI換算費用をSVGカードにします。READMEや資料に載せる利用状況をまとめられます。
Spring BootやQuarkusのJavaコードを、命名、例外処理、データの変更制限、テストなどの規約に沿って書き、レビューするスキル。
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their own words for a work plan before coding. NEVER self-activates: a bare ulw/ultrawork run, an agent-side routing decision, or reading this file is not a request, and the plan-gated reviewers (metis/momus) stay locked without a user request plus a written .omo/plans plan file. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, ulw plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode.
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。
Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.
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。
搭建 Coding Agent 或设计 Agent 护栏时使用——当你要构建能自主读写代码、跑测试、自我纠错的编码 Agent，或为已有 Agent 系统补约束/验证/纠正机制、设计执行边界与验收基线、判断某类任务是否适合交给 Agent、优化 Harness 提示词与工具集时使用。覆盖 Harness 四组件、任务四象限、四条设计原则与业界实践。
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。
Runs MiniMax Code headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to MiniMax Code or obtain a MiniMax-based coding-agent result.
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。
Runs GitHub Copilot CLI programmatically for repository analysis and coding tasks. Use when the user asks to delegate work to Copilot CLI or obtain a Copilot coding-agent result.
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。
Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
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。
Runs OpenCode non-interactively for repository analysis and coding tasks. Use when the user asks to delegate work to OpenCode or compare OpenCode with another coding agent.
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。
Runs Qwen Code headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Qwen Code or obtain a Qwen-based coding-agent result.
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。
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
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 this machine's Hindsight coding-agent memory works — the plugin behind the 🧠 banner. Use when the user says "store/remember this in hindsight", asks what the memory/knowledge pages are, wants to configure per-repo memory (disable, rename banks, git depth), or something memory-related looks broken.
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。
Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.
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 local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
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。
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.
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。
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.
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。
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.
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。