「code mode」の検索結果

Extract abstract mathematical models from functional code (Haskell, OCaml, F#) for formal reasoning in Isabelle/HOL. Use when users need to: (1) Convert functional programs to Isabelle definitions, (2) Extract high-level algorithm essence from implementation code, (3) Generate formal specifications and properties from code, (4) Create verification-ready models that capture mathematical properties while abstracting away implementation details. Focuses on structural recursion, algebraic data types, higher-order functions, and invariant extraction.

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。

Extract abstract mathematical models from imperative code (C, C++, Python, Java, etc.) suitable for formal reasoning in Coq. Use when the user asks to model imperative code in Coq, create Coq specifications from imperative programs, extract mathematical models for verification, or translate imperative algorithms to Coq for formal reasoning and proof.

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 a task may benefit from a bounded subagent for implementation, large-codebase discovery at task start, independent review, requested or pre-commit code simplification, or expert work on complex decisions, modeling, automation, or repeated failures. The main agent chooses whether to delegate and accepts the result. Do not use for simple questions or short work with no meaningful review or delegation.

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。

Implement complete dark mode for any frontend project. Auto-detects theme system (Flutter ThemeData, Tailwind dark class, CSS variables, MUI, Chakra UI, styled-components), generates a dark color palette with proper surface elevation hierarchy and desaturated brand colors, creates a theme toggle with system preference detection and persistence, migrates all hardcoded colors to theme tokens, handles special cases like images, shadows, form inputs, and charts, then verifies WCAG AA contrast ratios for both modes. Use when you need to add dark mode, fix dark theme contrast issues, create a theme switcher, or migrate hardcoded colors to theme-aware tokens.

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。

Papers With Code MCP tools for searching and reading AI/ML papers, discovering recent and trending research, finding related work and paper lineage, browsing tasks, methods, conferences, organizations, and frameworks, and inspecting benchmark leaderboards with model-size and metric filters through the public Papers With Code catalog. Use whenever the user asks to find papers, survey literature, compare research, inspect an arXiv paper, explore AI/ML taxonomy or conferences, discover benchmarks or state-of-the-art models, or mentions Papers With Code, the PwC MCP server, or paperswithcode.co/mcp.

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。

Security vulnerabilities in AI-generated code and LLM applications, covering OWASP Top 10 for LLMs, secure coding patterns, and AI-specific threat modelsUse when "ai code security, llm vulnerabilities, ai generated code review, owasp llm, secure ai development, security, ai, llm, owasp, code-review, vulnerabilities" mentioned.

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 experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".

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。

arkcli helper：为 Claude Code / Codex / OpenCode / OpenClaw / Hermes / ZCode 配置火山方舟 Plan 或 Platform Endpoint 的 model/provider，或给支持的 Agent（含 MCP-only Trae）配置 Harness 工具。真人 TTY 运行 `arkcli helper` 可选择模型和 Harness 能力；`helper mcp` 默认保持整组 Agent Plan MCP 行为，传 `--capability datapro|web-search|agent-memory` 只配单项，传 `--capability cua` 只给目标 Agent 安装云电脑 Skill；连 model/provider 一起配置用 `helper configure`，查状态用 `helper list`，移除用 `helper reset`。Agent Plan / Team 还支持专业数据集、豆包搜索、Agent 记忆、AI Native 应用开发底座、Agent 进化与 routing.v1 强制检索路由；上下文出现 ARKCLI ROUTING ENFORCEMENT / routing.v1，或用户要求在豆包搜索、DataPro、OpenViking、Supabase 之间强制分流时也使用本 Skill：调用这四类受管 Provider 前先提交 Route Plan，再调用唯一授权 Provider；原生 WebSearch/WebFetch/WebExtract 位于路由管理范围之外。Platform 只允许本人创建、Running、已验证为文本输出的 Endpoint，不配置 MCP、Supabase 或强制路由。豆包搜索配置成功后默认关闭目标客户端原生 WebSearch；传 `--keep-native-websearch` 可保留，并可用 `helper reset` 完整恢复 ArkCLI 配置。

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 coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama, LM Studio), Claude/OpenAI calls, or when Claude should do the work itself.

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 for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.

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。

Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer that fails differently from the authors, run to clean — distinct from the recursive-refinement ladder. Invoked by the team lead from the unified pre-ship gate (code-mode and /swarm:refine) after the ship steps.

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 /insights-style HTML report across MANY of your agent coding sessions (Claude Code and OpenAI Codex): what you work on, how you use the agent, your wins, your friction points, and concrete fixes to become more effective — precise goal-setting, not trusting output blindly, scoping, context hygiene, right-sizing models. Reads local session history and writes one self-contained report.html. Use when the user asks to "разбери мои сессии", "оцени как я работаю с агентом", "мой insights", "session insights report", "review how I work", "на что обратить внимание", or runs "/mentor", "/mentor claude", "/mentor codex", "/mentor both". Do NOT use for reviewing the CODE produced (that's code-review) or building the 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。

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

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 Fable 5 and OpenAI Codex as co-founders on the Rocket Fuel operating system. Fable is the Visionary (vision, plan, standards, final review); Codex is the Integrator (filters the plan, executes the build, reports). Context-routed, one entry point, four functions: KICKOFF a new project, CLARITY BREAK to refactor an existing one, SAME PAGE MEETING to pressure-test a plan, BUILD A ROCK to hand Codex a scoped task. Use when the user says /rocket-fuel, wants to start or refactor a project with Codex, wants a plan reviewed by a second model, or wants to delegate a build to Codex.

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。

Survey existing forecasting code or models in a codebase — find gaps, stale models, and missing validation. Use when asked "what forecasting models do we have", "audit our forecasts", or "find stale models".

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。

Generates 3-5 conceptually distinct approaches labeled Novel, Surprising, Diverse, or Conventional, and holds for the user's selection before implementing. The --codex mode runs the brainstorm on GPT-6 Astra via codex exec, then has Codex implement the selected approach. Use before committing to an approach when a creative, architectural, or analytical task has more than one non-obvious solution; use --codex when another model family should widen the range.

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。

Updates an existing OpenCode skill to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode skill", "fix opencode skill", "migrate skill to opencode", or wants to modernize an existing OpenCode SKILL.md file.

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。

Updates an existing OpenCode command to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode command", "fix opencode command", "migrate command to opencode", or wants to modernize an existing OpenCode command file.

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。

Updates an existing OpenCode agent to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode agent", "fix opencode agent", "migrate agent to opencode", or wants to modernize an existing OpenCode agent file.

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。

List configured models, guide provider setup, verify local Kimi companion readiness, and manage the PreToolUse hook plus optional review gate. Use when asked about available models, subscription/API-key setup, default selection, or explicitly requested to install, check, enable, disable, or uninstall the integration. Codex and Claude Code share one ~/.kimi-code/config.toml but each own a host-scoped block, so $kimi-setup here does not disturb Claude Code's /kimi:setup (and vice-versa).

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。

Fix intermittent `{:no_translation, :unicode, :latin1}` crashes in Elixir escript daemons that use length-prefixed framed IPC on stdin/stdout. Use when: (1) daemon worker crashes only on some input files, usually ones with non-ASCII bytes (kanji, cyrillic, emoji); (2) error surfaces as `Protocol error` from daemon's error branch or as garbled frame-length bytes seen by the orchestrator/client side; (3) standalone one-shot mode works fine on the same input but multi-request daemon mode fails; (4) `IO.binread(:stdio, N)` returns `{:error, {:no_translation, :unicode, :latin1}}` despite the "bin" prefix suggesting it should be encoding-agnostic. Root cause is the escript default `:standard_io` encoding — it's `:unicode`, and `IO.binread` still routes through the io_server, which translates bytes to codepoints and errors when raw binary frames contain invalid UTF-8 sequences.

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。

为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。 包含创建适配器、实现必需接口与注册安装流程。 适用：Decoder-only LLM、理解类 VLM（仅 LLM/text 部分）。 多模态生成（DiT/扩散，含双/多专家）见下方「多模态生成扩展」节，按需加载。 不适用：Encoder-only、非 Transformers 架构。

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。

Design a viable business model for a one-person company using Lean Canvas and a simplified Business Model Canvas. Use when Codex needs to explain the business-model concepts when needed, verify niche and value-proposition prerequisites, ask one question at a time, present multiple model choices, and write user-confirmed outputs into `opc-doc/`.

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。

Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions); tech selection; ADR research; migration/refactor planning; performance/security analysis; tests; code reviews; any spec/plan/design/ADR referencing project. WRITE MODE — NET DELTA vs. last doc sync: additions/modifications/REMOVALS/deprecations of previously-synced code or decisions (docs revert: delete BCU file/ADR), AND rollbacks. User signals: sync docs/done/ready to commit/pre-commit/record decision. Auto-fires before final task-completion reply. WRITE MODE does NOT fire on: brainstorming, generic/read-only Q&A, in-session try-and-undo with no net change, already-synced.

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。