「ode」の検索結果

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model cascade, route to cheap model, strong model plus cheap model, LLM cost 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。

Generate a coherent, whole-paper mathematical modeling solution framework from a complete contest problem. Use after the user supplies a CUMCM or other modeling problem and asks for modeling ideas, an overall solution plan, question-by-question analysis, candidate-model comparison, model-selection reasons, innovations, validation, or cross-question linkage. For every question, explain the task and mathematical essence, compare multiple feasible models in tables, recommend a route with explicit reasons, and keep all questions connected through shared data, variables, parameters, constraints, and validation.

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。

Multi-turn consultation with Codex CLI for second opinions, brainstorming, or collaborative problem-solving. Use when the user asks to "consult codex", "ask codex", "get codex's opinion", "brainstorm with codex", "discuss with codex", or "chat with 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。

Analyze a codebase and produce a structured threat model at .turbo/threat-model.md covering assets, trust boundaries, attack surfaces with existing mitigations, attacker stories, and calibrated severity. Use when the user asks to "create a threat model", "threat model", "threat model this codebase", "security analysis", "analyze the attack surface", "what are the threats", or "identify security risks".

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。

このスキルは、ユーザーが「プロンプトをレビューして」「対話履歴を分析して」「理解度を診断して」 と依頼したとき、または /prompt-review で呼び出されたときに使用する。 過去のAIエージェント対話履歴（Claude Code, GitHub Copilot Chat, Cursor, Cline, Roo Code, Windsurf, Antigravity, Gemini CLI, OpenAI Codex, OpenCode）を読み取り、技術理解度・プロンプティングパターン・AI依存度を推定してレポートを生成する。

Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain language. Defaults to the current branch's changes, and walks the code from the perspective of any context provided instead — a file, directory, symbol, pull request, plan, or ticket. Use when someone wants to be walked through, taught, paced through, or shown around code or a branch step by step, or to learn how a change works before reviewing or extending it. Stops after every step and waits, so the learner sets the pace. Paces through code that already exists and builds nothing — to build new work while being paced through it, use pairing. Does not produce a written overview to read alone — use code-overview. Does not review code quality — use code-review. Does not diagnose bugs — use investigate.

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。

CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling, solving, robustness, writing, compliance, and final submission review. Provides 10 stages, persistent decision state, competition-specific rules/templates, deterministic scoring helpers, numbered decisions, and Codex/Claude Code handoff. Do not trigger for generic model selection, ordinary data analysis, or non-competition paper review.

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 code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

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。

When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort. Use when the user asks for Codex or `codex exec`, when a change is complex or high-stakes enough that an independent reviewer would change the outcome, or when a delegated run needs its model, effort, or permissions chosen. For agents other than Codex 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。

Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md document that the clean-code atom will use as its override. Use when setting up coding standards, defining code quality rules, or when the user says 'setup clean code', 'define coding standards', 'code quality principles', 'coding guidelines', or 'help me define my code standards'.

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 clean code principles when generating or modifying implementation code. Enforces function focus, naming clarity, complexity management, error handling, and self-documenting style. Use when the user mentions 'clean code', 'code quality', 'coding guidelines', or 'implementation quality'. Loaded automatically by the code-generating molecules (code-forge, refactor-safely, bug-fix). This skill governs the craft of writing individual code units -- not architecture (see architecture), not security posture (see secure-coding), not test structure (see test-quality), and not refactoring workflows (see refactor-safely).

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。

Expert in understanding and navigating legacy codebases. Covers code archaeology techniques, finding hidden knowledge, mapping dependencies, and extracting understanding from code without documentation. Knows how to read the stories that old code tells. Use when "legacy code, old codebase, understand this code, archaeology, what does this do, no documentation, ancient code, " 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。

Expert in integrating Claude Code with CI/CD pipelines. Covers headless mode for non-interactive execution, GitHub Actions and GitLab CI/CD integration, automated code review, issue triage, and PR workflows. Essential for teams wanting AI-powered automation in their development pipelines. Use when "claude code CI/CD, headless mode, GitHub Actions claude, GitLab CI claude, automated code review, PR automation, issue triage, claude-code, cicd, automation, github-actions, gitlab, headless, pipeline, devops" 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。

Generate and maintain AI-readable markdown documentation for a codebase in docs/. Use this skill whenever the user asks to document their codebase, generate project docs, create architecture docs, update documentation after code changes, build a knowledge base for AI agents, create onboarding docs, map out a codebase, or explain a project structure. Also trigger when users say things like "document this repo", "create docs for my project", "update the docs", "write architecture documentation", "help AI understand my code", "generate a codebase overview", or "maintain docs". This skill is specifically about creating structured markdown files in a docs/ directory that serve as a knowledge base — NOT about writing inline code comments, README files, or API reference docs from docstrings.

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。

Delegate code review to a subagent running a specific model. Use ONLY when user explicitly names a model to review changes ("review with opus", "use sonnet to review", "review with gemini"). The root agent reconstructs changes from conversation history and spawns a subagent with the code-review skill using the specified model. Do NOT use for general code review (use code-review skill instead), for reviewing PRs from git history, or when no model is specified by the user.

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。

🇺🇸 GitHub README Writing System — Craft a README that converts visitors to stars in <3 seconds. Proven structure from AFFiNE's 0→60K star journey: tagline engineering, first-screen law, section-by-section copywriting guide, Claude Code integration section, anti-patterns, and a pre-publish checklist. Use when you need to write or rewrite a specific README file. 🇨🇳 GitHub README 写作系统 — 打造 3 秒内把访客转化为 star 的 README。来自 AFFiNE 0→60K star 实战：tagline 工程、首屏法则、逐节文案指南、Claude Code 集成板块、反模式、发布前自检清单。需要写或改一个具体 README 文件时使用。 🇯🇵 GitHub README 作成システム — 3秒以内にビジターをスターに変えるREADMEを作る。AFFiNE 0→60Kスター実績から: タグライン設計、ファーストスクリーン法則、セクション別ライティングガイド、Claude Codeインテグレーション、アンチパターン、公開前チェックリスト。 🇰🇷 GitHub README 작성 시스템 — 3초 안에 방문자를 스타로 전환하는 README 작성법. AFFiNE 0→60K 스타 실전: 태그라인 설계, 첫 화면 법칙, 섹션별 카피라이팅 가이드, Claude Code 통합 섹션, 안티패턴, 게시 전 체크리스트. Triggers: "write README" | "README template" | "GitHub README" | "project description" | "tagline" | "open source README" | "README structure" | "README review" | "fix README" | "rewrite README" | "README写作" | "写README" | "README模板" | "项目介绍" | "开源项目文案" | "改README" | "README检查" | "README 구조" | "README 작성" | "README 검토" | "READMEの書き方" | "READMEレビュー"

Query Codex banked reset credits from the local Codex Desktop login state and report available reset count plus expiration times. Use when the user asks to check Codex reset credits, reset opportunities, reset chances, reset count, rate-limit reset credits, or expiration times; also use when the user provides a codex-reset-credits-skill or codex-reset-credits runbook link and asks Codex to query the result directly.

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 safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders, downloaded Xcode DMGs/XIPs, duplicate Xcode installers, or old Xcode applications. Also use this skill proactively when you hit low storage during other work, such as a build, download, or install failing with an out-of-disk-space error. Always measure first, report recoverable GiB with evidence, and obtain explicit itemized approval before any mutation.

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。

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when: (1) Backend/logic implementation, (2) Algorithm design and optimization, (3) Bug analysis and debugging, (4) API/database code generation, (5) Code quality review and refactoring. Triggers: "implement algorithm", "debug", "analyze code", "backend task", "API implementation", "optimize performance", "refactor", "generate prototype", "code review". IMPORTANT: Default sandbox="read-only" (analysis/review/patch generation); use sandbox="workspace-write" only when codex must run tests/builds to verify. Always request unified diff patches only. Supports multi-turn sessions via SESSION_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。

显式触发的 Claude Code → Codex CLI 桥接 skill。把对话上下文 / plan / 相关文件 / 项目约定外化为 bundle 目录，调用 codex exec 并用 response.schema.json 作结构参考 + Claude Code jq 后处理校验。适用 4 场景（v1.1 起）：plan 审阅、Codex 编码、Claude-Codex 互审最多 2 轮迭代、verification-round 验证轮。

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。

Register trained models in MLflow Model Registry with version control, implement stage transitions (Staging, Production, Archived) with approval workflows, and manage model lineage with comprehensive metadata and deployment tracking. Use when promoting a trained model from experimentation to production, managing multiple model versions across development stages, implementing approval workflows for governance, rolling back to previous versions, or auditing model changes for compliance.

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。

Designs Claude Code prompts and CC environments. Produces CLAUDE.md drafts, agent topologies, scope-authorization frameworks, halt triggers, Skills/hooks/MCP plans, chat-to-CC handoff specs, and EXECUTION_PLAN.md remediation plans. Five modes: DESIGN (new CC deployments), EVOLVE (updates from friction), RESEARCH (evaluate a CC tool/pattern), TEMPLATE (reusable artifacts), REMEDIATE (consume hygiene findings → produce + execute plan). Do NOT use REMEDIATE for direct cleanup (Cat 1–10 — use rootnode-repo-hygiene Phase 2). Do NOT use for hygiene scanning (rootnode-repo-hygiene), chat prompts (rootnode-prompt-validation), or chat Projects (rootnode-project-audit).

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 RFDB data disappearing after compaction, where rfdb-server reports a tiny node count (e.g. "15 nodes") on startup despite manifest_index.json showing hundreds of thousands of nodes and segment files existing on disk. Use when: (1) rfdb-server logs "Default database: N nodes" with N orders of magnitude smaller than recent analysis output, (2) /api/stats returns only the most recent commit's nodes, (3) the issue appears AFTER a compaction event (manifest with l1_node_segments populated and node_segments: []), (4) subsequent commits dropped L1 references. Root cause: ManifestStore::create_manifest() initializes l1_node_segments/l1_edge_segments to Vec::new() instead of cloning from current manifest, so any commit AFTER compaction silently orphans all L1 data even though segment .seg files still exist on disk. Compaction injects L1 fields explicitly after create_manifest, but regular commits do not.

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 node query issues in Grafema tests when nodes have numeric IDs instead of human-readable IDs, or when `type` field is undefined. Use when: (1) queryNodes returns nodes with numeric IDs like "52710336597754872375318185843222727675" instead of semantic IDs like "net:request#__network__", (2) node.type is undefined but node.nodeType has a value, (3) metadata is a JSON string instead of parsed object, (4) tests fail with "Cannot read property 'length' of undefined" after queryNodes. Covers RFDBServerBackend vs RFDBClient distinction and async generator handling.

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。