“ralph”的搜索结果

Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.

中文简介正在准备中。当前显示原文说明。

Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish

中文简介正在准备中。当前显示原文说明。

Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL

中文简介正在准备中。当前显示原文说明。

Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand voice", or mentions content strategy, voice analysis, competitive research, or iterative content improvement.

中文简介正在准备中。当前显示原文说明。

This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.

中文简介正在准备中。当前显示原文说明。

Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users do not invoke it as a workflow phase.

中文简介正在准备中。当前显示原文说明。

Run a high-thoroughness end-to-end implementation loop using clean worker worktrees, per-slice planning, implementation, explicit review/fix iteration, orchestrator integration, and final commit/PR drafting. Use when the user explicitly wants a Ralph/Wiggum-style loop, autonomous multi-agent execution, a delegated feature/bugfix carried from confirmed scope through review-ready completion, or RFC-driven implementation that should be reviewed, bumped to In Progress, decomposed into phases, and executed through nested sub-loops. Supports Codex subagents by default and external CLI workers such as OpenCode when explicitly requested and available.

中文简介正在准备中。当前显示原文说明。

Run Claude Code in autonomous iteration loops until task completion — PRD-based feature development, test coverage improvement, lint fixing, documentation generation, dataset creation, or framework migrations. Uses in-session loop mechanism with specialized templates. Triggers on autonomous loop, iterate until done, run until passing, keep going until, ralph, PRD execution.

中文简介正在准备中。当前显示原文说明。

Expert en agent loops (ARIS, Ralph, recherche autonome, build-score-budget, guardrails)

中文简介正在准备中。当前显示原文说明。

やりたいことを1行で言うと、B 型 loop engineering の 7 要素 (context / feedback / verification gate / termination / error handling / state / cost guard) を埋めた loop spec をコピペ可能な形で生成する。生成した spec は現行 Claude Code の実行プリミティブ (Workflow ツール / /loop skill / ralph-loop plugin / claude -p) に落とせる骨格になる (旧 `claude --goal` は廃止)。10 件 failure mode (F1-F10) の対策フックも自動挿入。Hybrid モード: 1 行入力 → デフォルト埋めで一発出力 → 「ここを調整したい」場所だけ短く聞き直す。Use when ユーザーが「loop を作りたい / loop-design / 自走ループ書いて / Workflow 用の spec 作って / 7 要素埋めて / verification gate ありで」と言ったとき、または `/loop-design` を実行したとき。Loop engineering の理論背景は Cards/loop-engineering-autonomous-agents、失敗モード対策は Cards/loop-failure-modes-mechanism-2026 を参照。

中文简介正在准备中。当前显示原文说明。

Ralph - persistent self-referential execution loop wrapping ultrawork with independent verifier verification

中文简介正在准备中。当前显示原文说明。

将大型功能的RFC设计提案拆分为带依赖关系和验收测试的工作单元，组织多个智能体完成调查、实现、测试与审查，再依次合并变更并验证整个系统。

• 将大型设计提案拆成可验证的任务
• 为多个智能体分配带依赖关系的工作
• 审查并依次合并变更分支

帮助设计让人工智能智能体持续工作的循环，结合质量检查、评估与失败后的停止和重试规则，处理进度停滞、反复失败及成本增长问题。

• 选择持续工作的循环方式
• 结合质量检查与评估
• 从失败或进度停滞中恢复

Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.

中文简介正在准备中。当前显示英语简介。

• Setting tool permissions before spawning a sub-agent
• Separating implementation, planning, and review roles
• Configuring agents for review without file changes

Builds and maintains a DESIGN.md brief from existing screens, documentation, and components. It records product goals, visual rules, accessibility, and implementation constraints so future interface decisions have a shared reference.

中文简介正在准备中。当前显示英语简介。

• Documenting shared rules for interface design
• Preparing a design brief before implementation
• Reconciling existing screens, assets, and design constraints

Turn a feature idea into a structured product requirements document. Clarify goals and scope through multiple-choice questions, then produce a Markdown file with small implementation tasks, checkable completion criteria, functional requirements, and success measures.

中文简介正在准备中。当前显示英语简介。

• Plan requirements for a new feature
• Clarify goals and scope before development
• Prepare specifications for developers or AI agents

Coordinate independent Squad AI teams across repositories using procedures for questions, review requests, and task delegation. Choose between direct CLI sessions, reading team metadata, and asynchronous requests based on repository access and task needs.

中文简介正在准备中。当前显示英语简介。

• Asking another Squad about architecture or past decisions
• Requesting a pull request review across repositories
• Delegating work to another repository's AI team

Plan task handoffs between agents on different machines using Git to share YAML task and result files. This implementation specification describes validation, execution limits, result reporting, and GitHub Issues as an additional route for urgent requests.

中文简介正在准备中。当前显示英语简介。

• Designing GPU task handoffs from a laptop to a DevBox
• Standardizing task and result files across machines
• Designing urgent requests through labeled GitHub Issues

Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.

中文简介正在准备中。当前显示原文说明。

Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

中文简介正在准备中。当前显示原文说明。

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

中文简介正在准备中。当前显示原文说明。

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

中文简介正在准备中。当前显示原文说明。

Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.

中文简介正在准备中。当前显示原文说明。