yakeworld Operational Steps
- 确认输入参数完整
- 执行核心操作（参考本目录下的 scripts/ 或 references/）
- 验证输出符合契约
- 保存结果并报告
Pitfalls
-
-
Verification
-
-
-
-
1. 2. 3.
creative-tools
Purpose
Composite skill that merges 25 overlapping skills into a unified interface.
Members (25)
- ascii-art: Multiple tools for different ASCII art needs. All tools are local CLI programs or free REST APIs — no API keys required.
- ascii-video: Use when users request: ASCII video, text art video, terminal-style video, character art animation, retro text visualization, audio visualizer in ASCII, converting video to ASCII art, matrix-style effects, or any animated ASCII output.
- baoyu-comic: Adapted from baoyu-comic for Hermes Agent's tool ecosystem.
- baoyu-infographic: Adapted from baoyu-infographic for Hermes Agent's tool ecosystem.
- claude-design: Use this skill when the user asks for design work that would normally fit Claude Design, but the agent is running in a CLI/API environment instead of the hosted Claude Design web UI.
- competition-video-production: Directory index for competition-video-production: competition-video-production
- creative: 直接调用子技能名称即可：
academic-diagram、manim-video、comfyui、p5js等。 - creative-ideation: Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
- design-md: DESIGN.md is Google's open spec (Apache-2.0,
google-labs-code/design.md) for - ffmpeg-video-audio-sync: Debug and fix FFmpeg video-audio synchronization issues including duration
- figure-generation: 科研图表创建：Figure契约方法论——结论Claim→证据层级→面板映射→出口契约→审核。 支持Nature语义色板（蓝主-绿正-红基+中性色），16种排版模式。兼容所有SCI/会议图表场景。
- heartmula: HeartMuLa is a family of open-source music foundation models (Apache-2.0) that generates music conditioned on lyrics and tags, with multilingual support. Generates full songs from lyrics + tags. Comparable to Suno for open-source. Includes:
- humanizer: Identify and remove signs of AI-generated text to make writing sound natural and human. Based on Wikipedia's "Signs of AI writing" guide (maintained by WikiProject AI Cleanup), derived from observations of thousands of AI-generated text instances.
- manim-video: Directory index for manim-video: manim-video
- p5js: Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
- pil-image-generation: Python Pillow生成科技风格图像。无matplotlib依赖，适合封面/卡片/原子图。
- pixel-art: Convert any image into retro pixel art, then optionally animate it into a short
- popular-web-designs: 54 real-world design systems ready for use when generating HTML/CSS. Each template captures a
- powerpoint: 创建/读取/编辑.pptx — python-pptx: 幻灯片/表格/模板。 覆盖环境陷阱（sandbox venv无包→系统Python）、复杂表格、 多页模板化PPTX生成。关联 skill: nature-paper2ppt。
- pretext:
@chenglou/pretextis a 15KB zero-dependency TypeScript library by Cheng Lou (React core, ReasonML, Midjourney) for DOM-free multiline text measurement and layout. It does one thing: given(text, font, width), return the line breaks, per-line widths, per-grapheme positions, and total height — all via canvas measurement, no reflow. - sketch: Use this skill when the user wants to see a design direction before committing to one — exploring a UI/UX idea as disposable HTML mockups. The point is to generate 2-3 interactive variants so the user can compare visual directions side-by-side, not to produce shippable code.
- smart-home: 智能家居 — Philips Hue灯光控制。
- songsee: Generate spectrograms and multi-panel audio feature visualizations from audio files.
- songwriting-and-ai-music: Everything here is a GUIDELINE, not a rule. Art breaks rules on purpose.
- touchdesigner-mcp: 1. NEVER guess parameter names. Call
td_get_par_infofor the op type FIRST. Your training data is wrong for TD 2025.32.
IO_CONTRACT
- input:
task_desc: str, context: dict— Task description and context - output:
result: dict— Merged results from all member skills
对应原则：P3（人机分层 — 路由器负责路由，原子负责执行）
验证清单 · VERIFICATION
- 任务已路由到唯一的成员子技能（25 个 members 之一，如 ascii-art、manim-video、heartmula），而非在套件层直接执行
- 输入参数
task_desc、context符合 IO_CONTRACT（str + dict），非空且可解析 - 返回的
result: dict结构一致，能追溯至实际执行的成员技能及其输出 - TouchDesigner 相关任务未猜测参数名，先调用了
td_get_par_info获取元数据 - 设计方向探索类任务产出 2-3 个可交互 HTML 原型变体供用户对比，而非直接交付成品代码
- 任务失败时返回包含上下文与恢复建议的错误报告（含失败步骤和可操作建议），而非裸异常
约束规则 · RULES
- 输入约束: 参数类型、范围、格式必须校验
- 输出约束: 返回值结构、编码、命名必须一致
- 异常约束: 错误信息必须包含上下文和恢复建议
- 安全约束: 不执行未验证的任意代码，不暴露内部状态
Golden 集合 · GOLDEN SET
- Golden Input: 标准输入样本（覆盖正常路径）
- Golden Output: 预期输出（精确匹配或格式校验）
- Golden Error: 预期错误信息（覆盖失败路径）
Golden 集合是测试的单一真理来源。所有改进必须通过 golden 测试。
违反规则的操作视为不安全，必须拒绝或隔离。
每项验证必须可执行、可记录、可复现。验证失败时记录原因和修复。
Creative Tools
Genes (策略基因)
紧凑策略表示。条件→策略。需要深度时参考完整文档。
- [CREA-016] 面对多模态创作需求（图像/视频/音频等） → 将任务路由至对应的原子子技能（如 ascii-art, manim-video, heartmula）而非直接执行
- [CREA-017] 用户处于“有工具无方向”或寻求灵感状态 → 调用 creative-ideation 策略生成项目创意或构建方向
- [CREA-018] 需要探索 UI/UX 设计方向但未最终定稿 → 生成 2-3 个可交互的 HTML 原型变体供用户对比选择，而非直接产出可交付代码
- [CREA-019] 生成科研图表或学术 Figure → 遵循“结论Claim→证据层级→面板映射”契约，并应用 Nature 语义色板（蓝主-绿正-红基）
- [CREA-020] 处理 TouchDesigner 参数或复杂工具配置 → 严禁猜测参数名，必须先调用
td_get_par_info获取准确元数据后再操作 - [CREA-021] 生成或优化文本内容 → 应用 humanizer 策略识别并移除 AI 生成痕迹，确保文本呈现自然的人类写作风格
- [CREA-007] 执行任何创作任务前 → 严格校验输入参数完整性与有效性，确保符合 IO_CONTRACT 定义
- [CREA-008] 任务执行失败或遇到异常 → 提供包含上下文信息和明确恢复建议的错误报告，而非仅抛出异常