[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FZWC22K057TPF60F9R3505":3,"skill-same:01M6FZWC22K057TPF60F9R3505":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":28,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6FZWC22K057TPF60F9R3505","pdd",null,"Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fpdd\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,29,30,31,32,33,34,35,36,37,38,39,40,41],"design","research","development","planning","plan","prompt","implementation","document","idea","requirements","driven","transforms","with","2026-11-10 10:12:30",false,"---\nname: pdd\ndescription: Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.\ntype: anthropic-skill\nversion: \"1.1\"\n---\n\n# Prompt-Driven Development\n\n## Overview\n\nTransform a rough idea into a detailed design with an implementation plan. The process is iterative: clarify requirements, research, design, plan — moving between phases as needed.\n\n## Important Notes\n\nThese rules apply across ALL steps:\n\n- **User-driven flow:** Never proceed to the next step without explicit user confirmation. At each transition, ask the user what they want to do next.\n- **Iterative:** The user can move between requirements clarification and research at any time. Always offer this option at phase transitions.\n- **Record as you go:** Append questions, answers, and findings to project files in real time — don't batch-write at the end.\n- **Mermaid diagrams:** Include diagrams for architectures, data flows, and component relationships in research and design documents.\n- **Sources:** Cite references and links in research documents when based on external materials.\n\n## Parameters\n\n- **rough_idea** (required): The initial concept or idea to develop\n- **project_dir** (optional, default: `specs\u002F{task_name}\u002F`): Base directory for all artifacts. `{task_name}` is derived as kebab-case from the idea (e.g., \"build a rate limiter\" → `rate-limiter`). Aligns with Ralph's spec-driven pipeline.\n\n**Constraints:**\n- You MUST ask for all required parameters upfront in a single prompt\n- You MUST support multiple input methods: direct text, file path, URL\n- You MUST derive `task_name` from the rough idea as kebab-case\n- You MUST NOT overwrite an existing project directory — ask for a new path if it already has contents\n\n## Steps\n\n### 1. Create Project Structure\n\nCreate the directory and initial files:\n- `{project_dir}\u002Frough-idea.md` — the provided rough idea\n- `{project_dir}\u002Frequirements.md` — Q&A record (initially empty)\n- `{project_dir}\u002Fresearch\u002F` — directory for research notes\n\nInform the user the structure feeds into Ralph's spec-driven presets.\n\n### 2. Initial Process Planning\n\nAsk the user their preferred starting point:\n- Requirements clarification (default)\n- Preliminary research on specific topics\n- Provide additional context first\n\n### 3. Requirements Clarification\n\nGuide the user through questions to refine the idea into a thorough specification.\n\n**Constraints:**\n- You MUST ask ONE question at a time — do not list multiple questions\n- You MUST NOT pre-populate answers or batch-write Q&A to requirements.md\n- You MUST follow this cycle for each question:\n  1. Formulate and append question to requirements.md\n  2. Present to user, wait for complete response\n  3. Append answer to requirements.md\n  4. Proceed to next question\n- You MUST ask the user if requirements clarification is complete before moving on\n\nCover edge cases, user experience, technical constraints, and success criteria. Suggest options when the user is unsure.\n\n### 4. Research\n\nConduct research on technologies, libraries, or existing code to inform the design.\n\n**Constraints:**\n- You MUST propose a research plan to the user and incorporate their suggestions\n- You MUST document findings in `{project_dir}\u002Fresearch\u002F` as separate topic files\n- You MUST periodically check in with the user to share findings and confirm direction\n- You MUST summarize key findings before moving on\n\n### 5. Iteration Checkpoint\n\nSummarize the current state of requirements and research, then ask the user:\n- Proceed to design?\n- Return to requirements clarification?\n- Conduct additional research?\n\n### 6. Create Detailed Design\n\nCreate `{project_dir}\u002Fdesign.md` as a standalone document with these sections:\n- Overview\n- Detailed Requirements (consolidated from requirements.md)\n- Architecture Overview\n- Components and Interfaces\n- Data Models\n- Error Handling\n- Acceptance Criteria (Given-When-Then format for machine verification)\n- Testing Strategy\n- Appendices (Technology Choices, Research Findings, Alternative Approaches)\n\n**Constraints:**\n- You MUST write the design as standalone — understandable without reading other files\n- You MUST consolidate all requirements from requirements.md\n- You MUST include an appendix summarizing research (technology choices, alternatives, limitations)\n- You MUST review the design with the user and iterate on feedback\n\n### 7. Develop Implementation Plan\n\nCreate `{project_dir}\u002Fplan.md` — a numbered series of incremental implementation steps.\n\n**Guiding principle:** Each step builds on previous steps, results in working demoable functionality, and follows TDD practices. No orphaned code — every step ends with integration. Core end-to-end functionality should be available as early as possible.\n\n**Constraints:**\n- You MUST include a checklist at the top of plan.md tracking each step\n- You MUST format as \"Step N:\" with: objective, implementation guidance, test requirements, integration notes, and demo description\n- You MUST ensure the plan covers all aspects of the design without duplicating design details\n\n### 8. Summarize and Present Results\n\nCreate `{project_dir}\u002Fsummary.md` listing all artifacts, a brief overview, and suggested next steps. Present this summary in the conversation.\n\n### 9. Offer Ralph Integration\n\nAsk: \"Would you like me to set up Ralph to implement this autonomously?\"\n\nIf yes, create a concise PROMPT.md (under 100 lines) with:\n- Objective statement\n- Key requirements\n- Acceptance criteria (Given-When-Then)\n- Reference to `specs\u002F{task_name}\u002F`\n\nSuggest the appropriate command:\n- Full pipeline: `ralph run --config presets\u002Fpdd-to-code-assist.yml`\n- Simpler flow: `ralph run --config presets\u002Fspec-driven.yml`\n\n## Example\n\n**Input:** \"I want to build a template management feature for our internal tool — create, edit, share templates, generate documents with custom fields.\"\n\n**Output:** A `specs\u002Ftemplate-management\u002F` directory containing rough-idea.md, requirements.md, research\u002F, design.md, plan.md, and summary.md — plus optionally a PROMPT.md for autonomous implementation.\n\n## Troubleshooting\n\n**Requirements stall:** Suggest switching to a different aspect, provide examples, or pivot to research to unblock decisions.\n\n**Research limitations:** Document what's missing, suggest alternatives with available information, ask user for additional context. Don't block progress.\n\n**Design complexity:** Break into smaller components, focus on core functionality first, suggest phased implementation, return to requirements to re-prioritize.\n","# Prompt-Driven Development\n\n## Overview\n\nTransform a rough idea into a detailed design with an implementation plan. The process is iterative: clarify requirements, research, design, plan — moving between phases as needed.\n\n## Important Notes\n\nThese rules apply across ALL steps:\n\n- **User-driven flow:** Never proceed to the next step without explicit user confirmation. At each transition, ask the user what they want to do next.\n- **Iterative:** The user can move between requirements clarification and research at any time. Always offer this option at phase transitions.\n- **Record as you go:** Append questions, answers, and findings to project files in real time — don't batch-write at the end.\n- **Mermaid diagrams:** Include diagrams for architectures, data flows, and component relationships in research and design documents.\n- **Sources:** Cite references and links in research documents when based on external materials.\n\n## Parameters\n\n- **rough_idea** (required): The initial concept or idea to develop\n- **project_dir** (optional, default: `specs\u002F{task_name}\u002F`): Base directory for all artifacts. `{task_name}` is derived as kebab-case from the idea (e.g., \"build a rate limiter\" → `rate-limiter`). Aligns with Ralph's spec-driven pipeline.\n\n**Constraints:**\n- You MUST ask for all required parameters upfront in a single prompt\n- You MUST support multiple input methods: direct text, file path, URL\n- You MUST derive `task_name` from the rough idea as kebab-case\n- You MUST NOT overwrite an existing project directory — ask for a new path if it already has contents\n\n## Steps\n\n### 1. Create Project Structure\n\nCreate the directory and initial files:\n- `{project_dir}\u002Frough-idea.md` — the provided rough idea\n- `{project_dir}\u002Frequirements.md` — Q&A record (initially empty)\n- `{project_dir}\u002Fresearch\u002F` — directory for research notes\n\nInform the user the structure feeds into Ralph's spec-driven presets.\n\n### 2. Initial Process Planning\n\nAsk the user their preferred starting point:\n- Requirements clarification (default)\n- Preliminary research on specific topics\n- Provide additional context first\n\n### 3. Requirements Clarification\n\nGuide the user through questions to refine the idea into a thorough specification.\n\n**Constraints:**\n- You MUST ask ONE question at a time — do not list multiple questions\n- You MUST NOT pre-populate answers or batch-write Q&A to requirements.md\n- You MUST follow this cycle for each question:\n  1. Formulate and append question to requirements.md\n  2. Present to user, wait for complete response\n  3. Append answer to requirements.md\n  4. Proceed to next question\n- You MUST ask the user if requirements clarification is complete before moving on\n\nCover edge cases, user experience, technical constraints, and success criteria. Suggest options when the user is unsure.\n\n### 4. Research\n\nConduct research on technologies, libraries, or existing code to inform the design.\n\n**Constraints:**\n- You MUST propose a research plan to the user and incorporate their suggestions\n- You MUST document findings in `{project_dir}\u002Fresearch\u002F` as separate topic files\n- You MUST periodically check in with the user to share findings and confirm direction\n- You MUST summarize key findings before moving on\n\n### 5. Iteration Checkpoint\n\nSummarize the current state of requirements and research, then ask the user:\n- Proceed to design?\n- Return to requirements clarification?\n- Conduct additional research?\n\n### 6. Create Detailed Design\n\nCreate `{project_dir}\u002Fdesign.md` as a standalone document with these sections:\n- Overview\n- Detailed Requirements (consolidated from requirements.md)\n- Architecture Overview\n- Components and Interfaces\n- Data Models\n- Error Handling\n- Acceptance Criteria (Given-When-Then format for machine verification)\n- Testing Strategy\n- Appendices (Technology Choices, Research Findings, Alternative Approaches)\n\n**Constraints:**\n- You MUST write the design as standalone — understandable without reading other files\n- You MUST consolidate all requirements from requirements.md\n- You MUST include an appendix summarizing research (technology choices, alternatives, limitations)\n- You MUST review the design with the user and iterate on feedback\n\n### 7. Develop Implementation Plan\n\nCreate `{project_dir}\u002Fplan.md` — a numbered series of incremental implementation steps.\n\n**Guiding principle:** Each step builds on previous steps, results in working demoable functionality, and follows TDD practices. No orphaned code — every step ends with integration. Core end-to-end functionality should be available as early as possible.\n\n**Constraints:**\n- You MUST include a checklist at the top of plan.md tracking each step\n- You MUST format as \"Step N:\" with: objective, implementation guidance, test requirements, integration notes, and demo description\n- You MUST ensure the plan covers all aspects of the design without duplicating design details\n\n### 8. Summarize and Present Results\n\nCreate `{project_dir}\u002Fsummary.md` listing all artifacts, a brief overview, and suggested next steps. Present this summary in the conversation.\n\n### 9. Offer Ralph Integration\n\nAsk: \"Would you like me to set up Ralph to implement this autonomously?\"\n\nIf yes, create a concise PROMPT.md (under 100 lines) with:\n- Objective statement\n- Key requirements\n- Acceptance criteria (Given-When-Then)\n- Reference to `specs\u002F{task_name}\u002F`\n\nSuggest the appropriate command:\n- Full pipeline: `ralph run --config presets\u002Fpdd-to-code-assist.yml`\n- Simpler flow: `ralph run --config presets\u002Fspec-driven.yml`\n\n## Example\n\n**Input:** \"I want to build a template management feature for our internal tool — create, edit, share templates, generate documents with custom fields.\"\n\n**Output:** A `specs\u002Ftemplate-management\u002F` directory containing rough-idea.md, requirements.md, research\u002F, design.md, plan.md, and summary.md — plus optionally a PROMPT.md for autonomous implementation.\n\n## Troubleshooting\n\n**Requirements stall:** Suggest switching to a different aspect, provide examples, or pivot to research to unblock decisions.\n\n**Research limitations:** Document what's missing, suggest alternatives with available information, ask user for additional context. Don't block progress.\n\n**Design complexity:** Break into smaller components, focus on core functionality first, suggest phased implementation, return to requirements to re-prioritize.\n",{"name":5,"type":47,"version":48,"description":7},"anthropic-skill","1.1","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fpaulpete\u002Fpdd",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add kbarbel640-del\u002Fskills --skill pdd",{"tool":62,"command":63},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill pdd",{"tool":65,"command":66},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill pdd","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fpdd\u002FSKILL.md",true,[70],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"_meta.json","REFERENCE","参考文档",260,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fpdd\u002F_meta.json",[77,107,131,150,156,176],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":42},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[89,90,91,41,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106],"crowd prompting","prompting","api","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":42},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[113],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[115,91,116,117,118,119,120,121,122,123,124,29,125,126,127,128,129,95,130],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","strategy","headless","compete","submit","matchmaking","use",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":42},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[137],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[139,140,141,142,143,144,145,41,146,128,130,147,91,148,149],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":151,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":42},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[154],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[142,141,140,139,149,144,145,41,143,128,130,146,147,91,148],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":42},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[163,164,165,166,167,168,169,170,171,172,173,174,175],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":186,"publishedAt":42},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[182,183],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":184,"categoryName":185,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000037","律师与法务",[187,188,189,190,41,191,192,49,193,147,194,195,196,197,198,104,199,200,201],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]