[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2046":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":8,"languages":8,"totalLinesOfCode":8,"stars":9,"forks":10,"watchers":11,"openIssues":12,"contributorsCount":12,"subscribersCount":12,"size":12,"stars1d":11,"stars7d":13,"stars30d":14,"stars90d":12,"forks30d":12,"starsTrendScore":15,"compositeScore":16,"rankGlobal":8,"rankLanguage":8,"license":8,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":17,"hasPages":17,"topics":19,"createdAt":8,"pushedAt":8,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":12,"starSnapshotCount":12,"syncStatus":23,"lastSyncTime":24,"discoverSource":25},2046,"manual-SDD","LIDR-academy\u002Fmanual-SDD","LIDR-academy",null,43,39,1,0,8,9,3,45.71,false,"main",[],"2026-06-12 04:00:13","# AI Specs for Skills-First Development\n\nThis project is a practical manual and starter kit for running a complete **Spec-Driven Development (SDD)** workflow with AI, from product requirements and implementation planning to coding, verification, and code review. It provides a skills-first, reusable structure you can copy into your own repository to operationalize SDD in day-to-day delivery.\n\nIt is useful because it turns SDD from a high-level idea into a repeatable system with shared standards, canonical prompts, and portable conventions that stay consistent across Codex, Cursor, and Claude.\n\nIt is highly recommended to use it with a spec-driven process such as OpenSpec.\n\n\nIf you want to try our best-practices in an Openspec-ready ecosystem, check out our [Openspec AI Specs alternative](https:\u002F\u002Fgithub.com\u002FLIDR-academy\u002Fai-specs) \n\n## Repository Structure\n\n```text\n.\n├── ai-specs\u002F\n│   ├── .agents\u002F                 # Canonical agent role definitions\n│   ├── .commands\u002F               # Small set of shared utility commands\n│   └── skills\u002F                  # Canonical skill definitions (main workflow entrypoint)\n│\n├── .codex\u002F\n│   ├── agents -> ..\u002Fai-specs\u002F.agents\n│   ├── commands -> ..\u002Fai-specs\u002F.commands\n│   └── skills -> ..\u002Fai-specs\u002Fskills\n│\n├── .cursor\u002F\n│   ├── agents -> ..\u002Fai-specs\u002F.agents\n│   ├── commands -> ..\u002Fai-specs\u002F.commands\n│   ├── skills -> ..\u002Fai-specs\u002Fskills\n│   └── rules\u002F\n│\n├── .claude\u002F\n│   ├── agents -> ..\u002Fai-specs\u002F.agents\n│   ├── commands -> ..\u002Fai-specs\u002F.commands\n│   └── skills -> ..\u002Fai-specs\u002Fskills\n│\n├── docs\u002F                        # Project technical context and reference docs\n└── README.md\n```\n\n## Multi-Copilot Strategy\n\nThis repository keeps a single canonical source in `ai-specs\u002F` and exposes it to each copilot folder using symlinks:\n\n- `.codex\u002F*` links to canonical resources\n- `.cursor\u002F*` links to canonical resources\n- `.claude\u002F*` links to canonical resources\n\n### Why This Approach\n\n- **Single source of truth**: one canonical definition for agents, commands, and skills\n- **No duplicated maintenance**: update once, all copilot folders stay aligned\n- **Tool compatibility**: each copilot reads from its expected folder structure\n- **Safe evolution**: workflows can change without reorganizing every tool-specific folder\n\n## Skills-First Workflow\n\nUse skills as the default entrypoint for recurring tasks.\n\nCurrent examples in this repository:\n\n- `ai-specs\u002Fskills\u002Fenrich-user-story\u002FSKILL.md`\n- `ai-specs\u002Fskills\u002Fwrite-pr-report\u002FSKILL.md`\n\nCommands still exist as lightweight utilities in `ai-specs\u002F.commands`, but the main functional workflows should be implemented as skills.\n\n## Technical Context Location\n\nProject-level technical context now belongs in `docs\u002F`, for example:\n\n- `docs\u002Fdoc_architecture.md`\n- `docs\u002Fdoc_ai_planning_mode.md`\n- `docs\u002Fdoc_verification_guide.md`\n\nIf you bootstrap this setup into another project, replace these documents with your own architecture, planning, and verification references.\n\n## Quick Start\n\n1. Copy this structure into your project.\n2. Keep `ai-specs\u002F` as canonical.\n3. Create symlinks from `.codex\u002F`, `.cursor\u002F`, and `.claude\u002F` to `ai-specs\u002F`.\n4. Store project context in `docs\u002F`.\n5. Build new reusable workflows as skills under `ai-specs\u002Fskills\u002F`.\n\n## Customization Guidelines\n\n- Update agent definitions in `ai-specs\u002F.agents\u002F`.\n- Add or refine skills in `ai-specs\u002Fskills\u002F`.\n- Keep commands minimal and only for utility behavior.\n- Keep symlinks relative so the repo stays portable.\n- Document project-specific technical context in `docs\u002F`.\n\n## Contributing\n\nWhen contributing:\n\n1. Prefer creating\u002Fupdating a skill over adding a new command.\n2. Keep canonical content inside `ai-specs\u002F`.\n3. Preserve symlink-based sharing across copilot folders.\n4. Keep `docs\u002F` aligned with the real project state.\n\n## Creator\n\nThis framework was created by **Javier Vargas**, Head of AI @ Mapal.\n\nHe is the original author of the approach, structure, and workflow design implemented in this repository.\n\nConnect with him on [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fjaviervargascaro\u002F).\n\n## License\n\nCopyright (c) 2026 LIDR.co  \nLicensed under the MIT License\n\nThis repository is part of the AI4Devs program by LIDR.co. Learn more at [LIDR.co](https:\u002F\u002Flidr.co\u002Fia-devs).\n\n","该项目是一个用于实施基于AI的规范驱动开发（SDD）全流程的手册和启动工具包，涵盖从产品需求分析到代码编写、验证及代码审查等环节。其核心功能包括提供一套可复用的技能优先架构，该架构定义了标准的角色、命令以及技能，并通过符号链接的方式确保Codex、Cursor和Claude等不同AI助手间的一致性与兼容性。项目特别推荐与OpenSpec等规范驱动流程结合使用。适用于希望将SDD理念转化为日常开发中可重复执行系统的企业或团队，尤其适合那些寻求提高软件开发效率并通过统一标准提升协作质量的场景。",2,"2026-06-11 02:47:47","CREATED_QUERY"]