ilaandClaude Fable 5
678d081124
- 06-tasks: add per-task detail sheets for Phase 0/1 (concrete init commands, BLOCKED preconditions, verification commands with expected results) and a constraint/verification quick table for Phase 2/3; replace subjective acceptance wording with checkable items - 04-architecture: promote 3.4 to an authoritative filter-param contract (names, values, AND combination, invalid-value handling); add required/optional/default field annex with 0-5 validators to 3.3; state AiCodingScore is not a model in MVP; record structure decision (keep wagtail-start home/search apps, business models in new core app, no Dockerfile) - 03-tech-stack: add version-pinning policy row for T-001 - routes/02-requirements: point filter wording back to the 3.4 contract instead of maintaining copies - T-104: human-input boundary - seed projects, scores and verdicts must be user-confirmed; BLOCKED without a confirmed list - current-state snapshot updated; maintenance record appended to progress.md Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Skelet
Skelet 是一个面向 AI coding 开发者、独立开发者和小团队的开源项目骨架导航与评测网站。
第一版目标是把"我应该基于哪个稳定骨架开始新项目"这个决策做清楚：按场景分类，按语言和框架筛选，提供骨架项目详情、AI Coding 友好度评分、适用/不适用场景和基础对比。第一版为英文单语言站点，主打"AI Coding 友好度"这一差异化角度（决策依据见 business/content-strategy.md）。
当前状态
当前仓库只完成 harness coding 文档初始化，尚未初始化生产代码。下一步任务见 docs/06-tasks.md：先初始化 Wagtail 项目骨架（T-001），再实现内容模型和 MVP 页面。
入口
AGENTS.md：所有 AI coding agent 的唯一权威入口——项目定位、必读顺序、工作规则、技术边界、开发环境和验证方式统一维护在这里。CLAUDE.md：Claude Code 薄入口，指向AGENTS.md。docs/README.md：全部产品与工程文档导航。business/：商业计划、内容策略、变现方案、竞品分析。
技术选型摘要、开发原则和开工方式不在本文重复维护，以 AGENTS.md 和 docs/ 为准。