## 摘要 / Summary
### 中文
去除技能里束缚执行 Agent 自主判断的**机械数字策略**：create 需求收集的「每轮最多问 2 个」、discover
排序的「最多展示 5 个候选」。改为交由 Agent 按情况自主把握追问节奏与展示数量，保留「别让用户负担 /
别一次刷屏」的原则意图——把控制权交还给判断力更强的执行者，而非用固定上限约束。create 2.5.3 / discover
2.6.3，manifest 1.2.14，中英双份同步、重算 source_hash（validate-i18n 通过）。
### English
Remove mechanical numeric limits that constrain the executing Agent's
judgment: create's "at most 2 questions per turn" and discover's "show
at most 5 candidates". Both become "the Agent decides the pacing/count
by situation", keeping the principle intent (don't burden the user /
don't flood the screen) while handing control back to the more capable
executor instead of a fixed cap. create 2.5.3 / discover 2.6.3, manifest
1.2.14, both locales synced, hashes recomputed (validate-i18n passes).
## 摘要 / Summary
### 中文
#56 的复盘修正。上一轮"强改写压缩"把四技能 L1
的**技术属性、使用场景与交互示范当套话一刀切**，造成实质信息丢失（承诺"意图全保留"但未做到）。本 PR 补回：
- **create**：`创建仓库符合 AgentFS v2 规范、git
管理版本（可治理/可追溯）`定位；`基础创建`形态（name+description，description 自动填充 persona
L0）；需求收集的**引导问题示例**（"起什么名字？/主要负责什么？"…）；企业部署/开发者原型使用场景。
- **update**：`agent 目录 git 管理版本、历史可追溯`定位 + 使用场景。
- **discover**：使用场景（浏览/新用户/找替代）+ `语义匹配而非关键词搜索`。
- **delete**：使用场景（清理/测试/释放存储）。
根因：L1 混着实质技术属性与营销套话、使用场景是触发判据、引导问题是交互示范，不该按"只留独有信息"一刀切。补回后仍保留结构性压缩（zh
正文合计仍降 ~64%）。版本 create 2.5.2 / update 3.1.3 / delete 2.5.2 / discover
2.6.2，manifest 1.2.13，中英双份同步、重算 source_hash（validate-i18n 通过）。
### English
Post-mortem fix for #56. The previous aggressive compression treated the
skills' L1 technical attributes, use cases, and interaction demos as
boilerplate and cut them in a blanket way, dropping substantive
information (the "all intent preserved" claim wasn't fully met). This PR
restores: create's AgentFS-v2 / git-version-management positioning, the
"basic create" form (name+description auto-filling persona L0), the
requirement-gathering prompt questions, and enterprise/developer use
cases; update's git-versioned/traceable positioning and use cases;
discover's use cases and "semantic match, not keyword search"; delete's
use cases. Root cause: L1 mixed real technical attributes with marketing
boilerplate, use cases are trigger cues, and prompt questions are
interaction demos — none should have been blanket-cut. Structural
compression is retained (zh bodies still ~64% smaller). Versions bumped,
manifest 1.2.13, both locales synced, source hashes recomputed
(validate-i18n passes).
