fix(skills): 去除追问/展示数量的软性倾向措辞，完全交 Agent 自主 (#59)

## 摘要 / Summary

### 中文

在去除机械数字上限（#58）后，进一步删掉技能里追问/展示数量的**软性倾向措辞**——create
的「一次不要问太多以免用户负担」、discover 的「避免一次刷屏过多」。数量与节奏完全交由执行 Agent
自主判断，不带任何倾向暗示。create 2.5.4 / discover 2.6.4，manifest 1.2.15，中英双份同步、重算
source_hash（validate-i18n 通过）。

### English

After removing the mechanical numeric caps (#58), further drop the soft
directional hints on ask/display count — create's "don't ask too many so
as not to burden the user" and discover's "avoid flooding the screen".
Count and pacing are left entirely to the executing Agent's judgment
with no bias. create 2.5.4 / discover 2.6.4, manifest 1.2.15, both
locales synced, hashes recomputed (validate-i18n passes).

skills/discover-agent/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [2.6.4] - 2026-07-19
+
+- 进一步去除追问/展示数量的软性倾向措辞（'别让用户负担'、'避免刷屏'），完全交由执行 Agent 自主判断，不带任何数量暗示。
+
 ## [2.6.3] - 2026-07-19
 
 - 去除束缚执行 Agent 自主判断的机械数字策略（create 追问'每轮最多 2 个'、discover'最多展示 5 个候选'），改为交由 Agent 按情况自主把握节奏与数量，保留'别让用户负担/别刷屏'的原则意图。

skills/discover-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: discover-agent
 description: 根据用户需求推荐最匹配的智能体，展示候选列表并引导选择。Use when 用户描述需求但不确定该找哪个智能体帮忙，或想浏览可用的智能体。
-version: 2.6.3
+version: 2.6.4
 type: procedural
 risk_level: low
 status: enabled
@@ -24,7 +24,7 @@ metadata:
       short_desc: 根据需求描述智能推荐最匹配的智能体，引导快速选择
       description: 根据用户需求推荐最匹配的智能体，展示候选列表并引导选择。Use when 用户描述需求但不确定该找哪个智能体帮忙，或想浏览可用的智能体。
       body: ./SKILL.zh-CN.md
-      source_hash: sha256:72159b331107dfb6
+      source_hash: sha256:bf81bef8caa89cc5
       translated_by: human
     en-US:
       name: Discover Agent
@@ -32,7 +32,7 @@ metadata:
       description: >-
         Recommend the best-matching Agent based on the user’s needs, show a candidate list, and guide selection. Use when the user describes a need but is unsure which Agent to ask for help, or wants to browse available Agents.
       body: ./SKILL.md
-      source_hash: sha256:72159b331107dfb6
+      source_hash: sha256:bf81bef8caa89cc5
       translated_by: ai:claude-fable-5
       translated_at: '2026-07-19'
 market:
@@ -84,7 +84,7 @@ Judge match with LLM semantic understanding (not a formula): relevance of descri
 
 ### Stage 4: Ranking
 
-Descending by overall score; ties broken by online status; show the most relevant few — you decide how many by relevance, avoiding flooding the screen.
+Descending by overall score; ties broken by online status; show the most relevant ones — you decide how many by relevance.
 
 ### Stage 5: Presentation
 

skills/discover-agent/SKILL.zh-CN.md

@@ -28,7 +28,7 @@
 
 ### 阶段 4：排序
 
-综合得分降序；同分 online 优先；展示最相关的若干个即可，数量由你按相关性自主把握，避免一次刷屏过多。
+综合得分降序；同分 online 优先；展示最相关的若干个，数量由你按相关性自主把握。
 
 ### 阶段 5：结果展示