Refine WebUI commands and data skills

src/skills/bundled/eval-repair/SKILL.md

@@ -1,8 +1,8 @@
 ---
-name: eval-error-data-generation
+name: eval-repair
 description: 分析评测错误，并为针对性训练集/评测集补充生成可 review 的数据计划。
 when_to_use: 当用户提供评测结果、模型判错样本或带标签错误 case，并希望补充训练/评测数据时使用。
-aliases: eval-error-generation, error-driven-data
+aliases: error-repair, eval-data
 allowed_tools: read_file, write_file, edit_file, grep_search, glob_search, ask_user_question
 ---
 

src/skills/bundled/online-mining/SKILL.md

@@ -1,8 +1,8 @@
 ---
-name: online-badcase-mining
+name: online-mining
 description: 分析 badcase，并通过可 review 的策略迭代挖掘线上相似 case。
 when_to_use: 当用户提供线上 badcase 或产品/标签定义，并希望查找相似线上问题或构建专项集时使用。
-aliases: badcase-mining, online-mining
+aliases: badcase-mining, router-mining
 allowed_tools: read_file, write_file, edit_file, grep_search, glob_search, ask_user_question, data_agent_profile_router_sessions, data_agent_search_router_sessions, data_agent_sample_router_candidates, data_agent_convert_router_candidates_to_records, data_agent_export_dataset_records
 ---
 

src/skills/bundled/product-data/SKILL.md

@@ -1,8 +1,8 @@
 ---
-name: product-definition-data-generation
+name: product-data
 description: 从产品/标签定义、手写边界规则或示例 query 中提取标签边界，并生成可 review 的数据计划、dataset draft text 和 canonical metadata records。
 when_to_use: 当用户提供产品定义、标签规则、路由边界文档、示例 query、手写标签边界，并希望生成训练/评测/专项数据时使用。
-aliases: definition-data-generation, label-definition-generation
+aliases: definition-data, label-data
 allowed_tools: read_file, write_file, edit_file, grep_search, glob_search, ask_user_question, data_agent_load_input_sources, data_agent_render_source_context, data_agent_extract_case_evidence, data_agent_prepare_generation_goal, data_agent_confirm_generation_goal, data_agent_prepare_generation_plan, data_agent_show_generation_plan, data_agent_update_generation_plan, data_agent_confirm_generation_plan, data_agent_normalize_dataset_draft, data_agent_validate_dataset_records, data_agent_export_dataset_records
 ---
 

src/skills/bundled/tool-smoke-test/SKILL.md

@@ -1,24 +0,0 @@
----
-name: tool-smoke-test
-description: Exercise a small existing-tool chain for skill/tool debugging.
-when_to_use: When the user wants to verify directory skills and tool-call tracing in the Web UI.
-aliases: smoke-tools
-allowed_tools: list_dir, write_file, read_file, grep_search
----
-
-Use this skill to verify that directory-based skills and basic tool chaining work.
-
-## Required Flow
-
-1. Briefly state that this is a tool smoke test.
-2. Call `list_dir` on `.` with a small `max_entries` value.
-3. Call `write_file` to create `tasks/task-001-smoke/artifacts/smoke.md` with a short markdown note that includes the exact phrase `tool-smoke-ok`.
-4. Call `read_file` on `tasks/task-001-smoke/artifacts/smoke.md`.
-5. Call `grep_search` for `tool-smoke-ok` under `tasks/task-001-smoke`.
-6. Summarize whether all tool calls succeeded and include the created file path.
-
-## Constraints
-
-- Do not use `bash`.
-- Do not edit unrelated files.
-- Keep the final response short.