菜单
Use when debugging bfzs application data, verifying session messages, checking agent presets, or inspecting tool call history. Triggers: user asks about sessions, messages, tool usage, or agent preset configuration in bfzs.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ydf0509/lc-agent --skill query-bfzs-db命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Give vision capability to non-vision LLMs (e.g. DeepSeek) by sending images to an external vision model (default agnes-2.5-flash, OpenAI-compatible) and returning text descriptions. 为无视觉能力的大模型（如 DeepSeek）提供识图能力：把图片发给外部视觉模型（默认 agnes-2.5-flash，OpenAI 兼容协议）并返回文字描述。Use this skill whenever the user shares a local image path or network image URL, a message contains "Saved attachments:", or the user asks to describe/recognize/analyze/interpret an image, extract text from an image (OCR), or understand screenshots, charts, tables, QR codes, or memes — do NOT use the Read tool to look at images (the underlying model has no vision). 当用户分享本地图片路径或网络图片 URL、消息中出现 "Saved attachments:"、用户要求描述/识别/分析/解读图片、提取图片中的文字（OCR）、理解截图/图表/表格/二维码/表情包，或任何需要"看图"的场景，都必须使用本 skill —— 不要用 Read 工具看图（底层模型无视觉能力）。The skill prompts for configuration once on first use when the vision API is not configured; afterwards it recognizes images automatically without asking again. skill 首次使用且视觉 API 未配置时，引导用户配置一次；配置后自动识图，不再询问。
Rebuild lc-agent frontend and restart the bfzs Python server. Use when the user asks to restart, rebuild, or redeploy the bfzs application, or after making significant code changes to the framework or frontend.
百度联网检索。search 按关键词搜索网页返回摘要/链接；extract 阅读指定网页提取正文。 用户要搜索、查资料时用 search；要读某篇文章、看某个链接内容时用 extract。
基于 SOC 职业分类
正在显示 SKILL.md
| name | query-bfzs-db |
| description | Use when debugging bfzs application data, verifying session messages, checking agent presets, or inspecting tool call history. Triggers: user asks about sessions, messages, tool usage, or agent preset configuration in bfzs. |
Query the bfzs SQLite databases directly to inspect sessions, messages, agent presets, and tool call history — without needing the server running.
preset_id was applied to a session| Command | Purpose |
|---|---|
--sessions [--limit N] [--search KEYWORD] | List recent sessions, with optional keyword search |
--presets | List agent presets (all fields: model, prompt, tools, mcp, skills) |
--users | List users and their agent access permissions |
--last | Use the most recent session (shortcut) |
--last --msgs | UI messages for most recent session (fast, has usage) |
--last --tools | Tool calls for most recent session |
--msgs <session-uuid> | UI messages from chat_ui_messages table (fast, shows usage/traces) |
<session-uuid> | Full messages from LangGraph checkpoint |
--tools <session-uuid> | Tool calls only, from LangGraph checkpoint |
--state | Runtime MCP servers and tool groups status (server must be running) |
$Python = "D:\ProgramData\miniconda3\envs\py312\python.exe"
$Script = "D:\codes\lc-agent\.agents\skills\query-bfzs-db\scripts\query_session.py"
# Most common: see last session's UI messages
& $Python $Script --last --msgs
# List recent sessions
& $Python $Script --sessions --limit 20
# Search sessions by title
& $Python $Script --sessions --search "funboost"
# List agent presets (all fields)
& $Python $Script --presets
# List users and permissions
& $Python $Script --users
# Full checkpoint messages for a specific session
& $Python $Script "session-uuid-here"
# Tool calls for a specific session
& $Python $Script --tools "session-uuid-here"
| DB | Path | Contents |
|---|---|---|
| Data | D:\codes\lc-agent-bfzs\bfzs_data.db | sessions, agent_presets, users |
| Checkpoint | D:\codes\lc-agent-bfzs\bfzs_checkpoints.db | LangGraph state with messages |