@puyinkai/xiaobao-cli 0.1.0 → 0.1.8

package/skills/wangxiaobao-audio-wiki/references/llm-wiki-ingest.md

@@ -0,0 +1,450 @@
+---
+name: llm-wiki
+description: "Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency."
+version: 2.0.0
+author: Hermes Agent
+license: MIT
+metadata:
+  hermes:
+    tags: [wiki, knowledge-base, research, notes, markdown, rag-alternative]
+    category: research
+    related_skills: [obsidian, arxiv, agentic-research-ideas]
+---
+
+# Karpathy's LLM Wiki
+
+Build and maintain a persistent, compounding knowledge base as interlinked markdown files.
+Based on [Andrej Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).
+
+Unlike traditional RAG (which rediscovers knowledge from scratch per query), the wiki
+compiles knowledge once and keeps it current. Cross-references are already there.
+Contradictions have already been flagged. Synthesis reflects everything ingested.
+
+**Division of labor:** The human curates sources and directs analysis. The agent
+summarizes, cross-references, files, and maintains consistency.
+
+## When This Skill Activates
+
+Use this skill when the user:
+- Asks to create, build, or start a wiki or knowledge base
+- Asks to ingest, add, or process a source into their wiki
+- Asks a question and an existing wiki is present at the configured path
+- Asks to lint, audit, or health-check their wiki
+- References their wiki, knowledge base, or "notes" in a research context
+
+## Wiki Location
+
+**Location:** Set via `WIKI_PATH` environment variable (e.g. in `~/.hermes/.env`).
+
+If unset, defaults to `~/wiki`.
+
+```bash
+WIKI="${WIKI_PATH:-$HOME/wiki}"
+```
+
+The wiki is just a directory of markdown files — open it in Obsidian, VS Code, or
+any editor. No database, no special tooling required.
+
+## Architecture: Three Layers
+
+```
+wiki/
+├── SCHEMA.md           # Conventions, structure rules, domain config
+├── index.md            # Sectioned content catalog with one-line summaries
+├── log.md              # Chronological action log (append-only, rotated yearly)
+├── raw/                # Layer 1: Immutable source material
+│   ├── articles/       # Web articles, clippings
+│   ├── papers/         # PDFs, arxiv papers
+│   ├── transcripts/    # Meeting notes, interviews
+│   └── assets/         # Images, diagrams referenced by sources
+├── entities/           # Layer 2: Entity pages (people, orgs, products, models)
+├── concepts/           # Layer 2: Concept/topic pages
+├── comparisons/        # Layer 2: Side-by-side analyses
+└── queries/            # Layer 2: Filed query results worth keeping
+```
+
+**Layer 1 — Raw Sources:** Immutable. The agent reads but never modifies these.
+**Layer 2 — The Wiki:** Agent-owned markdown files. Created, updated, and
+cross-referenced by the agent.
+**Layer 3 — The Schema:** `SCHEMA.md` defines structure, conventions, and tag taxonomy.
+
+## Resuming an Existing Wiki (CRITICAL — do this every session)
+
+When the user has an existing wiki, **always orient yourself before doing anything**:
+
+① **Read `SCHEMA.md`** — understand the domain, conventions, and tag taxonomy.
+② **Read `index.md`** — learn what pages exist and their summaries.
+③ **Scan recent `log.md`** — read the last 20-30 entries to understand recent activity.
+
+```bash
+WIKI="${WIKI_PATH:-$HOME/wiki}"
+# Orientation reads at session start
+read_file "$WIKI/SCHEMA.md"
+read_file "$WIKI/index.md"
+read_file "$WIKI/log.md" offset=<last 30 lines>
+```
+
+Only after orientation should you ingest, query, or lint. This prevents:
+- Creating duplicate pages for entities that already exist
+- Missing cross-references to existing content
+- Contradicting the schema's conventions
+- Repeating work already logged
+
+For large wikis (100+ pages), also run a quick `search_files` for the topic
+at hand before creating anything new.
+
+## Initializing a New Wiki
+
+When the user asks to create or start a wiki:
+
+1. Determine the wiki path (from `$WIKI_PATH` env var, or ask the user; default `~/wiki`)
+2. Create the directory structure above
+3. Ask the user what domain the wiki covers — be specific
+4. Write `SCHEMA.md` customized to the domain (see template below)
+5. Write initial `index.md` with sectioned header
+6. Write initial `log.md` with creation entry
+7. Confirm the wiki is ready and suggest first sources to ingest
+
+### SCHEMA.md Template
+
+Adapt to the user's domain. The schema constrains agent behavior and ensures consistency:
+
+```markdown
+# Wiki Schema
+
+## Domain
+[What this wiki covers — e.g., "AI/ML research", "personal health", "startup intelligence"]
+
+## Conventions
+- File names: lowercase, hyphens, no spaces (e.g., `transformer-architecture.md`)
+- Every wiki page starts with YAML frontmatter (see below)
+- Use `[[wikilinks]]` to link between pages (minimum 2 outbound links per page)
+- When updating a page, always bump the `updated` date
+- Every new page must be added to `index.md` under the correct section
+- Every action must be appended to `log.md`
+
+## Frontmatter
+  ```yaml
+  ---
+  title: Page Title
+  created: YYYY-MM-DD
+  updated: YYYY-MM-DD
+  type: entity | concept | comparison | query | summary
+  tags: [from taxonomy below]
+  sources: [raw/articles/source-name.md]
+  ---
+  ```
+
+## Tag Taxonomy
+[Define 10-20 top-level tags for the domain. Add new tags here BEFORE using them.]
+
+Example for AI/ML:
+- Models: model, architecture, benchmark, training
+- People/Orgs: person, company, lab, open-source
+- Techniques: optimization, fine-tuning, inference, alignment, data
+- Meta: comparison, timeline, controversy, prediction
+
+Rule: every tag on a page must appear in this taxonomy. If a new tag is needed,
+add it here first, then use it. This prevents tag sprawl.
+
+## Page Thresholds
+- **Create a page** when an entity/concept appears in 2+ sources OR is central to one source
+- **Add to existing page** when a source mentions something already covered
+- **DON'T create a page** for passing mentions, minor details, or things outside the domain
+- **Split a page** when it exceeds ~200 lines — break into sub-topics with cross-links
+- **Archive a page** when its content is fully superseded — move to `_archive/`, remove from index
+
+## Entity Pages
+One page per notable entity. Include:
+- Overview / what it is
+- Key facts and dates
+- Relationships to other entities ([[wikilinks]])
+- Source references
+
+## Concept Pages
+One page per concept or topic. Include:
+- Definition / explanation
+- Current state of knowledge
+- Open questions or debates
+- Related concepts ([[wikilinks]])
+
+## Comparison Pages
+Side-by-side analyses. Include:
+- What is being compared and why
+- Dimensions of comparison (table format preferred)
+- Verdict or synthesis
+- Sources
+
+## Update Policy
+When new information conflicts with existing content:
+1. Check the dates — newer sources generally supersede older ones
+2. If genuinely contradictory, note both positions with dates and sources
+3. Mark the contradiction in frontmatter: `contradictions: [page-name]`
+4. Flag for user review in the lint report
+```
+
+### index.md Template
+
+The index is sectioned by type. Each entry is one line: wikilink + summary.
+
+```markdown
+# Wiki Index
+
+> Content catalog. Every wiki page listed under its type with a one-line summary.
+> Read this first to find relevant pages for any query.
+> Last updated: YYYY-MM-DD | Total pages: N
+
+## Entities
+<!-- Alphabetical within section -->
+
+## Concepts
+
+## Comparisons
+
+## Queries
+```
+
+**Scaling rule:** When any section exceeds 50 entries, split it into sub-sections
+by first letter or sub-domain. When the index exceeds 200 entries total, create
+a `_meta/topic-map.md` that groups pages by theme for faster navigation.
+
+### log.md Template
+
+```markdown
+# Wiki Log
+
+> Chronological record of all wiki actions. Append-only.
+> Format: `## [YYYY-MM-DD] action | subject`
+> Actions: ingest, update, query, lint, create, archive, delete
+> When this file exceeds 500 entries, rotate: rename to log-YYYY.md, start fresh.
+
+## [YYYY-MM-DD] create | Wiki initialized
+- Domain: [domain]
+- Structure created with SCHEMA.md, index.md, log.md
+```
+
+## Core Operations
+
+### 1. Ingest
+
+When the user provides a source (URL, file, paste), integrate it into the wiki:
+
+① **Capture the raw source:**
+   - URL → use `web_extract` to get markdown, save to `raw/articles/`
+   - PDF → use `web_extract` (handles PDFs), save to `raw/papers/`
+   - Pasted text → save to appropriate `raw/` subdirectory
+   - Name the file descriptively: `raw/articles/karpathy-llm-wiki-2026.md`
+
+② **Discuss takeaways** with the user — what's interesting, what matters for
+   the domain. (Skip this in automated/cron contexts — proceed directly.)
+
+③ **Check what already exists** — search index.md and use `search_files` to find
+   existing pages for mentioned entities/concepts. This is the difference between
+   a growing wiki and a pile of duplicates.
+
+④ **Write or update wiki pages:**
+   - **New entities/concepts:** Create pages only if they meet the Page Thresholds
+     in SCHEMA.md (2+ source mentions, or central to one source)
+   - **Existing pages:** Add new information, update facts, bump `updated` date.
+     When new info contradicts existing content, follow the Update Policy.
+   - **Cross-reference:** Every new or updated page must link to at least 2 other
+     pages via `[[wikilinks]]`. Check that existing pages link back.
+   - **Tags:** Only use tags from the taxonomy in SCHEMA.md
+
+⑤ **Update navigation:**
+   - Add new pages to `index.md` under the correct section, alphabetically
+   - Update the "Total pages" count and "Last updated" date in index header
+   - Append to `log.md`: `## [YYYY-MM-DD] ingest | Source Title`
+   - List every file created or updated in the log entry
+
+⑥ **Report what changed** — list every file created or updated to the user.
+
+A single source can trigger updates across 5-15 wiki pages. This is normal
+and desired — it's the compounding effect.
+
+### 2. Query
+
+When the user asks a question about the wiki's domain:
+
+① **Read `index.md`** to identify relevant pages.
+② **For wikis with 100+ pages**, also `search_files` across all `.md` files
+   for key terms — the index alone may miss relevant content.
+③ **Read the relevant pages** using `read_file`.
+④ **Synthesize an answer** from the compiled knowledge. Cite the wiki pages
+   you drew from: "Based on [[page-a]] and [[page-b]]..."
+⑤ **File valuable answers back** — if the answer is a substantial comparison,
+   deep dive, or novel synthesis, create a page in `queries/` or `comparisons/`.
+   Don't file trivial lookups — only answers that would be painful to re-derive.
+⑥ **Update log.md** with the query and whether it was filed.
+
+### 3. Lint
+
+When the user asks to lint, health-check, or audit the wiki:
+
+① **Orphan pages:** Find pages with no inbound `[[wikilinks]]` from other pages.
+```python
+# Use execute_code for this — programmatic scan across all wiki pages
+import os, re
+from collections import defaultdict
+wiki = "<WIKI_PATH>"
+# Scan all .md files in entities/, concepts/, comparisons/, queries/
+# Extract all [[wikilinks]] — build inbound link map
+# Pages with zero inbound links are orphans
+```
+
+② **Broken wikilinks:** Find `[[links]]` that point to pages that don't exist.
+
+③ **Index completeness:** Every wiki page should appear in `index.md`. Compare
+   the filesystem against index entries.
+
+④ **Frontmatter validation:** Every wiki page must have all required fields
+   (title, created, updated, type, tags, sources). Tags must be in the taxonomy.
+
+⑤ **Stale content:** Pages whose `updated` date is >90 days older than the most
+   recent source that mentions the same entities.
+
+⑥ **Contradictions:** Pages on the same topic with conflicting claims. Look for
+   pages that share tags/entities but state different facts.
+
+⑦ **Page size:** Flag pages over 200 lines — candidates for splitting.
+
+⑧ **Tag audit:** List all tags in use, flag any not in the SCHEMA.md taxonomy.
+
+⑨ **Log rotation:** If log.md exceeds 500 entries, rotate it.
+
+⑩ **Report findings** with specific file paths and suggested actions, grouped by
+   severity (broken links > orphans > stale content > style issues).
+
+⑪ **Append to log.md:** `## [YYYY-MM-DD] lint | N issues found`
+
+## Working with the Wiki
+
+### Searching
+
+```bash
+# Find pages by content
+search_files "transformer" path="$WIKI" file_glob="*.md"
+
+# Find pages by filename
+search_files "*.md" target="files" path="$WIKI"
+
+# Find pages by tag
+search_files "tags:.*alignment" path="$WIKI" file_glob="*.md"
+
+# Recent activity
+read_file "$WIKI/log.md" offset=<last 20 lines>
+```
+
+### Bulk Ingest
+
+When ingesting multiple sources at once, batch the updates:
+1. Read all sources first
+2. Identify all entities and concepts across all sources
+3. Check existing pages for all of them (one search pass, not N)
+4. Create/update pages in one pass (avoids redundant updates)
+5. Update index.md once at the end
+6. Write a single log entry covering the batch
+
+### Archiving
+
+When content is fully superseded or the domain scope changes:
+1. Create `_archive/` directory if it doesn't exist
+2. Move the page to `_archive/` with its original path (e.g., `_archive/entities/old-page.md`)
+3. Remove from `index.md`
+4. Update any pages that linked to it — replace wikilink with plain text + "(archived)"
+5. Log the archive action
+
+### Obsidian Integration
+
+The wiki directory works as an Obsidian vault out of the box:
+- `[[wikilinks]]` render as clickable links
+- Graph View visualizes the knowledge network
+- YAML frontmatter powers Dataview queries
+- The `raw/assets/` folder holds images referenced via `![[image.png]]`
+
+For best results:
+- Set Obsidian's attachment folder to `raw/assets/`
+- Enable "Wikilinks" in Obsidian settings (usually on by default)
+- Install Dataview CLI for queries like `TABLE tags FROM "entities" WHERE contains(tags, "company")`
+
+If using the Obsidian skill alongside this one, set `OBSIDIAN_VAULT_PATH` to the
+same directory as the wiki path.
+
+### Obsidian Headless (servers and headless machines)
+
+On machines without a display, use `obsidian-headless` instead of the desktop app.
+It syncs vaults via Obsidian Sync without a GUI — perfect for agents running on
+servers that write to the wiki while Obsidian desktop reads it on another device.
+
+**Setup:**
+```bash
+# Requires Node.js 22+
+npm install -g obsidian-headless
+
+# Login (requires Obsidian account with Sync subscription)
+ob login --email <email> --password '<password>'
+
+# Create a remote vault for the wiki
+ob sync-create-remote --name "LLM Wiki"
+
+# Connect the wiki directory to the vault
+cd ~/wiki
+ob sync-setup --vault "<vault-id>"
+
+# Initial sync
+ob sync
+
+# Continuous sync (foreground — use systemd for background)
+ob sync --continuous
+```
+
+**Continuous background sync via systemd:**
+```ini
+# ~/.config/systemd/user/obsidian-wiki-sync.service
+[Unit]
+Description=Obsidian LLM Wiki Sync
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+ExecStart=/path/to/ob sync --continuous
+WorkingDirectory=/home/user/wiki
+Restart=on-failure
+RestartSec=10
+
+[Install]
+WantedBy=default.target
+```
+
+```bash
+systemctl --user daemon-reload
+systemctl --user enable --now obsidian-wiki-sync
+# Enable linger so sync survives logout:
+sudo loginctl enable-linger $USER
+```
+
+This lets the agent write to `~/wiki` on a server while you browse the same
+vault in Obsidian on your laptop/phone — changes appear within seconds.
+
+## Pitfalls
+
+- **Never modify files in `raw/`** — sources are immutable. Corrections go in wiki pages.
+- **Always orient first** — read SCHEMA + index + recent log before any operation in a new session.
+  Skipping this causes duplicates and missed cross-references.
+- **Always update index.md and log.md** — skipping this makes the wiki degrade. These are the
+  navigational backbone.
+- **Don't create pages for passing mentions** — follow the Page Thresholds in SCHEMA.md. A name
+  appearing once in a footnote doesn't warrant an entity page.
+- **Don't create pages without cross-references** — isolated pages are invisible. Every page must
+  link to at least 2 other pages.
+- **Frontmatter is required** — it enables search, filtering, and staleness detection.
+- **Tags must come from the taxonomy** — freeform tags decay into noise. Add new tags to SCHEMA.md
+  first, then use them.
+- **Keep pages scannable** — a wiki page should be readable in 30 seconds. Split pages over
+  200 lines. Move detailed analysis to dedicated deep-dive pages.
+- **Ask before mass-updating** — if an ingest would touch 10+ existing pages, confirm
+  the scope with the user first.
+- **Rotate the log** — when log.md exceeds 500 entries, rename it `log-YYYY.md` and start fresh.
+  The agent should check log size during lint.
+- **Handle contradictions explicitly** — don't silently overwrite. Note both claims with dates,
+  mark in frontmatter, flag for user review.

package/skills/wangxiaobao-customer-focus-query/SKILL.md

@@ -1,86 +1,42 @@
 ---
 name: wangxiaobao-customer-focus-query
-description: |
-  旺小宝**客户关注点**分页查询 skill：按 visit/customer/audio ID 列表、一级/二级
-  分类模糊、来访时间窗组合查 AI 在客户对话里抽出的「关注点」标签
-  （客户主动表达的关心：学区 / 户型 / 价格优惠 / 配套等）。**只读、不写文件、
-  无副作用**。对应 `xiaobao_list_customer_focus` tool。排序固定 visit_time DESC。
-  每条 tag 含 customer / userInfo / audio + value_str（详细说明） + text_fragment（录音原文片段）。
-
-  **当以下情况时使用此 Skill**:
-  (1) 用户问"客户关注点"、"客户最在意什么"、"客户关心什么"、"客户问得最多"
-  (2) 用户问某客户的关注点 —— 先调 `xiaobao_list_customers` 反查 customerId，
-      再调本 skill 带 customerIds 精确过滤
-  (3) 用户问某次到访 / 某条录音里的关注点 —— 带 visitIds / audioIds
-  (4) 用户按分类找 —— 户型 / 价格 / 学区 / 交通 / 商业配套 等 → category 模糊
-  (5) 用户按二级分类找 —— "户型因素" / "位置因素" / "发展因素" → classification 模糊
-  (6) 用户给时间窗 —— "5 月份的关注点" / "本周关注点" → fromDate / toDate
-
-  **不要用本 skill 的场景**：
-  - 用户问的是**抗性点 / 疑虑 / 反对意见** → 走 `wangxiaobao-customer-resistance-query`
-  - 用户要的是客户**画像** / 标签 → 走 `wangxiaobao-customer-query`
-  - 用户问"完整录音文本" → 走 `wangxiaobao-audio-query` + `xiaobao_get_audio_text`
+version: 0.1.0
+description: "旺小宝客户关注点（focus）分页查询 —— AI 在客户对话里抽出的客户主动表达的关心标签（学区 / 户型 / 价格优惠 / 配套等）。按 visit/customer/audio ID 列表（IN） + 一级分类（category LIKE） + 二级分类（classification LIKE） + 来访时间窗组合过滤，排序固定 visit_time DESC。每条 tag 已带 customer + userInfo + audio + value_str（详细说明） + text_fragment（录音原文片段）。只读、不写文件。高频命令: xiaobao-cli focus list [--visit-ids a,b] [--customer-ids a,b] [--audio-ids a,b] [--category <kw>] [--classification <kw>] [--from <date>] [--to <date>] [--page N] [--size N]。何时用：用户问客户关注点/客户最在意什么/客户关心什么/客户问得最多/某客户的关注点/某次到访或某条录音里的关注点/户型 价格 学区 交通 商业配套类关注点/5 月份的关注点。注：客户名→wang_id 先用 xiaobao-cli customer list 反查；问抗性/疑虑/反对走 resistance-query；问完整录音文本走 audio-query。"
+metadata:
+  requires:
+    bins: ["xiaobao-cli"]
+  cliHelp: "xiaobao-cli focus --help"
 ---
 
-> **Host-agnostic CLI skill** — 本 skill 假设 `xiaobao-cli` 已装到 PATH
-> (`npm i -g @puyinkai/xiaobao-cli` 或 `npx -y @puyinkai/xiaobao-cli`)。
-> Agent 通过 shell 工具（Bash / Run / Shell）执行命令、读 **stdout JSON** 消费；
-> stderr 是进度/错误提示。退出码 0 = 成功，非 0 = 业务/网络错（错误对象同时打到 stdout 可解析）。
->
-> CLI 14 个子命令跟 openclaw-xiaobao plugin 14 个 tool **1:1 等价**，返回 JSON
-> 结构完全一致（`{status, ok, data: {...}}`）。skill 里看到的 `resp.data.data.xxx`
-> 取数路径直接对 stdout JSON 用 `jq` / `JSON.parse` 即可。
->
-> **plugin tool → CLI 命令翻译表（数组参数走逗号分隔）**：
->
-> | plugin tool | CLI 命令 |
-> | --- | --- |
-> | `xiaobao_authorize { force? }` | `xiaobao-cli auth login [--force]` |
-> | `xiaobao_whoami` | `xiaobao-cli auth whoami` |
-> | `xiaobao_logout` | `xiaobao-cli auth logout` |
-> | `xiaobao_list_projects { keyword? }` | `xiaobao-cli project list [--keyword <kw>]` |
-> | `xiaobao_switch_project { tenantId, tenantName, projectId, projectName }` | `xiaobao-cli project use --tenant-id ... --tenant-name ... --project-id ... --project-name ...` |
-> | `xiaobao_list_consultants` | `xiaobao-cli consultant list` |
-> | `xiaobao_list_audio { fromDate, toDate, userId?, userIdList?, page, size }` | `xiaobao-cli audio list --from "..." --to "..." [--user-id ...] [--user-id-list a,b,c] [--page N] [--size N]` |
-> | `xiaobao_get_audio_text { audioId }` | `xiaobao-cli audio text <audioId>` |
-> | `xiaobao_list_customers { ... }` | `xiaobao-cli customer list [--user-id] [--user-name] [--customer-name] [--customer-phone] [--portrait] [--from] [--to] [--page] [--size]` |
-> | `xiaobao_list_visits { ... }` | `xiaobao-cli visit list [--customer-id] [--customer-name] [--from] [--to] [--page] [--size]` |
-> | `xiaobao_list_customer_focus { visitIds, customerIds, audioIds, category, classification, fromDate, toDate, ... }` | `xiaobao-cli focus list [--visit-ids a,b] [--customer-ids a,b] [--audio-ids a,b] [--category ...] [--classification ...] [--from ...] [--to ...]` |
-> | `xiaobao_list_customer_resistance { ... }` | `xiaobao-cli resistance list [同 focus]` |
-> | `xiaobao_quick_qa { prompt, threadId? }` | `xiaobao-cli qa "<prompt>" [--thread-id ...]` |
-> | `xiaobao_api { method, path, query, body, headers }` | `xiaobao-cli api <METHOD> <PATH> [--query k=v] [--body '<json>'] [--headers k=v]` |
->
-> 用 `--format toon` 切到 TOON（uniform 数组省 30-50% token，LLM 上下文优化）；
-> 用 `--format json`（默认）保持 JSON。state 路径：`~/.xiaobao/`（fallback 读 `~/.openclaw/state/wangxiaobao/`）。
-
-
 # 旺小宝客户关注点查询
 
-调 `xiaobao_list_customer_focus` tool 查 AI 抽出的客户关注点标签。
+> **CRITICAL** —— 跑命令前 MUST 先用 Read tool 读取 [`../wangxiaobao-shared/SKILL.md`](../wangxiaobao-shared/SKILL.md)（一份共享文档讲清安装 / 登录 / 选项目 / 错误码 / 输出协议等所有 xiaobao-cli 命令通用的前置约定）。
+
+跑 `xiaobao-cli focus list` 查 AI 抽出的客户关注点标签。
 跟抗性点 skill 镜像，差别就是底层走 `mv_open_customer_focus` 表。
 
 ## 执行前必读
 
-- 必须有有效 token：先调 `xiaobao_whoami`；未登录就 `xiaobao_authorize`
-- **必须有激活项目**：tool 内部自动读，缺失返回 `NO_ACTIVE_PROJECT`
+- 必须有有效 token：先调 `xiaobao-cli auth whoami`；未登录就 `xiaobao-cli auth login`
+- **必须有激活项目**：命令内部自动读，缺失返回 `NO_ACTIVE_PROJECT`
 - **数据权限隔离**：按当前用户授权可见顾问范围过滤（普通顾问看自己 /
   团队长看团队 / 项目管理员看全项目）
-- LocalDateTime 格式：`yyyy-MM-dd HH:mm:ss`（空格分隔），plugin 自动转
+- LocalDateTime 格式：`yyyy-MM-dd HH:mm:ss`（空格分隔），CLI 自动转
 - **不要**写文件、出报告
 
 ---
 
 ## 快速索引：意图 → 工具
 
-| 用户意图                             | plugin tool                       | 关键参数                           |
+| 用户意图                             | 命令                       | 关键参数                           |
 | ------------------------------------ | --------------------------------- | ---------------------------------- |
-| 列时段内全部关注点                   | `xiaobao_list_customer_focus`     | `fromDate` / `toDate`              |
-| 看某客户的关注点                     | `xiaobao_list_customers` → `xiaobao_list_customer_focus` | `customerIds: [<wang_id>]` |
-| 看某次到访的关注点                   | `xiaobao_list_customer_focus`     | `visitIds: [<visit_id>]`           |
-| 看某条录音的关注点                   | `xiaobao_list_customer_focus`     | `audioIds: [<audio_id>]`           |
-| 按分类找（一级）                     | `xiaobao_list_customer_focus`     | `category: "户型"` 等              |
-| 按分类找（二级）                     | `xiaobao_list_customer_focus`     | `classification: "户型因素"`        |
-| 估算总数                             | `xiaobao_list_customer_focus`     | `page: 1, size: 1`，只读 `total`   |
+| 列时段内全部关注点                   | `xiaobao-cli focus list`     | `--from` / `--to`              |
+| 看某客户的关注点                     | `xiaobao-cli customer list` → `xiaobao-cli focus list` | `--customer-ids <wang_id>` |
+| 看某次到访的关注点                   | `xiaobao-cli focus list`     | `--visit-ids <visit_id>`           |
+| 看某条录音的关注点                   | `xiaobao-cli focus list`     | `--audio-ids <audio_id>`           |
+| 按分类找（一级）                     | `xiaobao-cli focus list`     | `--category 户型` 等              |
+| 按分类找（二级）                     | `xiaobao-cli focus list`     | `--classification 户型因素`        |
+| 估算总数                             | `xiaobao-cli focus list`     | `--page 1 --size 1`，只读 `total`   |
 
 ---
 
@@ -88,8 +44,8 @@ description: |
 
 ### 1. 客户名 → wang_id 反查
 
-用户说"屈哥的关注点"——先调 `xiaobao_list_customers { customerName: "屈哥" }`
-拿到 `customerId`（= wang_id），再传给 `customerIds` 数组（即使只有一个也用数组）。
+用户说"屈哥的关注点"——先调 `xiaobao-cli customer list { customerName: "屈哥" }`
+拿到 `--customer-id`（= wang_id），再传给 `--customer-ids` 数组（即使只有一个也用数组）。
 
 ### 2. 分类模糊：一级 + 二级二选一或同时用
 
@@ -98,7 +54,7 @@ category 一级常见值：户型 / 价格 / 环境 / 教育 / 交通 / 商业
 classification 二级常见值：户型因素 / 价格因素 / 环境因素 / ... / 位置因素 / 发展因素
 ```
 
-模糊关键词越短越宽：`category: "户型"` 同时命中 "户型因素" 和别的含 "户型" 的分类。
+模糊关键词越短越宽：`--category 户型` 同时命中 "户型因素" 和别的含 "户型" 的分类。
 
 ### 3. 时间窗：用户没明确说就推断
 
@@ -151,7 +107,7 @@ classification 二级常见值：户型因素 / 价格因素 / 环境因素 / ..
 }
 ```
 
-plugin tool 又外包一层 → 渲染用 `resp.data.data.content`。
+CLI 又包一层 → 渲染用 `resp.data.data.content`。
 
 ### 5. 渲染给用户时只展示核心
 
@@ -165,38 +121,32 @@ plugin tool 又外包一层 → 渲染用 `resp.data.data.content`。
 
 ### 场景 1：本月客户最在意什么
 
-```jsonc
-{
-  "fromDate": "2026-05-01 00:00:00",
-  "toDate":   "2026-06-01 00:00:00",
-  "page": 1, "size": 50
-}
+```bash
+xiaobao-cli focus list --from "2026-05-01 00:00:00" --to "2026-06-01 00:00:00" --page 1 --size 50
 ```
 
-后处理：按 `category` 聚合 → "5 月份 87 条关注点：户型因素 28 条 / 价格因素 19 条 / ..."。
+后处理：按 `--category` 聚合 → "5 月份 87 条关注点：户型因素 28 条 / 价格因素 19 条 / ..."。
 
 ### 场景 2：屈哥本次到访的关注点
 
-```jsonc
-// step 1: 反查 wang_id（如果只知名字）
-// xiaobao_list_customers
-{ "customerName": "屈哥" }
+```bash
+# step 1: 反查 wang_id（如果只知名字）
+xiaobao-cli customer list --customer-name 屈哥
 
-// step 2: 拿到 customerId = 507016570019512320
-// xiaobao_list_customer_focus
-{ "customerIds": ["507016570019512320"], "page": 1, "size": 20 }
+# step 2: 拿到 customerId = 507016570019512320，用 --customer-ids 过滤
+xiaobao-cli focus list --customer-ids 507016570019512320 --page 1 --size 20
 ```
 
 ### 场景 3：户型相关关注点
 
-```jsonc
-{ "category": "户型", "page": 1, "size": 30 }
+```bash
+xiaobao-cli focus list --category 户型 --page 1 --size 30
 ```
 
 ### 场景 4：特定录音里的关注点
 
-```jsonc
-{ "audioIds": ["507494047338729472"], "page": 1, "size": 50 }
+```bash
+xiaobao-cli focus list --audio-ids 507494047338729472 --page 1 --size 50
 ```
 
 渲染：列出该录音里 AI 抽出的所有关注点，按 startOffset 升序展示原文 + 描述。
@@ -206,7 +156,7 @@ plugin tool 又外包一层 → 渲染用 `resp.data.data.content`。
 ## 常见错误与排查
 
 - **`error: 'NO_ACTIVE_PROJECT'`** — 跑 `wangxiaobao-switch-project` skill
-- **401 / token 过期** — 调 `xiaobao_authorize { force: true }` 重登
+- **401 / token 过期** — 调 `xiaobao-cli auth login --force` 重登
 - **`total: 0`** — 过滤条件没匹配 / 该时段没数据 / 当前用户授权范围内没匹配的接待顾问
 - **传入的 ID 找不到对应数据** — 数据权限隔离把不属于授权顾问的 tag 过滤掉了；
   这是预期行为，不是 bug