xlb-topic-index

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Topic Index Command

主题索引命令

Overview

概述

Resolve
xlb
query phrases into a
title
command for the local API, then return Markdown index content.
xlb
查询语句转换为本地API的
title
命令,然后返回Markdown索引内容。

When to Use

使用场景

  • User input contains
    xlb
    as a query trigger.
  • User gives
    >.../
    command directly and expects passthrough.
  • User asks for topic index/navigation instead of narrative explanation.
  • User wants direct Markdown output from the knowledge source.
  • 用户输入包含
    xlb
    作为查询触发词。
  • 用户直接给出
    >.../
    命令并期望直接传递。
  • 用户询问主题索引/导航而非叙述性解释。
  • 用户希望从知识源直接获取Markdown输出。

Interaction Rule

交互规则

  • If input matches any trigger pattern below, execute directly without extra questions.
  • If input mentions
    xlb
    but no topic can be extracted, ask:
    • 请发送你要查询的指令,例如:xlb >Vibe Coding/AI超元域 或 xlb ??Vibe Coding
  • 如果输入匹配以下任何触发模式,直接执行,无需额外提问。
  • 如果输入提到
    xlb
    但无法提取主题,询问:
    • 请发送你要查询的指令,例如:xlb >Vibe Coding/AI超元域 或 xlb ??Vibe Coding

Trigger Mapping

触发映射

  • xlb >vibe coding/vib
    ->
    title=>vibe coding/vib
    (strip
    xlb 
    , payload passthrough)
  • xlb ??vibe coding
    ->
    title=??vibe coding
    (strip
    xlb 
    , payload passthrough)
  • xlb ->vibe coding/:
    ->
    title=->vibe coding/:
    (strip
    xlb 
    , payload passthrough to API)
  • xlb >vibe coding/searchin:
    ->
    title=>vibe coding/searchin:
    (related-topic edges only)
  • xlb >vibe coding/command:
    ->
    title=>vibe coding/command:
    (executable command edges only)
  • 查询xlb vibe coding主题
    ->
    title=>vibe coding/
  • >AI Model/
    ->
    title=>AI Model/
    (direct passthrough)
  • xlb >vibe coding/vib
    ->
    title=>vibe coding/vib
    (移除
    xlb 
    ,负载直接传递)
  • xlb ??vibe coding
    ->
    title=??vibe coding
    (移除
    xlb 
    ,负载直接传递)
  • xlb ->vibe coding/:
    ->
    title=->vibe coding/:
    (移除
    xlb 
    ,负载直接传递给API)
  • xlb >vibe coding/searchin:
    ->
    title=>vibe coding/searchin:
    (仅返回相关主题关联)
  • xlb >vibe coding/command:
    ->
    title=>vibe coding/command:
    (仅返回可执行命令关联)
  • 查询xlb vibe coding主题
    ->
    title=>vibe coding/
  • >AI Model/
    ->
    title=>AI Model/
    (直接传递)

Execute

执行方式

Run:
bash
skills/xlb-topic-index/scripts/fetch-topic-index.sh "xlb ??Vibe Coding"
The script performs:
  • POST http://localhost:5000/getPluginInfo
  • form fields:
    • title=<resolved command>
    • url=
    • markdown=
运行:
bash
skills/xlb-topic-index/scripts/fetch-topic-index.sh "xlb ??Vibe Coding"
该脚本执行以下操作:
  • 发送
    POST http://localhost:5000/getPluginInfo
    请求
  • 表单字段:
    • title=<解析后的命令>
    • url=
    • markdown=

Output Rule

输出规则

  • Return API response Markdown directly.
  • Do not paraphrase unless the user asks for analysis.
  • 直接返回API响应的Markdown内容。
  • 除非用户要求分析,否则不要改写内容。

Local URL Opening (built-in, no external dependency)

本地URL打开(内置功能,无外部依赖)

  • This project has native URL-open capability for local apps, no dependency on
    /Users/wowdd1/App/*.sh
    .
  • Single URL:
    • skills/xlb-topic-index/scripts/xlb-open-url.sh "https://example.com" chrome
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app chrome
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app dia
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app atlas
  • Open links from search result JSON:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-hits --hits-json-file /tmp/xlb-search.json --app chrome --limit 3
  • Optional integration with retrieve script:
    • XLB_OPEN_HITS=1 XLB_OPEN_APP=chrome XLB_OPEN_LIMIT=2 skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/:" "codex cli"
  • 本项目具有本地应用URL打开的原生能力,不依赖
    /Users/wowdd1/App/*.sh
  • 单个URL打开:
    • skills/xlb-topic-index/scripts/xlb-open-url.sh "https://example.com" chrome
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app chrome
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app dia
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-url --url "https://example.com" --app atlas
  • 从搜索结果JSON中打开链接:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py open-hits --hits-json-file /tmp/xlb-search.json --app chrome --limit 3
  • 与检索脚本的可选集成:
    • XLB_OPEN_HITS=1 XLB_OPEN_APP=chrome XLB_OPEN_LIMIT=2 skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/:" "codex cli"

Capability Routing Rule (for network content)

能力路由规则(针对网络内容)

  • Before fetching external URL content, discover capabilities each run:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py discover
  • If discover result contains suitable network skills or MCP tools, use them first.
  • If no suitable skill/MCP capability exists, fallback to this skill's local scripts.
  • Fallback policy: this skill must always remain runnable standalone (no hard dependency on external skills).
  • Optional external route hook:
    • Set
      XLB_EXTERNAL_ROUTE_CMD=/path/to/command
    • Command contract:
      cmd "<input>" "<retrieval_query>"
      and prints final output when it handles the request.
    • If external command exits non-zero or prints empty, fallback to local pipeline.
  • 在获取外部URL内容之前,每次运行时先发现可用能力:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py discover
  • 如果发现结果包含合适的网络技能或MCP工具,优先使用它们。
  • 如果没有合适的技能/MCP能力,回退到本技能的本地脚本。
  • 回退策略:本技能必须始终可以独立运行(不依赖外部技能)。
  • 可选外部路由钩子:
    • 设置
      XLB_EXTERNAL_ROUTE_CMD=/path/to/command
    • 命令约定:
      cmd "<input>" "<retrieval_query>"
      ,当它处理请求时打印最终输出。
    • 如果外部命令返回非零状态或输出为空,回退到本地流水线。

Code Retrieval Mode (efficient)

代码检索模式(高效)

  • Use code-based retrieval instead of full markdown dump when user asks to search/analyze:
    • skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/coding" "codex cli"
  • This mode does:
    1. Cache raw markdown
    2. Incremental update: if raw hash unchanged, skip re-ingest
    3. Parse markdown to virtual file tree
    4. Build sqlite index
    5. Optional concurrent prefetch of top-k URLs (
      XLB_PREFETCH_ARTIFACTS=1
      )
      • HTML links are converted to
        markdown
        /
        text
        artifacts (not stored as raw HTML)
      • External HTML converter is optional and preferred when configured
    6. Return top-k hits by query, or iterative rounds with stop strategy (
      XLB_ITERATIVE_SEARCH=1
      )
当用户要求搜索/分析时,使用基于代码的检索而非完整Markdown导出:
  • skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/coding" "codex cli"
    该模式执行以下步骤:
  1. 缓存原始Markdown
  2. 增量更新:如果原始内容哈希未变,跳过重新导入
  3. 将Markdown解析为虚拟文件树
  4. 构建sqlite索引
  5. 可选的Top-K URL并发预取(
    XLB_PREFETCH_ARTIFACTS=1
    • HTML链接转换为
      markdown
      /
      text
      格式的工件(不存储为原始HTML)
    • 配置后优先使用外部HTML转换器
  6. 根据查询返回Top-K结果,或采用带停止策略的多轮迭代检索(
    XLB_ITERATIVE_SEARCH=1

Performance Flags

性能参数

  • XLB_FORCE_REFRESH=1
    force refresh markdown from API
  • XLB_RAW_CACHE_TTL_SEC=300
    raw cache TTL value used only when
    XLB_AUTO_REFRESH_ON_QUERY=1
  • XLB_AUTO_REFRESH_ON_QUERY=0
    (default) do not auto refresh by TTL; only user explicit refresh (
    XLB_FORCE_REFRESH=1
    ) or cache miss will fetch
  • XLB_STORAGE_PROFILE=minimal
    (default) keep compact cache (
    raw + db + jsonl/topics
    ), no large VFS tree
  • XLB_STORAGE_PROFILE=full
    enable VFS folder/file materialization for folder-style browsing
  • XLB_OUTPUT=json
    force JSON output for no-query mode (returns raw file reference instead of full markdown text)
  • XLB_FORCE_REINDEX=1
    force re-ingest even when cache hash unchanged
  • XLB_PREFETCH_ARTIFACTS=1
    enable concurrent URL artifact prefetch
  • XLB_MAX_WORKERS=6
    control prefetch concurrency
  • XLB_TOPK=8
    control returned hit count
  • XLB_HTML_MODE=markdown|text
    choose HTML conversion output format
  • XLB_HTML_CONVERTER_BIN=/path/to/script
    optional external converter command
  • XLB_HTML_CONVERTER_TOOL_ID=url-to-markdown
    tool id passed to external converter
  • XLB_HTML_CONVERT_TIMEOUT_SEC=20
    timeout for external converter execution
  • XLB_ITERATIVE_SEARCH=1
    enable iterative retrieval summary output
  • XLB_MAX_ITER=5
    max iterative rounds
  • XLB_GAIN_THRESHOLD=0.05
    low-gain threshold
  • XLB_LOW_GAIN_ROUNDS=3
    consecutive low-gain rounds before stop
  • XLB_DISCOVER_CACHE_TTL_SEC=30
    capability discovery cache TTL (seconds)
  • XLB_OPEN_HITS=1
    open top hit URLs after retrieval (local app automation)
  • XLB_OPEN_APP=chrome|dia|atlas|default
    target app for opened URLs
  • XLB_OPEN_LIMIT=1
    number of URLs to open
  • XLB_OPEN_DRY_RUN=1
    print open plan only, do not trigger app actions
  • XLB_FORCE_REFRESH=1
    强制从API刷新Markdown
  • XLB_RAW_CACHE_TTL_SEC=300
    原始缓存TTL值,仅当
    XLB_AUTO_REFRESH_ON_QUERY=1
    时生效
  • XLB_AUTO_REFRESH_ON_QUERY=0
    (默认) 不按TTL自动刷新;仅当用户显式刷新(
    XLB_FORCE_REFRESH=1
    )或缓存未命中时才获取
  • XLB_STORAGE_PROFILE=minimal
    (默认) 保持紧凑缓存(
    raw + db + jsonl/topics
    ),不生成大型VFS树
  • XLB_STORAGE_PROFILE=full
    启用VFS文件夹/文件实例化,支持文件夹式浏览
  • XLB_OUTPUT=json
    在无查询模式下强制输出JSON(返回原始文件引用而非完整Markdown文本)
  • XLB_FORCE_REINDEX=1
    即使缓存哈希未变,也强制重新导入
  • XLB_PREFETCH_ARTIFACTS=1
    启用URL工件并发预取
  • XLB_MAX_WORKERS=6
    控制预取并发数
  • XLB_TOPK=8
    控制返回结果数量
  • XLB_HTML_MODE=markdown|text
    选择HTML转换输出格式
  • XLB_HTML_CONVERTER_BIN=/path/to/script
    可选的外部转换器命令
  • XLB_HTML_CONVERTER_TOOL_ID=url-to-markdown
    传递给外部转换器的工具ID
  • XLB_HTML_CONVERT_TIMEOUT_SEC=20
    外部转换器执行超时时间
  • XLB_ITERATIVE_SEARCH=1
    启用迭代检索摘要输出
  • XLB_MAX_ITER=5
    最大迭代轮数
  • XLB_GAIN_THRESHOLD=0.05
    低增益阈值
  • XLB_LOW_GAIN_ROUNDS=3
    连续低增益轮数达到此值时停止
  • XLB_DISCOVER_CACHE_TTL_SEC=30
    能力发现缓存TTL(秒)
  • XLB_OPEN_HITS=1
    检索后打开Top结果URL(本地应用自动化)
  • XLB_OPEN_APP=chrome|dia|atlas|default
    打开URL的目标应用
  • XLB_OPEN_LIMIT=1
    打开的URL数量
  • XLB_OPEN_DRY_RUN=1
    仅打印打开计划,不触发应用操作

??
Multi-Topic Behavior

??
多主题行为

  • For inputs like
    xlb ??vibe coding
    (without retrieval query), the script returns a topic suggestion JSON.
  • Each topic item includes:
    • topic
      ,
      count
      ,
      samples
    • entry_query
      (for example
      >Vibe Coding/
      )
    • entry_input
      (for example
      xlb >Vibe Coding/
      )
  • If multiple topics are returned, pick one
    entry_input
    and run it for focused retrieval.
  • 对于
    xlb ??vibe coding
    这类输入(无检索查询),脚本返回主题建议JSON。
  • 每个主题项包含:
    • topic
      count
      samples
    • entry_query
      (例如
      >Vibe Coding/
    • entry_input
      (例如
      xlb >Vibe Coding/
  • 如果返回多个主题,选择其中一个
    entry_input
    运行以进行聚焦检索。

Network Confirmation Policy

网络确认策略

  • Default is confirmation-required for expensive network expansion steps.
  • XLB_REQUIRE_NETWORK_CONFIRMATION=1
    (default): external route + prefetch disabled unless confirmed.
  • XLB_NETWORK_CONFIRMED=1
    : allow network-expensive actions for current command.
  • XLB_SHOW_CONFIRM_TEMPLATE=1
    (default): print standardized confirmation template to stderr when network expansion is blocked.
  • Default behavior without confirmation: only local index search + URL metadata output.
Example:
bash
XLB_PREFETCH_ARTIFACTS=1 \
XLB_HTML_MODE=markdown \
XLB_HTML_CONVERTER_BIN=/path/to/url-convert.sh \
XLB_HTML_CONVERTER_TOOL_ID=url-to-markdown \
skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/coding" "agent skills"
  • 默认情况下,执行高开销的网络扩展步骤需要确认。
  • XLB_REQUIRE_NETWORK_CONFIRMATION=1
    (默认):除非确认,否则禁用外部路由和预取。
  • XLB_NETWORK_CONFIRMED=1
    :允许当前命令执行高开销的网络操作。
  • XLB_SHOW_CONFIRM_TEMPLATE=1
    (默认):当网络扩展被阻止时,向标准错误输出打印标准化确认模板。
  • 未确认时的默认行为:仅执行本地索引搜索 + URL元数据输出。
示例:
bash
XLB_PREFETCH_ARTIFACTS=1 \
XLB_HTML_MODE=markdown \
XLB_HTML_CONVERTER_BIN=/path/to/url-convert.sh \
XLB_HTML_CONVERTER_TOOL_ID=url-to-markdown \
skills/xlb-topic-index/scripts/retrieve-topic-index.sh "xlb >vibe coding/coding" "agent skills"

Benchmark (before/after)

基准测试(优化前后)

bash
python3 skills/xlb-topic-index/bench/run_benchmark.py \
  --queries-file skills/xlb-topic-index/bench/queries.txt \
  --runs 3 \
  --topk 8
bash
python3 skills/xlb-topic-index/bench/run_benchmark.py \
  --queries-file skills/xlb-topic-index/bench/queries.txt \
  --runs 3 \
  --topk 8

Interop for Other Skills

与其他技能的互操作性

  • Cache contract reference:
    skills/xlb-topic-index/references/cache-interop.md
  • Resolve user input to stable cache key:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py resolve-input --input "xlb >vibe coding/coding"
  • Export cache usage guide from meta:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py describe-cache --meta-path "skills/xlb-topic-index/cache/index/<HASH>.meta.json" --format markdown
  • Program-first data files:
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.nodes.jsonl
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.topics.json
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.navigation.json
  • 缓存契约参考:
    skills/xlb-topic-index/references/cache-interop.md
  • 将用户输入解析为稳定的缓存键:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py resolve-input --input "xlb >vibe coding/coding"
  • 从元数据导出缓存使用指南:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py describe-cache --meta-path "skills/xlb-topic-index/cache/index/<HASH>.meta.json" --format markdown
  • 程序优先的数据文件:
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.nodes.jsonl
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.topics.json
    • skills/xlb-topic-index/cache/dataset/snap-<HASH>.navigation.json

Query Edge Semantics (for auto exploration)

查询关联语义(用于自动探索)

  • searchin
    section ->
    topic_navigation
    edges:
    • usually “related topics”, for example
      >AI Model
      -> normalized executable
      >AI Model/
  • command
    section ->
    knowledge_search
    edges:
    • executable knowledge-search commands, including bracket style like
      search(>vibe coding/vibe)
      -> executable
      >vibe coding/vibe
  • External skill can choose either:
    • follow
      topic_navigation
      to jump to another topic
    • run
      knowledge_search
      to deepen inside current domain
  • Prefer section-specific commands for efficient edge collection:
    • >topic/searchin:
      for topic-to-topic traversal
    • >topic/command:
      for command/deep-search traversal
  • searchin
    区段 ->
    topic_navigation
    关联:
    • 通常为“相关主题”,例如
      >AI Model
      -> 标准化可执行命令
      >AI Model/
  • command
    区段 ->
    knowledge_search
    关联:
    • 可执行的知识搜索命令,包括括号格式如
      search(>vibe coding/vibe)
      -> 可执行命令
      >vibe coding/vibe
  • 外部技能可选择:
    • 跟随
      topic_navigation
      跳转到另一个主题
    • 运行
      knowledge_search
      深入当前领域
  • 优先使用区段特定命令以高效收集关联:
    • >topic/searchin:
      用于主题间遍历
    • >topic/command:
      用于命令/深度搜索遍历

Auto Explore Command

自动探索命令

  • Use:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py explore-next --meta-path "skills/xlb-topic-index/cache/index/<HASH>.meta.json" --strategy topic_first --dry-run
  • Remove
    --dry-run
    to execute next hop directly.
  • Useful flags:
    • --strategy topic_first|search_first|mixed
    • --visited-file <path> --update-visited
      to avoid repeated edges
    • --include-other-queries
      to allow
      ??...
      style fallback edges
  • 使用方式:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py explore-next --meta-path "skills/xlb-topic-index/cache/index/<HASH>.meta.json" --strategy topic_first --dry-run
  • 移除
    --dry-run
    参数可直接执行下一步操作。
  • 实用参数:
    • --strategy topic_first|search_first|mixed
    • --visited-file <path> --update-visited
      避免重复关联
    • --include-other-queries
      允许
      ??...
      格式的回退关联

Explore Loop (dedupe + budget + priority)

探索循环(去重 + 预算 + 优先级)

  • Use:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py explore-loop --seed-input "xlb >vibe coding/:" --edge-strategy searchin_command_backlink --max-steps 12 --max-depth 4 --max-seconds 90 --visited-file /tmp/xlb-visited.json --visited-topics-file /tmp/xlb-visited-topics.json --update-visited
  • Behavior:
    • Auto uses
      >topic/searchin:
      and
      >topic/command:
      to collect next edges.
    • Applies visited dedupe (
      visited-file
      +
      visited-topics-file
      ) to avoid loops.
    • Stops by budget (
      max-steps
      /
      max-depth
      /
      max-seconds
      ).
    • Edge priority default is
      searchin -> command -> backlink
      .
  • 使用方式:
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py explore-loop --seed-input "xlb >vibe coding/:" --edge-strategy searchin_command_backlink --max-steps 12 --max-depth 4 --max-seconds 90 --visited-file /tmp/xlb-visited.json --visited-topics-file /tmp/xlb-visited-topics.json --update-visited
  • 行为:
    • 自动使用
      >topic/searchin:
      >topic/command:
      收集下一层关联。
    • 应用已访问去重(
      visited-file
      +
      visited-topics-file
      )避免循环。
    • 根据预算(
      max-steps
      /
      max-depth
      /
      max-seconds
      )停止。
    • 关联优先级默认顺序为
      searchin -> command -> backlink

One-Click Wrapper

一键式包装器

  • Use:
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "vibe coding"
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "xlb >vibe coding/:"
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "xlb auto vibe coding"
  • Wrapper defaults:
    • persistent visited files under
      skills/xlb-topic-index/cache/
    • strategy
      searchin_command_backlink
    • budget
      12 steps / depth 4 / 90s
  • Override with env vars:
    • XLB_AUTO_MAX_STEPS
      ,
      XLB_AUTO_MAX_DEPTH
      ,
      XLB_AUTO_MAX_SECONDS
    • XLB_AUTO_EDGE_STRATEGY
      ,
      XLB_AUTO_INCLUDE_BACKLINKS
      ,
      XLB_AUTO_UPDATE_VISITED
  • 使用方式:
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "vibe coding"
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "xlb >vibe coding/:"
    • skills/xlb-topic-index/scripts/xlb-auto-explore.sh "xlb auto vibe coding"
  • 包装器默认配置:
    • 持久化已访问文件存储在
      skills/xlb-topic-index/cache/
    • 策略为
      searchin_command_backlink
    • 预算为
      12步 / 深度4 / 90秒
  • 可通过环境变量覆盖:
    • XLB_AUTO_MAX_STEPS
      XLB_AUTO_MAX_DEPTH
      XLB_AUTO_MAX_SECONDS
    • XLB_AUTO_EDGE_STRATEGY
      XLB_AUTO_INCLUDE_BACKLINKS
      XLB_AUTO_UPDATE_VISITED

Graph Backlink Query (
->
)

图反向链接查询(
->

  • Input:
    • xlb ->vibe coding/:
  • Meaning:
    • This is a server-side command and is passed through as
      title=->vibe coding/:
      .
    • retrieve-topic-index.sh
      should not local-intercept this command.
  • Local graph helper (explicit, optional):
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py graph-neighbors --index-dir skills/xlb-topic-index/cache/index --target-title "->vibe coding/:"
    • Used only when you explicitly want cache-based local graph exploration.
  • 输入:
    • xlb ->vibe coding/:
  • 含义:
    • 这是一个服务器端命令,将直接传递为
      title=->vibe coding/:
    • retrieve-topic-index.sh
      不应在本地拦截此命令。
  • 本地图辅助工具(显式、可选):
    • python3 skills/xlb-topic-index/scripts/xlb_rag_pipeline.py graph-neighbors --index-dir skills/xlb-topic-index/cache/index --target-title "->vibe coding/:"
    • 仅当你明确想要基于缓存的本地图探索时使用。

Error Handling

错误处理

  • API unreachable: report connection failure and suggest checking local service on port
    5000
    .
  • Empty response: return a short warning and ask whether to retry with a broader command (for example
    >Vibe Coding/
    ).
  • Empty input only: ask user to provide any non-empty title command.
  • API不可达:报告连接失败,并建议检查端口
    5000
    上的本地服务。
  • 空响应:返回简短警告,并询问是否使用更宽泛的命令重试(例如
    >Vibe Coding/
    )。
  • 仅输入空内容:要求用户提供非空的标题命令。