ByClaw

当用户想了解本体如何开发和使用时使用本技能。它能够通过 CRM 的实际 DEMO，演示以下 6 项能力：1）自然语言数据查询（无需 SQL）；2）聚合统计分析；3）字段歧义智能消歧；4）非结构化文本转对象和跨表视图的创建；5）数据操作（周报生成→信息抽取→客户录入→商机任务创建）；6）非结构化本体的文档融合检索。你可以通过以下对话唤起本技能：「给我演示一下」「本体能做什么」「怎么创建对象和视图」「结构化和非结构化怎么融合」「帮我查一下客户数据」。

当你想让 Agent 查询或操作你自己定义的业务数据（而不是系统内置数据）时使用本技能。它能够帮你用自然语言定义一张新的数据表，并基于这张表开发出本体对象，设定字段和字段含义，数据自动存入专属 数据表；还能创建跨表视图，让 Agent 同时查询多个对象。定义完成后挂载到当前数字员工，Agent 就能直接查询和操作你的数据了。你可以通过以下对话唤起本技能：「帮我创建一个任务管理对象」「我想建一个拜访记录表，包含客户名、拜访日期、跟进结果」「查看我有哪些本体对象」「把任务对象挂载到我的助理」。

当你有文档、图片、视频等非结构化内容存在知识库里，想让 Agent 能像查结构化数据一样精准检索和操作它们时使用本技能。它能够帮你给非结构化内容打上结构化标签（定义字段，如日期、主题、参会人），让每份文档/图片/视频都带有可查询的属性，实现结构化数据与非结构化内容的融合检索。定义的标签字段相当于表的字段，支持新增、修改、删除操作。与结构化本体的区别在于：内容本身存在知识库里，而不是动态表。你可以通过以下对话唤起本技能：「帮我创建一个会议纪要对象，绑定到我的会议知识库」「我的周报存在知识库里，想让 Agent 能按日期和项目名检索」「查看我的知识库有哪些」「把会议纪要对象挂载到我的助理」。

把任意内容（网页链接、文章、关键词）整理成一份结构化的播客视频大纲，是制作播客视频的第一步， 后续的幻灯片和对话脚本都从这份大纲生成，保证两者内容一致。 只要用户想制作播客视频、把文章变成视频、做一期播客、先规划内容结构， 或者说"做个大纲"、"做播客"、"把这篇文章做成播客"，就必须触发此技能—— 即使用户没有提到"大纲"，只要目标是制作播客视频就要触发。

根据播客大纲生成双人对话脚本（主持人和嘉宾），对话自然流畅，每句话都标注对应的幻灯片编号， 方便后续配音和视频同步。也可以直接从关键词或文章生成对话脚本。 只要用户想写播客脚本、生成对话、把内容做成两个人聊天的形式、帮我写播客、做播客对白， 就应该触发此技能——即使用户只说"写个脚本"或"把这个做成对话"也要触发。

把幻灯片和播客配音合成为一个带字幕的视频，幻灯片随着对话内容自动切换，字幕逐句出现，是播客视频的最后一步。 只要用户说合成视频、生成视频、把幻灯片和音频合在一起、加字幕、做成视频、最后一步，好了合成吧， 或者前面几步都做完了想收尾，就应该触发此技能——即使用户只说"合成"也要触发。

用火山引擎（豆包）语音合成将播客对话脚本转成双声道音频，主持人和嘉宾各用一个声音， 同时生成精确到每个句子的时间信息，供视频合成使用。 只要用户想给脚本配音、生成播客音频、把对话变成声音、生成语音、脚本转音频， 或者正在做播客视频需要录音，就应该触发此技能——即使用户只说"配音"或"生成音频"也要触发。

根据播客大纲生成专业的演示文稿，是播客视频流水线的视觉环节。也可以独立生成 PPT 或编辑已有演示文稿。 只要用户提到生成 PPT、做幻灯片、制作演示文稿、做 slides、幻灯片生成， 或者正在制作播客视频需要视觉内容，就应该触发此技能——即使用户只说"帮我做个 PPT"也要触发。

分析 GitHub 开源项目并写成一篇适合发布的技术文章，带真实安装测试和性能数据，风格接地气、手机友好。 只要用户给了一个 GitHub 链接，并提到写文章、做评测、项目推荐、公众号推文、帮我介绍这个项目、 把这个项目写成文章、安利一下这个工具，就应该触发此技能——即使用户只说"帮我写写这个"也要触发。 生成的文章也可以直接用来制作播客视频。

byCLI 全能力 skill — 统一管理 bycli 命令执行、浏览器驱动、适配器自修复、适配器编写、Markdown 入库。当用户需要运行 bycli 命令、驱动浏览器完成任务、修复失败的 adapter、编写新 adapter、查询 bycli 用法、将内容存入知识库，或发起搜索 / 采集 / 抓取 / 爬取 / 网站操作类任务时使用。触发短语："bycli"、"浏览器操作"、"adapter 坏了"、"写个 adapter"、"爬取数据"、"修复命令"、"browser open"、"autofix"、"open cli"、"驱动浏览器"、"写爬虫"、"browser driving"、"fix adapter"、"write adapter"、"搜索"、"查找"、"采集"、"抓取"、"爬取"、"获取"、"打开网站"、"访问网页"、"登录"、"操作网站"、"scrape"、"crawl"、"browse"、"open URL"、"存到知识库"、"入库"、"导入知识库"、"保存到知识库"、"沉淀到知识库"、"收藏到知识库"、"归档"。

使用 gbrain CLI 接管 agent 记忆管理：先查脑、写入/维护第二大脑、导入 Markdown、向量检索、图谱/时间线、embed/sync/dream/onboard。用户要求记忆、brain-first 查询、知识库维护时使用；不要替代实时网页搜索或其它专用业务 skill。

Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.

Universal archivist for personal file archives (Dropbox/B2/Gmail-takeout/local-mount/hard-drive-dump). Filters for high-value content (the user's own writing, ideas, relationships) and surfaces it interactively. REFUSES TO RUN without an explicit gbrain.yml `archive-crawler.scan_paths:` allow-list.

Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/<slug>-personalized.md plus an optional PDF via brain-pdf.

Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.

Generate a publication-quality PDF from any brain page via the gstack make-pdf binary. Strips YAML frontmatter, sanitizes emoji, applies running headers and page numbers. Brain page is always the source of truth; PDF is a rendering.

Filing gate for ALL brain writes. Consulted before creating any new brain page to determine the correct path. Reads the ACTIVE schema pack via `gbrain schema show --json` — no hardcoded directory table. Also runs periodic taxonomy drift detection via `gbrain schema review-orphans`.

Compile daily briefing with meeting context, active deals, and citation tracking

Save any thought or content into the brain via one CLI command. The single human-facing entrypoint that replaces "put_page vs commit-then-sync vs autopilot-wait" with one command that just works.

Audit and fix citation formatting across brain pages. Ensures every fact has an inline [Source: ...] citation matching the standard format. Extended in v0.25.1: scans for broken tweet/post references that lack actual URLs and resolves them via the host's X / Twitter API integration.

Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.

Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.

Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, switch silently to the next. Extended in v0.25.1 with structured review-mode gating (when to invoke vs not) and a Codex code-review handoff for the diff-review case.

Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.

Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable.

Enrich brain pages with tiered enrichment protocol. Creates and updates person/company pages with compiled truth, timeline, and cross-links. Use when a new entity is mentioned or an existing page needs updating.

Validate and auto-repair YAML frontmatter on brain pages. Catches malformed pages before they enter the brain (missing closing

Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.

Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, create author people page, and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".

Route content to specialized ingestion skills. Detects input type and delegates.

Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

Ingest meeting transcripts into brain pages with attendee enrichment, entity propagation, and timeline merge. A meeting is NOT fully ingested until the enrich skill has processed every entity.

Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface.

Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).

Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.

Where new brain files go. Decision protocol for filing brain pages by primary subject, not by format or source. Reference for all brain-writing skills.

Evolve your brain's schema pack. Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the pack declares.

Set up GBrain with auto-provision Supabase or PGLite, AGENTS.md injection, first import