@jayjiang/byoao 1.1.2 → 2.0.1

package/src/assets/obsidian-skills/vault-thinking.md

@@ -11,21 +11,22 @@ This vault has BYOAO thinking commands available. Suggest them when they match t
 
 | Command | What it does | Suggest when |
 |---------|-------------|--------------|
-| `/weave` | Enrich notes with frontmatter, wikilinks, suggest permanent concept notes | User imports new files, asks to organize, or vault has many unlinked notes |
+| `/cook` | Digest notes and sources into structured knowledge pages under `entities/`, `concepts/`, `comparisons/`, `queries/` | User imports new files, asks to organize raw notes, or wants the vault compiled into LLM Wiki pages |
+| `/health` | Check knowledge-page health (orphans, stale content, contradictions among agent pages) | User wants a big-picture review of compiled knowledge, asks what's broken or outdated, or after heavy `/cook` activity |
 | `/trace topic` | Chronological timeline of how an idea evolved | User asks how something developed, wants history, or says "when did I start..." |
-| `/emerge` | Surface hidden patterns, clusters, contradictions across the vault | User asks "what am I missing", wants a big-picture review, or seems stuck |
 | `/connect A B` | Bridge two topics via the vault's link graph | User wonders if two areas are related, or wants cross-domain insight |
 | `/ideas` | Deep scan to generate actionable ideas from vault content | User asks "what should I work on", wants brainstorming, or needs next steps |
 | `/challenge topic` | Pressure-test a belief against the vault's own history | User is making a decision, says "am I wrong", or wants to validate an assumption |
 | `/drift` | Compare stated intentions vs actual behavior over 30-90 days | User asks about follow-through, wonders where time went, or reviews goals |
 | `/diagnose` | Vault health check — orphans, broken links, frontmatter gaps | User notices broken links, asks "what's wrong with my vault", or after heavy editing |
+
 ## When to Proactively Suggest
 
 - User is **reflecting on a topic** → suggest `/trace` to see how their thinking evolved
-- User is **brainstorming or feels stuck** → suggest `/emerge` or `/ideas`
+- User is **brainstorming or feels stuck** → suggest `/ideas` or `/health` on compiled knowledge
 - User is **making a decision** → suggest `/challenge` to pressure-test it
 - User is **reviewing goals or progress** → suggest `/drift`
-- User **imported new notes** or mentions disorganization → suggest `/weave`
+- User **imported new notes** or mentions disorganization → suggest `/cook`
 - User asks about **connections between topics** → suggest `/connect`
 - User mentions **broken links or vault messiness** → suggest `/diagnose`
 
@@ -35,6 +36,6 @@ Mention the command naturally in conversation. For example:
 
 - "You could run `/trace data-mesh` to see how that idea has evolved across your notes."
 - "If you want to pressure-test that assumption, `/challenge` can find counter-evidence in your vault."
-- "After importing those files, `/weave` can add frontmatter and link them to your existing notes."
+- "After importing those files, `/cook` can distill them into linked knowledge pages under entities and concepts."
 
 Do not run these commands automatically — they read many vault files and can take several minutes. Always let the user decide when to invoke them.

package/src/assets/presets/common/AGENTS.md.hbs

@@ -1,25 +1,29 @@
 # AI Agent Guide
 
-## 关于本知识库
-这是一个基于 Zettelkasten 理念构建的个人知识库。知识通过原子化的笔记和双向链接形成网络。你可以保留自己的目录组织习惯，笔记之间的关联由 Agent 通过 `/weave` 自动维护。
+## About This Knowledge Base
+This is an LLM Wiki knowledge base. Your notes are raw material — the Agent compiles them into structured knowledge pages via `/cook`. Both coexist in the same vault, connected through wikilinks.
 
-## 从哪里开始
-知识图谱：运行 `/wiki` 生成 `INDEX.base` 后，从这里探索知识库的结构。
+## Getting Started
+Run `/wiki` to generate `INDEX.base`, then explore the knowledge structure from there.
 
-## 笔记类型
-每条笔记通过 frontmatter 的 `note_type` 分为三类：
-- **fleeting** — 原始摄入，待处理
-- **literature** — 对某来源的整理笔记
-- **permanent** — 原子概念笔记
+## Note Types
+User notes: Your existing notes, kept in their original directories (Projects/, Daily/, etc.) — untouched.
+Agent pages: Knowledge pages maintained by the Agent, located in `entities/`, `concepts/`, `comparisons/`, `queries/`.
 
-## 操作规则
-**使用 Obsidian CLI 进行所有笔记操作**（`obsidian read`、`obsidian search`、`obsidian create` 等）。
-不要用 bash（`cat`、`grep`、`find`、`sed` 等）直接处理笔记文件——Obsidian CLI 能正确维护 wikilink、frontmatter 和文件关系。
+## Operating Rules
+**Use Obsidian CLI for all note operations** (`obsidian read`, `obsidian search`, `obsidian create`, etc.).
+Do not use bash (`cat`, `grep`, `find`, `sed`, etc.) to manipulate note files directly — Obsidian CLI correctly maintains wikilinks, frontmatter, and file relationships.
 
-## 可用能力
-- **/weave** — 编织新笔记：提取概念、建立 wikilink、生成 frontmatter
-- **/wiki** — 生成 INDEX.base 知识图谱索引
-- **/organize** — 按需重组目录结构
-- **/ask** — 对知识库进行开放式问答
-- **Thinking Tools** — /trace、/emerge、/connect、/ideas、/challenge、/drift
-- **/diagnose** — 检查知识库健康状态，查看哪些笔记需要编织
+## Available Skills
+- **/cook** — Digest notes and external sources, compile knowledge pages
+- **/health** — Check knowledge page health (orphans, stale content, contradictions)
+- **/prep** — Fix frontmatter and broken wikilinks
+- **/wiki** — Generate INDEX.base knowledge map
+- **/organize** — Reorganize directory structure as needed
+- **/ask** — Open-ended Q&A against the knowledge base
+- **Thinking Tools** — /trace, /connect, /ideas, /challenge, /drift
+- **/diagnose** — Check overall vault health
+
+{{#if ROLE_SECTION}}
+## {{ROLE_SECTION}}
+{{/if}}

package/src/assets/presets/common/SCHEMA.md.hbs

@@ -0,0 +1,57 @@
+# SCHEMA.md
+
+Knowledge taxonomy and conventions for [[{{KB_NAME}}]].
+
+## Knowledge Domains
+
+{{#if WIKI_DOMAIN}}
+{{WIKI_DOMAIN}}
+{{else}}
+Not yet defined. The Agent will populate this as it learns the domain.
+{{/if}}
+
+## Tag Taxonomy
+
+Tags follow these conventions:
+- 2-5 tags per page, alphabetically sorted
+- Tags should be singular (use `#project` not `#projects`)
+- New tags should be added here first before use
+
+### Current Tags
+
+No tags defined yet. The Agent will propose new tags as knowledge pages are created.
+
+## Domain Taxonomy
+
+No domains defined yet. The Agent will propose domains as knowledge pages are created.
+
+## Agent Page Conventions
+
+| Directory | Purpose |
+|-----------|---------|
+| `entities/` | Concrete, named things (people, organizations, products, systems) |
+| `concepts/` | Abstract ideas (methods, rules, decisions, processes) |
+| `comparisons/` | Side-by-side analyses of options |
+| `queries/` | User-question-driven answers worth keeping |
+
+## Frontmatter Schema
+
+See the /cook skill specification for the complete frontmatter schema. Key required fields:
+
+- `title` — concise one-line summary
+- `date` — primary temporal anchor (ISO 8601)
+- `created` — page creation date
+- `updated` — last content change date (bump on every edit)
+- `type` — one of: entity, concept, comparison, query
+- `tags` — 2-5 tags from this taxonomy, alphabetically sorted
+- `sources` — relative paths to contributing notes
+
+## Page Thresholds
+
+- Create a page when: entity/concept appears in 2+ notes OR is central subject of one note
+- Split a page when: it exceeds ~200 lines
+- Do NOT create pages for: passing mentions, minor details, out-of-domain topics
+
+## Custom Fields
+
+No custom fields defined yet. The Agent documents new fields here when first used.

package/src/assets/presets/common/Start Here.md.hbs

@@ -7,8 +7,8 @@ tags: [onboarding]
 
 # Welcome to {{KB_NAME}}
 
-Your personal knowledge base. Curate what matters, and let AI
-connect the dots into a knowledge graph.
+Your LLM-powered knowledge base. Write notes freely, and let AI
+compile them into structured, cross-referenced knowledge pages.
 
 ## Choose Your Path
 
@@ -25,58 +25,43 @@ you decide what belongs in your local knowledge base.
    and drop them into this vault folder.
 2. **Obsidian Web Clipper** — Install the browser extension to save
    any web page directly into your vault as a clean markdown note.
-3. **Write summaries** — You don't need full copies. Create a local
-   note that captures the key insights and link back to the source:
+3. **Write summaries** — Create a local note that captures key insights.
 
-```yaml
----
-title: "Migration Plan Q2"
-source: "https://confluence.example.com/pages/12345"
----
-```
-
-> The `source` property keeps the connection between your local note
-> and the cloud original. Add it whenever a note originates from an
-> external document.
-
-**Once you have a few notes → run `/weave`** (see below).
+**Once you have a few notes → run `/cook`** (see below).
 
 ### Path B: I already have local notes
 
-If you have existing markdown files — whether organized or scattered:
+If you have existing markdown files:
 
 1. **Drop them in** — Copy or move your files into this vault folder.
-   (Or if you ran `byoao init --from`, they're already here.)
-2. **Don't worry about structure** — Your files don't need frontmatter,
-   wikilinks, or any particular organization yet.
+2. **Don't worry about structure** — Your files don't need frontmatter
+   or any particular organization yet.
 
-**Run `/weave` now** — it will scan your notes, add frontmatter
-metadata (including dates from file timestamps), discover connections,
-and build your [[Glossary]] from frequently mentioned concepts.
+**Run `/cook` now** — it will scan your notes, identify entities and
+concepts, and compile them into structured knowledge pages.
 
 ### Path C: Starting fresh
 
 No existing notes? No problem.
 
 1. Press `Cmd+T` (Mac) or `Ctrl+T` (Windows) → choose "Daily Note".
-2. Write what's on your mind today. Don't worry about structure.
-3. After a few notes, run `/weave` to connect them.
+2. Write what's on your mind today.
+3. After a few notes, run `/cook` to compile them.
 
 ---
 
-## /weave — Where the Magic Happens
-
-Open your AI agent and type `/weave`. It will:
+## /cook — Where the Magic Happens
 
-- **Add frontmatter** — title, date, type, domain, tags
-- **Create wikilinks** — connect related notes automatically
-- **Build your Glossary** — extract key terms and concepts
-- **Suggest organization** — propose directory structure (with your approval)
+Open your AI agent and type `/cook`. It will:
 
-Watch: scattered files become a connected knowledge graph.
+- **Read your notes** — from anywhere in the vault
+- **Identify entities** — people, organizations, products, systems
+- **Identify concepts** — methods, rules, decisions, processes
+- **Create/update pages** — in `entities/`, `concepts/`, `comparisons/`, `queries/`
+- **Flag contradictions** — when notes disagree
+- **Report in plain language** — what changed, what needs your attention
 
-After weaving, press `Cmd+G` (Mac) or `Ctrl+G` (Windows) to see your
-knowledge visualized. Every node is a note, every line is a connection.
+After cooking, press `Cmd+G` to open Graph View and see the connections.
 
 ---
 
@@ -97,15 +82,17 @@ knowledge visualized. Every node is a note, every line is a connection.
 
 | Command | What it does |
 |---------|-------------|
-| `/weave` | Connect your notes into a knowledge graph |
-| `/organize` | Reorganize vault directories using enriched metadata |
+| `/cook` | Compile notes into structured knowledge pages |
+| `/health` | Check knowledge page health |
+| `/wiki` | Generate INDEX.base knowledge map |
+| `/organize` | Reorganize vault directories |
+| `/ask` | Open-ended Q&A against your knowledge |
 | `/trace` | Track how an idea evolved over time |
-| `/emerge` | Discover patterns you haven't noticed |
 | `/connect` | Bridge two seemingly unrelated topics |
 | `/ideas` | Generate actionable ideas from your vault |
 | `/challenge` | Pressure-test a belief against your own notes |
 | `/drift` | Compare intentions vs actions over time |
-| `/diagnose` | Check knowledge graph health |
+| `/diagnose` | Check overall vault health |
 
 {{#if HAS_MCP_SERVICES}}
 
@@ -122,11 +109,13 @@ These services authenticate via your browser. If a connection expires,
 tell the agent: "reconnect to {service name}".
 
 {{/if}}
+
 ---
 
 ## Key Files
 
-- **[[Glossary]]** — Domain terms and key concepts
+- **[[SCHEMA]]** — Tag taxonomy and knowledge conventions
+- **[[log]]** — Agent activity log
 - **AGENTS.md** — How AI agents navigate this vault
 
 ---

package/src/assets/presets/minimal/preset.json

@@ -1,9 +1,9 @@
 {
   "name": "minimal",
-  "displayName": "Personal Knowledge Base",
-  "description": "A minimal personal knowledge base — just Daily notes, templates, and Glossary. Add structure as you go.",
+  "displayName": "Minimal",
+  "description": "Core LLM Wiki with no extra MCP servers or role-specific directories",
   "directories": [],
-  "agentDescription": "Personal knowledge base. Notes are connected through wikilinks and frontmatter. Use /weave to discover and strengthen connections.",
+  "agentDescription": "LLM Wiki knowledge base. Use /cook to digest notes and external sources. Use /health to health-check.",
   "frontmatterExtras": {},
   "templates": [],
   "mcpServers": {},

package/src/assets/presets/pm-tpm/preset.json

@@ -1,9 +1,9 @@
 {
   "name": "pm-tpm",
   "displayName": "PM / TPM",
-  "description": "Project tracking, sprint cycles, stakeholder management, data analysis",
+  "description": "Adds Atlassian + BigQuery MCP servers, project directories, and PM templates on top of the core LLM Wiki",
   "directories": ["Projects", "Sprints"],
-  "agentDescription": "PM/TPM knowledge base",
+  "agentDescription": "LLM Wiki knowledge base with PM/TPM tooling. Use /cook to digest notes and external sources. Use /health to health-check. Atlassian and BigQuery are connected.",
   "frontmatterExtras": {
     "project": ["jira", "stakeholders", "priority"],
     "sprint": ["sprint-dates", "jira-board"]

package/src/skills/ask/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: ask
+description: >
+  Open-ended Q&A against the knowledge base. Agent reads INDEX.base for page discovery
+  and SCHEMA.md for tag taxonomy, navigates entities/, concepts/, comparisons/, and queries/,
+  synthesizes answers with citations. Use when the user asks questions about vault content
+  like "what is X", "why did we decide Y", "explain Z", "what do my notes say about",
+  "summarize what I know about", or any question that should be answered from accumulated
+  knowledge rather than general training data.
+---
+
+# /ask — Knowledge Q&A
+
+You are a knowledge assistant. Your job is to answer questions by navigating the vault's knowledge graph, reading relevant pages, and synthesizing evidence-based answers — always citing sources with wikilinks.
+
+## Prerequisites Check
+
+**Before doing anything else**, verify Obsidian CLI is available:
+
+```bash
+obsidian --version
+```
+
+If this fails, STOP and display the Obsidian CLI availability message (see /prep).
+
+## Parameters
+
+- **question** (required): The question to answer.
+- **output** (optional): Save the answer as a note at this path.
+
+## Process
+
+### Step 1: Understand the Question
+
+Identify the key concepts, entities, and intent in the user's question.
+
+### Step 2: Locate Relevant Pages
+
+If `INDEX.base` exists, read it first for page discovery and the compiled knowledge map:
+
+```bash
+obsidian read file="INDEX.base"
+```
+
+Read `SCHEMA.md` when you need the tag taxonomy, domain rules, or agent directory conventions.
+
+Then search for relevant pages:
+
+```bash
+obsidian search "<key concept>"
+```
+
+Search for each key concept mentioned in the question. Combine results across concepts.
+
+### Step 3: Read Relevant Pages
+
+For each promising result, read the full content:
+
+```bash
+obsidian read file="entities/some-page.md"
+```
+
+Prioritize:
+- Agent pages in `entities/`, `concepts/`, `comparisons/`, `queries/`
+- Pages with matching tags or domain
+- Pages with `status: reviewed` (over `draft`)
+- Recent pages (higher `updated` date)
+
+Also read user source notes when the question requires original context.
+
+### Step 4: Synthesize Answer
+
+Combine evidence from all relevant pages into a clear, structured answer:
+
+- **Direct answer first** — address the question directly
+- **Supporting evidence** — cite specific pages with wikilinks and brief quotes
+- **Context** — explain how the evidence connects
+- **Uncertainties** — flag gaps where the vault doesn't have enough information
+
+Every claim must be backed by at least one vault note. Do not use general knowledge to answer — ground everything in the vault.
+
+### Step 5: Present Answer
+
+```markdown
+## Answer
+
+<Direct answer to the question>
+
+## Evidence
+
+- **[[Page A]]**: "<relevant quote>"
+- **[[Page B]]**: "<relevant quote>"
+- **[[Page C]]**: "<relevant quote>"
+
+## Context
+
+<Brief paragraph connecting the evidence and explaining the bigger picture>
+
+## Gaps
+
+<What the vault doesn't cover that would help answer more completely>
+
+## Related Questions
+
+- Consider exploring: "..."
+- Run `/trace topic="X"` to see how this evolved
+- Run `/connect from="A" to="B"` to understand the relationship
+- If the vault lacks pages for key entities or concepts, run `/cook` to compile knowledge from source notes
+```
+
+### Step 6: Save (Optional)
+
+At the end of your answer, ask:
+
+> "Would you like me to save this as a note?"
+
+If the user confirms, save the answer with frontmatter:
+
+```yaml
+---
+title: "Answer: <topic>"
+date: <today>
+tags: [qa, <topic>]
+---
+```
+
+Use `obsidian create` to save. Ask the user where they'd like it saved.
+
+## Key Principles
+
+- **Evidence-based**: Every answer must cite vault notes. No general knowledge answers.
+- **Direct first**: Answer the question before providing supporting detail.
+- **Acknowledge gaps**: If the vault doesn't have enough information, say so.
+- **Respect scope**: Only answer based on vault content, not external knowledge.
+- **Save on request**: Always offer to save the answer as a note for future reference.

package/src/skills/challenge/SKILL.md

@@ -0,0 +1,134 @@
+---
+name: challenge
+description: >
+  Pressure-tests beliefs against vault evidence. Finds contradictions, position changes,
+  unstated assumptions, and weak points in arguments. Use when the user wants to question
+  a decision, test a hypothesis, find flaws in reasoning, play devil's advocate, or says
+  anything like "challenge this", "what's wrong with my thinking", "poke holes in this",
+  "are there contradictions", or "stress test this idea".
+---
+
+# /challenge — Pressure Test
+
+You are a respectful adversary. Your job is to find the weak points in a belief, decision, or argument — not to be destructive, but to strengthen the user's thinking by exposing vulnerabilities they may have missed.
+
+## Prerequisites Check
+
+```bash
+obsidian --version
+```
+
+If this fails, STOP and display the Obsidian CLI availability message (see /prep).
+
+## Parameters
+
+- **claim** (required): The belief, decision, or argument to challenge.
+- **scope** (optional): `all` (full vault) or a specific directory/page. Default: `all`.
+
+## Process
+
+### Step 1: Understand the Claim
+
+Clarify what exactly is being challenged:
+- What is the core assertion?
+- What assumptions does it rest on?
+- What would falsify it?
+
+If the claim is ambiguous, ask the user to clarify before proceeding.
+
+### Step 2: Find Supporting Evidence
+
+```bash
+obsidian search "<key terms from claim>"
+```
+
+Read relevant notes and agent pages. Identify:
+- Notes that explicitly support the claim
+- Notes that provide indirect support (data, observations)
+- The strength of each piece of evidence
+
+### Step 3: Find Contradicting Evidence
+
+This is the core of /challenge. Search for:
+
+1. **Direct contradictions** — Notes that explicitly state the opposite
+   ```bash
+   obsidian search "not <term>" OR "instead of <term>" OR "changed from <term>"
+   ```
+
+2. **Implicit contradictions** — Notes that describe a situation incompatible with the claim
+   - Read pages with shared tags but different conclusions
+   - On related `entities/` and `concepts/` pages, check optional `contradictions` frontmatter (v2: YAML list of other agent page names documenting conflicting claims — see `/cook` Contradiction Handling)
+
+3. **Position changes over time** — Notes that show the user changed their mind
+   ```bash
+   obsidian search "actually" OR "turns out" OR "reconsidered" OR "reversed"
+   ```
+
+4. **Weasel words** — Notes that express uncertainty about aspects the claim treats as certain
+   - "might", "probably", "not sure", "need to verify"
+   - These indicate the claim is stronger than the evidence supports
+
+### Step 4: Identify Unstated Assumptions
+
+For the claim to be true, what else must be true?
+
+- Technical assumptions (about systems, tools, constraints)
+- People assumptions (about availability, skills, priorities)
+- Temporal assumptions (about deadlines, sequencing, stability)
+- External assumptions (about market, users, dependencies)
+
+Check if the vault evidence supports each assumption.
+
+### Step 5: Assess Evidence Strength
+
+Rate the overall case:
+
+| Strength | Meaning |
+|----------|---------|
+| Strong | Multiple independent sources agree, no contradictions |
+| Moderate | Some support, minor gaps or contradictions |
+| Weak | Limited evidence, significant contradictions or gaps |
+| Unknown | Vault doesn't have enough information |
+
+### Step 6: Present the Challenge
+
+```markdown
+# Challenge: "{claim}"
+
+## The Claim
+{Restate the claim clearly}
+
+## What Rests On This
+{What assumptions does the claim depend on?}
+- {Assumption 1} — {supported / unsupported / contradicted}
+- {Assumption 2} — {supported / unsupported / contradicted}
+
+## Supporting Evidence
+- [[Note A]]: "{quote}"
+- [[Note B]]: "{quote}"
+
+## Challenging Evidence
+- ⚠ [[Note C]]: "{quote that contradicts or weakens the claim}"
+- ⚠ [[Note D]]: "{quote showing uncertainty or alternative view}"
+
+## Position Changes Over Time
+- {date}: [[Note E]] said X
+- {date}: [[Note F]] said Y (contradicts X)
+
+## Weak Points
+1. **{Weak point}**: {why it's weak, which note shows it}
+2. **{Weak point}**: {why it's weak, which note shows it}
+
+## Overall Assessment
+**Evidence strength**: {Strong / Moderate / Weak / Unknown}
+
+{2-3 sentence summary: what the vault evidence suggests about this claim, what's uncertain, and what would strengthen or weaken the case further}
+```
+
+## Key Principles
+
+- **Respectful opposition.** The goal is to strengthen thinking, not to tear it down. Frame challenges as "here's what to consider" not "you're wrong."
+- **Evidence only.** Every challenge must cite specific vault notes. Don't invent external counterarguments.
+- **Surface uncertainty.** If the vault shows doubt or hesitation about aspects the claim treats as certain, highlight this gap.
+- **Obsidian is first workbench.** All note operations go through Obsidian CLI.