studiograph 1.3.46 → 1.3.48-beta.0

package/dist/agent/skills/interview/entity-templates.md

@@ -0,0 +1,193 @@
+---
+name: interview/entity-templates
+description: Patterns for extracting structured entities from conversational interview answers and website content
+loading: on-demand
+---
+
+# Entity Extraction Patterns
+
+When the user gives a conversational answer, extract structured entities. These patterns show how to parse natural language into frontmatter fields and wikilinks.
+
+## General Rules
+
+1. **Use kebab-case for entity IDs** — lowercase, hyphens, no special characters: `alex-morgan`, `modern-museum`
+2. **Always set wikilinks** between related entities as you create them
+3. **Prefer the user's exact words** for names and descriptions — don't paraphrase or formalize
+4. **Never wrap content in quotes** — the `content` parameter is raw markdown, not a JSON string. Do not add leading or trailing `"` characters.
+4. **Don't over-extract** — if the user mentions something in passing, don't create an entity for it. Focus on the things they describe with enough detail to be useful.
+5. **Confirm before creating** when the answer is ambiguous — "I'll create entries for X, Y, and Z — sound right?"
+
+## People from Team Descriptions
+
+**User says:** "My team is myself, Jordan who's my business partner in New York, Sam our Director of Creative Technology also in New York, Casey who handles operations from South Carolina, and Taylor who's a mid-level designer here in Seattle with me."
+
+**Extract 5 person entities:**
+
+```yaml
+# alex-morgan.md
+entity_type: person
+name: Alex Morgan
+role: Founder & CEO
+status: current
+location: Seattle
+organization: "[[acme-studio]]"
+
+# jordan-lee.md
+entity_type: person
+name: Jordan Lee
+role: Business Partner
+status: current
+location: New York
+organization: "[[acme-studio]]"
+
+# sam-reyes.md
+entity_type: person
+name: Sam Reyes
+role: Director of Creative Technology
+status: current
+location: New York
+organization: "[[acme-studio]]"
+```
+
+**Key patterns:**
+- Map informal descriptions to `role` field ("handles operations" → "Associate Operations Director" only if the user used that title; otherwise keep it informal)
+- Set `status: current` for active team members
+- Always link to the organization entity
+
+## Projects from Workstream Lists
+
+**User says:** "We're launching the first phase of our Modern Museum collections website, working with Apex Systems on their dashboard UI, and about to start a new engagement with the Civic Initiative on an AI knowledge hub."
+
+**Extract 3 project entities + ensure client orgs exist:**
+
+```yaml
+# modern-museum-collections.md
+entity_type: project
+name: Modern Museum Collections Website
+category: Client Work
+client: "[[modern-museum]]"
+status: active
+
+# apex-systems-dashboard.md
+entity_type: project
+name: Apex Systems Dashboard UI
+category: Client Work
+client: "[[apex-systems]]"
+status: active
+
+# civic-knowledge-hub.md
+entity_type: project
+name: Civic AI Knowledge Hub
+category: Client Work
+client: "[[civic-initiative]]"
+status: active
+```
+
+**Key patterns:**
+- Derive entity IDs from the project name, not the client name
+- Always check if the client `organization` entity exists; create it if not
+- Map status language: "launching" → active, "about to start" → active, "on hold" → on-hold
+
+## Organizations from Client Mentions
+
+**User says:** "Our clients include Modern Museum, Apex Systems — which was co-founded by Pat Rivers and Robin Shaw — and Biomed Partners."
+
+**Extract 3 organization entities + 2 person entities for named contacts:**
+
+```yaml
+# modern-museum.md
+entity_type: organization
+name: Modern Museum of Design
+category: client
+status: active
+industry: Museums & Cultural Institutions
+
+# apex-systems.md
+entity_type: organization
+name: Apex Systems
+category: client
+status: active
+industry: AI / Enterprise Software
+
+# pat-rivers.md
+entity_type: person
+name: Pat Rivers
+role: Co-founder
+organization: "[[apex-systems]]"
+status: client
+```
+
+**Key patterns:**
+- Set `category: client` for client organizations
+- Only create person entities for contacts the user named specifically — don't infer unnamed contacts
+- Use the `status: client` on person entities for external contacts (vs `current` for team members)
+
+## Processes from Workflow Descriptions
+
+**User says:** "We have our Monday team meeting, a pipeline meeting Monday with Jordan and Casey, mid-week pipeline check-in Wednesday, and resourcing meeting Friday."
+
+**Extract 1 note (tagged `Process`) with structured body:**
+
+```yaml
+# weekly-cadence.md
+entity_type: note
+name: Weekly Team Cadence
+tags: [Process]
+owner: "[[alex-morgan]]"
+```
+
+Body:
+```markdown
+## Overview
+Weekly rhythm of standing meetings.
+
+## Steps
+- **Monday — Team Meeting** (full team): Align priorities, discuss deadlines and presentations
+- **Monday — Pipeline Meeting** ([[alex-morgan]], [[jordan-lee]], [[casey-brooks]]): Review new business pipeline, discuss follow-ups
+- **Wednesday — Pipeline Check-in**: Mid-week pipeline status
+- **Friday — Resourcing Meeting**: Plan next week's allocation, ensure billability
+```
+
+**Key patterns:**
+- Use wikilinks to people in the note body
+- Capture the cadence, not just the meetings — the pattern of how work flows
+- One note can capture multiple related meetings if they form a weekly rhythm
+
+## Website Content Extraction
+
+When the user provides a website URL, fetch it and extract:
+
+**From the About page:**
+- Organization description → `organization` entity body
+- Mission/vision statements → body content
+- Year founded, team size → frontmatter fields
+
+**From the Team page:**
+- Names, titles, locations → `person` entities
+- Bios → person entity body content
+- Photos → skip (not stored as entity data)
+
+**From the Portfolio/Work page:**
+- Project names, descriptions → `project` entities
+- Client names → `organization` entities (category: client)
+- Project categories → `category` field
+
+**From the Services page:**
+- Service areas → `practice-area` entities
+- Descriptions → practice-area entity body
+
+**Important:** Website content may be outdated. Always present extracted entities as confirmation questions: "From your site, I see you've worked with [clients] on projects like [projects]. Are these current?"
+
+## Handling Ambiguity
+
+**When the user is vague:**
+- "We work with some museums" → Don't create entities. Ask: "Which museums specifically?"
+
+**When names are incomplete:**
+- "My partner Jordan" → Create with what you have, follow up: "What's Jordan's last name and role?"
+
+**When relationships are unclear:**
+- "We're talking to a pharma company" → Don't create a deal yet. Ask: "Which company? Is this an active deal or early conversation?"
+
+**When multiple interpretations exist:**
+- "We're working on a dashboard" → Could be a project, could be Studiograph. Ask: "Is this a client project, or an internal tool?"

package/dist/agent/skills/interview/question-domains.md

@@ -0,0 +1,391 @@
+---
+name: interview/question-domains
+description: The 10-topic interview script with questions, follow-ups, and deepening patterns
+loading: on-demand
+---
+
+# Interview Script: 10 Topics
+
+Work through these topics in order. Ask one question at a time. Create entries immediately from each answer. Adapt phrasing if website context or prior answers already covered the topic.
+
+**Important:** Route entries to the correct folder (see skill.md Folder Structure). Create new folders as you reach the relevant topics. Never set optional fields to empty strings — omit them entirely if unknown.
+
+---
+
+## Pre-step: Website
+
+Before starting the script, ask:
+
+> "Before we begin — do you have a website for your organization? Sharing it helps me ask better questions."
+
+If provided:
+- Fetch with `web_fetch`
+- Extract: org description, team bios, project/portfolio entries, client logos/names, service areas
+- Use extracted context to turn open-ended questions into confirmations
+- If the site is sparse or doesn't exist, proceed with the script as-is
+
+---
+
+## Topic 1: Organization
+
+**Primary question:** "Tell me about your organization — what do you do, and how would you describe the firm?"
+
+**Follow-ups:**
+- "How big is the team?"
+- "Where are you based?"
+- "How long have you been operating?"
+
+**With website context:** "I see from your site that [description]. Is that accurate? What would you add or change?"
+
+**Folder:** Create the `{org-name}` folder (function graph type) first. This is the org's home folder.
+
+**Creates:** `organization` entry in the org folder with name, category, status, industry, website fields. This is the anchor entry — most other entries will link back to it. The body should include a substantive overview, philosophy/mission, and team roster.
+
+```yaml
+entity_type: organization
+entity_id: acme-studio
+name: Acme Studio
+status: active
+industry: Design & Technology
+website: https://example.com
+```
+
+**Sufficiently covered when:** Organization entry exists with name, a rich markdown body (overview, philosophy, services), and at least industry set.
+
+---
+
+## Topic 2: Team
+
+**Primary question:** "Who's on your team? Walk me through the key people, their roles, and where they're based."
+
+**Follow-ups:**
+- "Who do you work most closely with?"
+- "Anyone else — contractors, freelancers, key collaborators?"
+
+**With website context:** "I see [names] on your team page. Are they all current? What are their roles?"
+
+**Folder:** `{org-name}` (same as the org entry — team members live alongside the org).
+
+**Creates:** `person` entries linked to the organization via wikilinks. Each person entry should have a substantive body — not just "Role at Org, based in Location." Include what they do, what they're responsible for, who they work with. If the user only gave name + title, that's OK for now but the body should note what's known and flag gaps.
+
+```yaml
+entity_type: person
+entity_id: alex-morgan
+name: Alex Morgan
+role: Business Partner
+status: current
+location: New York
+organization: "[[acme-studio]]"
+```
+
+**Sufficiently covered when:** At least 2 person entries exist with roles, organization wikilinks, and meaningful body content.
+
+---
+
+## Topic 3: Clients
+
+**Primary question:** "Who are your current clients?"
+
+**Follow-ups:**
+- "Any key contacts at those organizations you work with regularly?"
+- "Are these ongoing relationships or project-based?"
+
+**With website context:** "Your portfolio mentions [clients]. Are those current? Anyone else?"
+
+**Folder:** Create the `clients` folder (function graph type) when you reach this topic.
+
+**Creates:** `organization` entries (category: client) in the `clients` folder, and optionally `person` entries for key contacts.
+
+```yaml
+# In clients folder:
+entity_type: organization
+entity_id: modern-museum
+name: Modern Museum of Design
+category: client
+status: active
+industry: Museums & Cultural Institutions
+```
+
+**Sufficiently covered when:** At least 1 client organization exists in the `clients` folder.
+
+---
+
+## Topic 4: Active Projects
+
+**Primary question:** "What are the active projects or workstreams right now?"
+
+**Follow-ups:**
+- "What's the status of each — launching, in progress, on hold?"
+- "Who's working on which projects?"
+
+**With website context:** "I see projects like [names] on your site. Which of these are current?"
+
+**Folder:** Create the `projects` folder (function graph type) when you reach this topic.
+
+**Creates:** `project` entries in the `projects` folder, linked to client organizations in `clients` and team members in the org folder.
+
+```yaml
+# In projects folder:
+entity_type: project
+entity_id: modern-museum-collections
+name: Modern Museum Collections Website
+category: Client Work
+project_type: Design
+client: "[[modern-museum]]"
+status: active
+```
+
+**Sufficiently covered when:** At least 1 project entry exists with a client wikilink and a meaningful body describing the work.
+
+---
+
+## Topic 5: Pipeline & Deals
+
+**Primary question:** "Any active deals or prospects in the pipeline?"
+
+**Follow-ups:**
+- "What stage are they at — early conversation, proposal, negotiation?"
+- "What's the expected timeline?"
+
+**Folder:** Create the `new-business` folder (function graph type) when you reach this topic. Prospect organizations also go here.
+
+**Creates:** prospect `organization` entries (category: prospect) and/or `note` entries describing individual deals, both in the `new-business` folder. (The `deal` type isn't agent-creatable in the launch set — capture the stage/status/value/timeline as fields in the prospect organization entry or as a note linked to it.)
+
+```yaml
+# In new-business folder:
+entity_type: note
+entity_id: civic-knowledge-hub
+name: Civic Knowledge Hub Engagement
+tags: [Pipeline, Deal]
+date: 2026-04-20
+client: "[[civic-initiative]]"
+stage: proposal
+status: active
+---
+Engagement overview, value, decision-makers, and next steps.
+```
+
+For prospect organizations, include why they're a target, what the angle would be, and any existing connections. Don't just repeat their tagline.
+
+**Sufficiently covered when:** At least 1 prospect organization or pipeline note exists, or user confirms there's nothing in the pipeline.
+
+---
+
+## Topic 6: Processes & Workflows
+
+**Primary question:** "How does your team work day to day — what's the meeting cadence, how do projects flow?"
+
+**Follow-ups:**
+- "Walk me through your typical week."
+- "How do decisions get made — is there a process, or is it more ad hoc?"
+
+**Creates:** `note` entries (tagged `Process`) or `document` entries describing recurring workflows. (The `process` type isn't agent-creatable in the launch set — put the steps in the body of a note/document.)
+
+```yaml
+entity_type: note
+entity_id: weekly-cadence
+name: Weekly Team Cadence
+tags: [Process]
+owner: "[[team-lead]]"
+---
+## Overview
+Weekly rhythm of meetings and check-ins.
+
+## Steps
+- Monday: Team meeting (full team) — align priorities, discuss deadlines
+- Monday: Pipeline meeting (leads) — review new business
+- Wednesday: Mid-week pipeline check-in
+- Friday: Resourcing meeting — plan next week, ensure billability
+
+## Best Practices
+- Keep meetings focused on decisions and blockers
+- Use async updates for status that doesn't need discussion
+```
+
+**Sufficiently covered when:** At least 1 process note or document exists.
+
+---
+
+## Topic 7: Tools & Systems
+
+**Primary question:** "What tools and systems does the team rely on?"
+
+**Follow-ups:**
+- "What do you use each tool for specifically?"
+- "Any internal tools or custom systems?"
+
+**Creates:** `note` entities tagged `tool`, or a single summary note.
+
+```yaml
+entity_type: note
+entity_id: tools-and-systems
+name: Tools & Systems
+tags: [Tool, Reference]
+---
+## Design
+- **Figma** — primary design tool, also used for AI-generated designs via Claude Code
+
+## Development
+- **Claude Code** — coding, prototyping, AI automation, Figma design generation
+
+## Project Management
+- **Asana** — project management and task tracking
+- **Streamtime** — time tracking and resourcing
+
+## Communication
+- **Slack** — team communication
+
+## Storage
+- **Google Drive** — file storage
+```
+
+**Sufficiently covered when:** At least 1 note about tools exists.
+
+---
+
+## Topic 8: Capabilities & Expertise
+
+**Primary question:** "What does your firm specialize in — what are you known for?"
+
+**Follow-ups:**
+- "What sets you apart from others in your space?"
+- "Any emerging areas you're moving into?"
+
+**Creates:** `note` entries describing each practice area, tagged `Core Capability`. (The `practice-area` type isn't agent-creatable in the launch set — use tagged notes.)
+
+```yaml
+entity_type: note
+entity_id: data-visualization
+name: Data Visualization
+tags: [Core Capability]
+---
+Core focus of the firm since founding. Creating interactive, designed encounters with data — not just static charts but full data experiences for museums, enterprises, and public platforms.
+```
+
+**Sufficiently covered when:** At least 1 capability note exists.
+
+---
+
+## Topic 9: Goals & Strategy
+
+**Primary question:** "What are your main goals right now — what does a good next six months look like?"
+
+**Follow-ups:**
+- "What's driving these priorities?"
+- "What would you consider a win vs. a setback?"
+
+**Creates:** `note` entity tagged `goals`.
+
+```yaml
+entity_type: note
+entity_id: goals-2026-h1
+name: Goals — 2026 H1
+tags: [Goals, Strategy]
+---
+## Primary Goals
+- Keep the team 80%+ billable
+- Shift focus toward AI product design (intelligent interfaces)
+- Publish AI case studies to reposition the firm
+- Sign new business aligned with AI direction
+
+## Success Criteria
+- Team is resourced and funded
+- Increasing share of work is AI-native UX
+- Schema is seen as an AI-focused creative technology firm
+```
+
+**Sufficiently covered when:** At least 1 goals note exists.
+
+---
+
+## Topic 10: Standards & Communication
+
+**Primary question:** "How do you communicate with clients and your team? Any guidelines or preferences the AI should know about?"
+
+**Follow-ups:**
+- "What does good writing sound like for your firm?"
+- "Anything that makes you cringe in AI-generated content?"
+
+**Creates:** `note` or `document` entries for general standards, and `skill` entries for repeatable patterns the agent should follow when doing specific jobs (proposal writing, meeting summaries, email style, etc.). See "Listening for Skill-Worthy Patterns" in the parent skill.md for when to offer a skill. (The `guideline` type isn't agent-creatable in the launch set — use note/document for guidelines and skill for agent-instruction patterns.)
+
+```yaml
+entity_type: note
+entity_id: communication-style
+name: Communication Style
+tags: [Communication, Standards]
+---
+## Overview
+Honest, authentic, to the point. Empathetic to client needs without being soft. Not too formal, not too casual. Relatively terse. Service-oriented.
+
+## Guidelines
+- Mirror how we speak on calls — conversational but professional
+- Focus on substance: understanding needs, solving problems, moving forward
+- Direct and concise — no padding with filler
+- AI writing must be indistinguishable from human writing
+
+## Examples
+### Do
+- Terse, substantive emails focused on next steps
+- Empathetic acknowledgment of client concerns without over-accommodating
+
+### Avoid
+- Robotic or formulaic phrasing
+- Overuse of em dashes
+- Neutral cadence that feels impersonal
+- Anything that reads as templated
+```
+
+**Sufficiently covered when:** At least 1 standards note/document exists (or a skill entry if the user described a concrete agent-instruction pattern).
+
+---
+
+# Deepening Patterns
+
+After all 10 topics have baseline coverage, use these patterns for re-entry bursts and reactive questions.
+
+## Sparse Entity Gaps
+
+Look for entities with minimal frontmatter or empty bodies:
+- "I see [project] doesn't list who's working on it — who's on that team?"
+- "[Person] has no role set — what's their title?"
+- "[Client] has no industry — what sector are they in?"
+
+## Missing Relationships
+
+Look for entities that should be connected but aren't:
+- "You have a project for [client] but they're not linked — should I connect them?"
+- "[Person] isn't linked to any projects — what are they working on?"
+- "No meeting entities yet — do you want to capture any recurring meetings?"
+
+## Stale Content
+
+Check timestamps and look for outdated information:
+- "Your goals note is from [date] — has anything shifted?"
+- "[Project] is marked active but was created [months ago] — is that still current?"
+- "Any new clients or deals since we last talked?"
+
+## New Graph Content
+
+When entities appear from connectors, manual entry, or imports:
+- "I see a new [type] entity called [name] — tell me more about it."
+- "A meeting with [client] was just added — any decisions or action items from that?"
+- "[Person] was added but has no role or organization — who are they?"
+
+## Cross-Folder Gaps
+
+Look across all folders for inconsistencies:
+- "You have a project for [client] but no deal entity — is there an active engagement?"
+- "[Person] is listed as a contact for [client] but doesn't appear in the people folder."
+- "Several projects reference a process that doesn't exist yet — should we capture it?"
+
+## Folder Evolution
+
+Projects start in a shared `projects` folder, which is the right default for small teams. As the graph matures, suggest promoting individual projects to their own folders when they accumulate enough related entities to warrant isolation:
+
+**When to suggest:** A project has 8+ related entries (meetings, decisions, deliverables, tasks, artifacts) across the graph, or when the user mentions needing per-project permissions (e.g., bringing on a contractor for one project).
+
+**How to suggest:** "Your [project] has grown to [N] related entries — meetings, decisions, deliverables. Would you like to give it its own folder? That makes it easier to organize and lets you control who has access."
+
+**What happens:** Create a new folder named after the project (e.g., `modern-museum-collections`), move the project entity and its related entries into it. Wikilinks across folders continue to work — entity IDs don't change.
+
+**Don't push this early.** A 5-person team with 5 projects doesn't need 5 separate folders. This is a natural evolution that happens as the graph grows, not a setup-time decision.