claude-code-arcane 1.0.0

package/skills/board-meeting/references/meeting-facilitation.md

@@ -0,0 +1,167 @@
+# Meeting Facilitation Guide
+
+Operational playbook for running board meetings using the 6-phase protocol.
+Reference this when things go sideways — and they will.
+
+---
+
+## Keeping Phase 2 Contributions Focused
+
+**The problem:** Agents with deep domain knowledge tend to over-contribute. An unconstrained CFO can produce 1,500 words on a single agenda item. This kills the meeting.
+
+**The rules:**
+- **Hard cap: 5 key points per role.** If a role produces more than 5, Chief of Staff trims to the 5 most material.
+- **Every point must include a recommendation or stance.** Observations without positions are filler.
+- **No hedging language.** "It depends" is not a key point. "We should do X if Y, Z if not Y" is.
+- **Confidence rating required.** Forces the agent to be honest about what they actually know.
+- **"What would change my mind"** — this is the most important line in the contribution. It forces falsifiability.
+
+**How to enforce:**
+```
+Chief of Staff instruction to each role:
+"You have 5 key points maximum. Each must include a clear stance.
+End with your recommendation and what would change your mind.
+Do not read other agents' contributions before writing yours."
+```
+
+**If a contribution runs long:**
+- Trim to the 5 highest-signal points
+- Preserve the recommendation and confidence rating
+- Flag in the raw transcript: "[Trimmed for meeting — full version in raw log]"
+
+---
+
+## Handling Role Conflicts in Phase 3
+
+**What the Executive Mentor is for:** Not harmony. Not consensus. Productive friction.
+
+**Common conflict types:**
+
+### 1. Data conflict (two agents cite contradictory numbers)
+- Flag both numbers explicitly
+- Do NOT pick a winner — that's the founder's job
+- Ask: "CFO says CAC is $2,400. CRO says $1,800. These can't both be right. Which dataset are you using?"
+- Action item: Assign data reconciliation to one owner before next meeting
+
+### 2. Priority conflict (two agents want different things first)
+- Surface the underlying assumption difference
+- Example: "CMO wants to invest in brand. CFO wants to cut burn. The real question is: do we believe revenue will grow 40% next quarter?"
+- Frame as a bet, not a fight
+
+### 3. Role conflict (agent operating outside their lane)
+- CFO making product calls → flag and exclude from synthesis
+- CMO commenting on architecture → flag and exclude
+- The Executive Mentor notes: "[ROLE] contribution on [topic] is outside domain. Excluded from synthesis. Refer to [correct role]."
+- This is not an error. It's expected. Executives have opinions on everything. Only domain-relevant contributions count.
+
+### 4. False consensus (everyone agrees but nobody has evidence)
+- This is the most dangerous failure mode
+- Symptom: All Phase 2 contributions say "yes" with high confidence
+- Executive Mentor response: "Unanimous agreement on a hard question is a red flag. What evidence does each of you have? Or are you reasoning from the same assumption?"
+- Force each agreeing agent to state their independent evidence
+
+---
+
+## When to Extend vs Cut Short a Meeting
+
+**Extend when:**
+- A genuine new risk surfaces in Phase 3 that wasn't in the agenda
+- The founder asks a question that requires re-running Phase 2 for a new angle
+- A data conflict is discovered that changes the decision space entirely
+- The action items from synthesis are unclear or unowned
+
+**How to extend:** Add a new mini-Phase 2 with only the relevant roles for the new question. Don't restart the full meeting.
+
+**Cut short when:**
+- The founder has already reached a decision before Phase 4 — capture it, log it, move on
+- The agenda item is resolved in Phase 2 without genuine conflict — skip Phase 3, go straight to synthesis
+- It's a pure update meeting with no decisions required — skip Phases 2-4, go straight to action items
+
+**Never cut short:**
+- Phase 5 (founder review) — always required, always explicit
+- Phase 6 (decision extraction) — always required, even for small decisions
+
+---
+
+## Handling Founder Disagreement with All Agents
+
+This happens. The founder has context agents don't.
+
+**Protocol:**
+1. Acknowledge explicitly: "You're overriding the consensus position."
+2. Ask: "What do you know that the agents didn't factor in?" (Not to challenge — to capture.)
+3. Log the override in Layer 2 with full context:
+   ```
+   User Override: Founder rejected [consensus position] because [reason].
+   Decision: [founder's actual decision]
+   Agent recommendation: [what they said] — DO NOT RESURFACE without new data
+   ```
+4. Never push back on a founder override. Document it. Move on.
+5. If the same override happens 3+ times, flag a pattern: "You've overridden the CFO on burn rate three meetings in a row. Would you like to update the financial constraints in company-context.md?"
+
+**What NOT to do:**
+- Don't say "but the CFO said..."
+- Don't re-argue on behalf of any agent
+- Don't note it as a "controversial" decision in the minutes — it's just the decision
+
+---
+
+## Common Failure Modes
+
+### Groupthink
+**Symptom:** All agents produce similar recommendations with high confidence.
+**Cause:** Agents are inadvertently reading each other's outputs (Phase 2 isolation violated), or company-context.md contains implicit bias toward one direction.
+**Fix:** Re-run Phase 2 with explicit isolation. Ask: "Give me the strongest argument AGAINST this direction."
+
+### Analysis Paralysis
+**Symptom:** Phase 2 produces comprehensive analysis but no clear recommendation from any role.
+**Cause:** Agents are hedging. Usually happens on genuinely hard questions.
+**Fix:** Force the issue. "I need a recommendation, not an analysis. If you had to bet the company on one direction, what would it be? Confidence can be Low."
+
+### Bikeshedding
+**Symptom:** 30+ minutes spent on a detail that doesn't matter to the core decision.
+**Cause:** An easy-to-understand sub-problem attracts disproportionate attention.
+**Example:** Debating button color on a pricing page instead of the pricing strategy.
+**Fix:** Chief of Staff intervenes: "This is a sub-decision. I'm logging it as a separate action item for async resolution. Back to [main agenda item]."
+
+### Scope Creep
+**Symptom:** New agenda items keep appearing mid-meeting.
+**Cause:** Meeting surfaces real issues that feel urgent.
+**Fix:** New items go on a "parking lot" list. Addressed after the current agenda is complete or in the next meeting.
+```
+🅿️ PARKING LOT
+- [Item 1] — added by [role], will address [when]
+- [Item 2]
+```
+
+### Layer Contamination
+**Symptom:** Future meeting references a rejected proposal or a debate that was never approved.
+**Cause:** Phase 1 accidentally loaded a raw transcript instead of decisions.md.
+**Fix:** Hard rule in Phase 1: load decisions.md (Layer 2) ONLY. Never load raw transcripts. If raw context is needed, founder explicitly requests it.
+
+### Decision Amnesia
+**Symptom:** Same question debated again in a later meeting.
+**Cause:** Layer 2 decisions.md not consulted in Phase 1, or entry was too vague.
+**Fix:** Phase 1 always surfaces relevant past decisions. If a question was already decided, Chief of Staff surfaces it: "We addressed this on [DATE]. Decision was [X]. Do you want to reopen it?"
+
+### Role Fatigue
+**Symptom:** Later agents in Phase 2 (CHRO, CRO) produce weaker contributions.
+**Cause:** Context window pressure. Agents at the end of a long meeting have less capacity.
+**Fix:** For meetings with 7+ roles, split into two batches. First batch: strategic roles (CEO, CFO, CMO). Second batch: operational roles (COO, CHRO, CRO). Run Executive Mentor after all contributions.
+
+---
+
+## Meeting Health Metrics
+
+After each board meeting, score it:
+
+| Metric | Good | Bad |
+|--------|------|-----|
+| Action items produced | 3–7 | 0 or >10 |
+| Decisions with clear owners | 100% | < 80% |
+| Unresolved open questions | 1–3 | >5 |
+| Founder overrides | 0–2 | >5 (suggests context mismatch) |
+| Roles activated | 3–6 | All 9 (too many = noise) |
+| Phase 2 conflicts surfaced | At least 1 | 0 (groupthink risk) |
+
+Track these in `memory/board-meetings/meeting-health.md` over time. Pattern: if action items consistently exceed 8, meetings are too infrequent. If conflicts are consistently 0, isolation is broken.

package/skills/board-meeting/templates/meeting-agenda.md

@@ -0,0 +1,81 @@
+# Board Meeting Agenda Template
+
+Use this to structure a board meeting before invoking `/cs:board`.
+Paste it into the conversation or save it as `memory/board-meetings/agenda-YYYY-MM-DD.md`.
+
+---
+
+## Board Meeting — [DATE]
+
+**Convened by:** [Founder name]
+**Facilitator:** Chief of Staff (Leo)
+**Duration:** [estimated, e.g., 45–90 min]
+**Status:** Draft / Confirmed
+
+---
+
+## Standing Items (always included)
+
+| Item | Owner | Time |
+|------|-------|------|
+| Layer 2 decisions review (what changed since last meeting) | Chief of Staff | 5 min |
+| Open action items from last meeting | All | 10 min |
+| Blockers requiring founder decision | All | 5 min |
+
+---
+
+## Agenda Items
+
+### Item 1: [Title]
+**Type:** Decision required / Exploration / Update
+**Lead role(s):** [e.g., CEO + CFO]
+**Context:** [1-2 sentences on why this is on the agenda now]
+**Decision needed:** [What specifically must be decided, or what question must be answered]
+**Success criteria:** [How will we know this agenda item is resolved?]
+**Relevant past decisions:** [Reference any Layer 2 entries]
+**Time box:** [e.g., 20 min]
+
+---
+
+### Item 2: [Title]
+**Type:** Decision required / Exploration / Update
+**Lead role(s):**
+**Context:**
+**Decision needed:**
+**Success criteria:**
+**Relevant past decisions:**
+**Time box:**
+
+---
+
+### Item 3: [Title]
+**Type:** Decision required / Exploration / Update
+**Lead role(s):**
+**Context:**
+**Decision needed:**
+**Success criteria:**
+**Relevant past decisions:**
+**Time box:**
+
+---
+
+## Out of Scope (explicitly excluded)
+
+List topics that might come up but are NOT on today's agenda:
+- [Topic] — defer to [date or next meeting]
+- [Topic] — owner to handle async
+
+---
+
+## Pre-Read
+
+Materials all participants should review before the meeting:
+- [ ] `memory/board-meetings/decisions.md` (Chief of Staff loads automatically)
+- [ ] [Link or filename]
+- [ ] [Link or filename]
+
+---
+
+## Notes
+
+[Any special instructions, constraints, or context for this meeting]

package/skills/board-meeting/templates/meeting-minutes.md

@@ -0,0 +1,91 @@
+# Board Meeting Minutes Template
+
+This is the Layer 2 output — the founder-approved record of what was decided.
+Written by Chief of Staff after Phase 5 (founder approval).
+Appended to `memory/board-meetings/decisions.md`.
+
+Do NOT include raw agent debate here. That lives in `YYYY-MM-DD-raw.md` (Layer 1).
+
+---
+
+## Board Meeting — [DATE]
+
+**Agenda:** [Topic or meeting title]
+**Participants (roles activated):** [e.g., CEO, CFO, CMO, COO, Executive Mentor]
+**Facilitator:** Chief of Staff
+**Status:** ✅ Approved by founder / ⏸️ Pending review
+
+---
+
+## Decisions Made
+
+### Decision 1: [Title]
+**Agenda item:** [Item this decision resolves]
+**Decision:** [Exactly what was decided — one clear statement]
+**Rationale:** [Why this was chosen over alternatives, in 1-3 sentences]
+**Owner:** [Who is accountable for execution]
+**Deadline:** [Date]
+**Review date:** [When to check progress]
+**User override:** [If founder overrode agent consensus — what and why. Leave blank if not applicable.]
+
+---
+
+### Decision 2: [Title]
+**Agenda item:**
+**Decision:**
+**Rationale:**
+**Owner:**
+**Deadline:**
+**Review date:**
+**User override:**
+
+---
+
+## Action Items
+
+| # | Action | Owner | Deadline | Review Date | Status |
+|---|--------|-------|----------|-------------|--------|
+| 1 | [action] | [name/role] | [date] | [date] | Open |
+| 2 | [action] | [name/role] | [date] | [date] | Open |
+| 3 | [action] | [name/role] | [date] | [date] | Open |
+
+---
+
+## Explicitly Rejected Proposals
+
+These were considered and rejected. Do not resurface without new information.
+
+| Proposal | Rejected by | Reason | Flag |
+|----------|-------------|--------|------|
+| [Proposal text] | Founder | [reason] | [DO_NOT_RESURFACE] |
+| [Proposal text] | Consensus | [reason] | [DO_NOT_RESURFACE] |
+
+---
+
+## Open Questions (unresolved, deferred)
+
+These were not resolved in this meeting. They carry forward.
+
+1. [Question] — Owner: [who will research] — Due: [date]
+2. [Question] — Owner: — Due:
+
+---
+
+## Risk Register Updates
+
+| Risk | Probability | Impact | Owner | Mitigation | Status |
+|------|-------------|--------|-------|-----------|--------|
+| [risk] | H/M/L | H/M/L | [name] | [action] | Open |
+
+---
+
+## Next Meeting
+
+**Suggested date:** [DATE]
+**Trigger items:** [Action items with review dates that will need board discussion]
+**Pre-read:** [What to prepare]
+
+---
+
+*Minutes approved by: [Founder name] on [DATE]*
+*Raw transcript: `memory/board-meetings/[DATE]-raw.md`*

package/skills/brainstorm/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: brainstorm
+description: "Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration."
+category: "workflow"
+argument-hint: "[genre or theme hint, or 'open'] [--review full|lean|solo]"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Write, WebSearch, Task, AskUserQuestion
+---
+
+# Brainstorm — Game Concept Ideation
+
+## Setup
+
+1. Parse argument for genre/theme hint (`roguelike`, `space survival`, `open`). Resolve review mode: `--review` flag → `production/review-mode.txt` → default `lean`. See `.claude/docs/director-gates.md`.
+2. Check existing work: `design/gdd/game-concept.md` (resume), `design/gdd/game-pillars.md` (build on).
+3. Run phases **interactively** — collaborative exploration, not silent generation. Use `AskUserQuestion` at key decision points.
+
+Studio principles: withhold judgment, encourage unusual ideas, "yes and...", constraints as creative fuel, time-box phases.
+
+### Phase 1: Creative Discovery
+
+**Emotional anchors** (plain text, not constrained): moment in a game that moved/thrilled you, fantasy never quite found.
+
+**Taste profile**: 3 most-played games (plain text — no preset options), genres loved/avoided.
+
+**Practical constraints** (single multi-tab `AskUserQuestion`):
+- Tab "Experience": Challenge & Mastery / Story & Discovery / Expression & Creativity / Relaxation & Flow
+- Tab "Timeline": Weeks / Months / 1-2 years / Multi-year
+- Tab "Dev level": First game / Shipped before / Professional background
+
+Synthesize into **Creative Brief** (3-5 sentences: emotional goals, taste, constraints). Read back and confirm.
+
+### Phase 2: Concept Generation
+
+Generate **3 concepts** using ideation techniques:
+
+| Technique | Approach |
+|-----------|----------|
+| Verb-First | Core player verb (build/fight/explore/solve) → build outward |
+| Mashup | Genre A + Theme B tension creates unique hook |
+| MDA Backward | Target emotion → dynamics → mechanics |
+
+Per concept present: Working Title, Elevator Pitch (1-2 sentences), Core Verb, Core Fantasy, Unique Hook ("Like X, AND ALSO Y"), Primary MDA Aesthetic, Estimated Scope, Why It Could Work, Biggest Risk.
+
+Present all three → `AskUserQuestion` plain list (NO tabs): pick one, combine, or fresh directions.
+
+### Phase 3: Core Loop Design
+
+For chosen concept, structured questioning:
+
+| Loop | Focus |
+|------|-------|
+| **30-second** | Core action feel (AskUserQuestion with concept-derived options), key design dimension |
+| **5-minute** | What structures cycles, "one more turn" psychology, choices |
+| **Session** (30-120 min) | Complete session shape, stopping points, between-session hook |
+| **Progression** (days/weeks) | Growth type (power/knowledge/options/story), long-term goal, "done" condition |
+
+**Player motivation (SDT):** autonomy (meaningful choice), competence (skill growth), relatedness (connection).
+
+### Phase 4: Pillars and Boundaries
+
+Define **3-5 pillars**: name + one-sentence definition + design test ("If debating X vs Y, this pillar says choose __"). Pillars should create tension with each other.
+
+**3+ anti-pillars**: "We will NOT do [thing] because it would compromise [pillar]."
+
+Pillar confirmation via `AskUserQuestion` → iterate until user selects "Lock these in."
+
+> → Read references/review-mode-gates.md for review mode gate details (Phase 4 + Phase 6)
+
+### Phase 5: Player Type Validation
+
+Using Bartle taxonomy + Quantic Foundry: primary player type, secondary appeal, who this is NOT for, market validation (successful games serving similar type).
+
+### Phase 6: Scope and Feasibility
+
+- **Platform**: AskUserQuestion (PC / Mobile / Console / Web / Multiple)
+- **Engine**: AskUserQuestion (Unity / Unreal / No preference → suggest `/setup-engine` later). Don't second-guess if they pick one.
+- **Art pipeline, content scope, MVP definition, biggest risks, scope tiers**
+
+## Document Generation
+
+Generate game concept using template at `.claude/docs/templates/game-concept.md`. Include Visual Identity Anchor section. Scope consistency rule: Estimated Scope must match full-vision timeline.
+
+AskUserQuestion for write approval → if "revise" → iterate until approved → write to `design/gdd/game-concept.md`.
+
+## Next Steps
+
+> → Read references/next-steps-pipeline.md for the full 11-step pipeline after concept creation
+
+## Context Window
+
+If context ≥70%: note that `design/gdd/game-concept.md` is saved, suggest fresh session.
+
+Verdict: **COMPLETE** — game concept created and handed off.

package/skills/brainstorm/references/next-steps-pipeline.md

@@ -0,0 +1,13 @@
+# Next Steps — Full Pipeline
+
+1. `/setup-engine` — configure engine + reference docs
+2. `/art-bible` — visual identity (BEFORE GDDs)
+3. `/design-review design/gdd/game-concept.md` — validate completeness
+4. `/map-systems` — decompose into systems with dependencies
+5. `/design-system` — per-system GDDs
+6. `/create-architecture` — master architecture blueprint + ADR list
+7. `/architecture-decision` (xN) — one ADR per decision
+8. `/gate-check` — phase gate before production
+9. `/prototype [core-mechanic]` — validate core loop
+10. `/playtest-report` — validate hypothesis
+11. `/sprint-plan new` — first sprint

package/skills/brainstorm/references/review-mode-gates.md

@@ -0,0 +1,13 @@
+# Review Mode Gates
+
+## Phase 4 Gates (Pillars)
+
+- `solo` / `lean` → skip CD-PILLARS and AD-CONCEPT-VISUAL, note skipped
+- `full` → spawn both `creative-director` (CD-PILLARS gate) and `art-director` (AD-CONCEPT-VISUAL gate) in parallel via Task. Present verdicts together in two-tab AskUserQuestion (Pillars + Visual anchor). User's visual anchor selection → stored as Visual Identity Anchor.
+
+If CD returns CONCERNS/REJECT on pillars → resolve before visual anchor selection.
+
+## Phase 6 Gates (Scope)
+
+- `solo` / `lean` → skip TD-FEASIBILITY and PR-SCOPE
+- `full` → spawn `technical-director` (TD-FEASIBILITY) after tech risks identified, then `producer` (PR-SCOPE) after scope tiers defined. Present assessments, offer adjustments if HIGH RISK/UNREALISTIC.

package/skills/brand-guidelines/SKILL.md

@@ -0,0 +1,91 @@
+---
+name: brand-guidelines
+description: "Apply, document, and enforce brand guidelines — color systems, typography, logo rules, imagery, and tone matrix for any brand."
+argument-hint: ""
+category: "marketing-strategy"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Bash
+---
+
+# Brand Guidelines
+
+You are an expert in brand identity and visual design standards. Your goal is to help teams apply brand guidelines consistently across all marketing materials, products, and communications — whether working with an established brand system or building one from scratch.
+
+## How to Use This Skill
+
+**Check for product marketing context first:**
+If `.claude/product-marketing-context.md` exists, read it before applying brand standards. Use that context to tailor recommendations to the specific brand.
+
+When helping users:
+1. Identify whether they need to *apply* existing guidelines or *create* new ones
+2. For Anthropic artifacts, use the Anthropic identity system below
+3. For other brands, use the framework sections to assess and document their system
+4. Always check for consistency before creativity
+
+---
+
+## Anthropic Brand Identity
+→ See references/brand-identity-and-framework.md for details
+
+## Quick Audit Checklist
+
+Use this to rapidly assess brand consistency across any asset:
+
+- [ ] Colors match approved palette (no off-brand variations)
+- [ ] Fonts are correct typeface and weight
+- [ ] Logo has proper clear space and is an approved variation
+- [ ] Body text meets minimum size and contrast requirements
+- [ ] Imagery style matches brand guidelines
+- [ ] Tone matches brand voice attributes
+- [ ] No prohibited uses present (gradients on logo, wrong accent color, etc.)
+- [ ] Co-branding (if any) follows partner logo rules
+
+---
+
+## Task-Specific Questions
+
+1. Are you applying existing guidelines or creating new ones?
+2. What's the output format? (Digital, print, presentation, social)
+3. Do you have existing brand assets? (Logo files, color codes, fonts)
+4. Is there a brand foundation document? (Mission, values, positioning)
+5. What's the specific inconsistency or gap you're trying to fix?
+
+---
+
+## Proactive Triggers
+
+Proactively apply brand guidelines when:
+
+1. **Any visual asset requested** — Before creating any poster, slide, email, or social graphic, check if brand guidelines exist; if not, offer to establish a minimal system first.
+2. **Copy review touches tone** — When reviewing copy, cross-check against voice attributes and tone matrix, not just grammar.
+3. **New channel launch** — When a new marketing channel (TikTok, newsletter, podcast) is being set up, offer to apply the brand guidelines to that channel's specific format requirements.
+4. **Design feedback session** — When a user shares a design for feedback, run through the quick audit checklist before giving subjective opinions.
+5. **Partner or co-branded material** — Any co-branding situation should immediately trigger a review of logo clear space, sizing ratios, and color dominance rules.
+
+---
+
+## Output Artifacts
+
+| Artifact | Format | Description |
+|----------|--------|-------------|
+| Brand Audit Report | Markdown doc | Asset-by-asset compliance check against all brand dimensions |
+| Color System Reference | Table | Full palette with hex, RGB, CMYK, Pantone, and usage rules |
+| Tone Matrix | Table | Voice attributes × context combinations with example phrases |
+| Typography Scale | Table | All type roles with font, size, weight, and line-height specifications |
+| Brand Guidelines Mini-Doc | Markdown doc | Condensed brand guide covering all 7 dimensions, ready to share with contractors |
+
+---
+
+## Communication
+
+Brand consistency is not a design preference — it's a trust signal. Every deviation from guidelines erodes recognition. When auditing or creating brand materials, be specific: name the exact color code, font weight, and pixel measurement rather than giving subjective feedback. Reference `marketing-context` to ensure brand voice recommendations align with the ICP and product positioning. Quality bar: brand outputs should be specific enough that a contractor who has never worked with the brand could produce on-brand work from the artifact alone.
+
+---
+
+## Related Skills
+
+- **marketing-context** — USE as the brand foundation layer; brand voice and visual decisions must align with ICP, positioning, and messaging; always load first.
+- **copywriting** — USE when brand voice guidelines need to be applied to specific page or campaign copy; NOT as a substitute for defining voice attributes.
+- **content-humanizer** — USE when existing content needs to be rewritten to match brand tone without losing information; NOT for structural content work.
+- **social-content** — USE when applying brand guidelines to social-specific formats and platform constraints; NOT for cross-channel brand system design.
+- **canvas-design** — USE when brand guidelines need to be applied to visual design artifacts (posters, PDFs, graphics); NOT for copy-only brand work.