[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HPXQEDCA3B1PWQZPSP2FR8":3,"skill-same:01M6HPXQEDCA3B1PWQZPSP2FR8":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":77},"01M6HPXQEDCA3B1PWQZPSP2FR8","design-system",null,"Guided, section-by-section GDD authoring for a single game system. Gathers context from existing docs, walks through each required section collaboratively, cross-references dependencies, and writes incrementally to file.","welflau\u002Fai-dev-system","welflau","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7010385?v=4","01M6HPTDGF18RFY07M229P8CTM","01M6HPTDMRMZCJPYBFEA9XVVYT",3,"MIT","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fconfig_packs\u002Fgame-dev\u002Fshared\u002Fskills\u002Fdesign-system\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"design system","design","system","single","section","Existing","for","true","ComBat","name","authoring","dependencies","dialogue","task","references","context","edit","write","read","game","inventory","file","2026-11-10 10:12:30",false,"---\nname: design-system\ndescription: \"Guided, section-by-section GDD authoring for a single game system. Gathers context from existing docs, walks through each required section collaboratively, cross-references dependencies, and writes incrementally to file.\"\nargument-hint: \"\u003Csystem-name> (e.g., 'combat-system', 'inventory', 'dialogue')\"\nuser-invocable: true\nallowed-tools: Read, Glob, Grep, Write, Edit, Task, AskUserQuestion, TodoWrite\n---\n\nWhen this skill is invoked:\n\n## 1. Parse Arguments & Validate\n\nA system name argument is **required**. If missing, fail with:\n> \"Usage: `\u002Fdesign-system \u003Csystem-name>` — e.g., `\u002Fdesign-system combat-system`\n> Run `\u002Fmap-systems` first to create the systems index, then use this skill\n> to write individual system GDDs.\"\n\nNormalize the system name to kebab-case for the filename (e.g., \"combat system\"\nbecomes `combat-system`).\n\n---\n\n## 2. Gather Context (Read Phase)\n\nRead all relevant context **before** asking the user anything. This is the skill's\nprimary advantage over ad-hoc design — it arrives informed.\n\n### 2a: Required Reads\n\n- **Game concept**: Read `design\u002Fgdd\u002Fgame-concept.md` — fail if missing:\n  > \"No game concept found. Run `\u002Fbrainstorm` first.\"\n- **Systems index**: Read `design\u002Fgdd\u002Fsystems-index.md` — fail if missing:\n  > \"No systems index found. Run `\u002Fmap-systems` first to map your systems.\"\n- **Target system**: Find the system in the index. If not listed, warn:\n  > \"[system-name] is not in the systems index. Would you like to add it, or\n  > design it as an off-index system?\"\n\n### 2b: Dependency Reads\n\nFrom the systems index, identify:\n- **Upstream dependencies**: Systems this one depends on. Read their GDDs if they\n  exist (these contain decisions this system must respect).\n- **Downstream dependents**: Systems that depend on this one. Read their GDDs if\n  they exist (these contain expectations this system must satisfy).\n\nFor each dependency GDD that exists, extract and hold in context:\n- Key interfaces (what data flows between the systems)\n- Formulas that reference this system's outputs\n- Edge cases that assume this system's behavior\n- Tuning knobs that feed into this system\n\n### 2c: Optional Reads\n\n- **Game pillars**: Read `design\u002Fgdd\u002Fgame-pillars.md` if it exists\n- **Existing GDD**: Read `design\u002Fgdd\u002F[system-name].md` if it exists (resume, don't\n  restart from scratch)\n- **Related GDDs**: Glob `design\u002Fgdd\u002F*.md` and read any that are thematically related\n  (e.g., if designing \"status-effects\", also read \"combat-system\" even if it's not\n  a direct dependency)\n\n### 2d: Present Context Summary\n\nBefore starting design work, present a brief summary to the user:\n\n> **Designing: [System Name]**\n> - Priority: [from index] | Layer: [from index]\n> - Depends on: [list, noting which have GDDs vs. undesigned]\n> - Depended on by: [list, noting which have GDDs vs. undesigned]\n> - Existing decisions to respect: [key constraints from dependency GDDs]\n> - Pillar alignment: [which pillar(s) this system primarily serves]\n\nIf any upstream dependencies are undesigned, warn:\n> \"[dependency] doesn't have a GDD yet. We'll need to make assumptions about\n> its interface. Consider designing it first, or we can define the expected\n> contract and flag it as provisional.\"\n\nUse `AskUserQuestion`:\n- \"Ready to start designing [system-name]?\"\n  - Options: \"Yes, let's go\", \"Show me more context first\", \"Design a dependency first\"\n\n---\n\n## 3. Create File Skeleton\n\nOnce the user confirms, **immediately** create the GDD file with empty section\nheaders. This ensures incremental writes have a target.\n\nUse the template structure from `.claude\u002Fdocs\u002Ftemplates\u002Fgame-design-document.md`:\n\n```markdown\n# [System Name]\n\n> **Status**: In Design\n> **Author**: [user + agents]\n> **Last Updated**: [today's date]\n> **Implements Pillar**: [from context]\n\n## Overview\n\n[To be designed]\n\n## Player Fantasy\n\n[To be designed]\n\n## Detailed Design\n\n### Core Rules\n\n[To be designed]\n\n### States and Transitions\n\n[To be designed]\n\n### Interactions with Other Systems\n\n[To be designed]\n\n## Formulas\n\n[To be designed]\n\n## Edge Cases\n\n[To be designed]\n\n## Dependencies\n\n[To be designed]\n\n## Tuning Knobs\n\n[To be designed]\n\n## Visual\u002FAudio Requirements\n\n[To be designed]\n\n## UI Requirements\n\n[To be designed]\n\n## Acceptance Criteria\n\n[To be designed]\n\n## Open Questions\n\n[To be designed]\n```\n\nAsk: \"May I create the skeleton file at `design\u002Fgdd\u002F[system-name].md`?\"\n\nAfter writing, update `production\u002Fsession-state\u002Factive.md` with:\n- Task: Designing [system-name] GDD\n- Current section: Starting (skeleton created)\n- File: design\u002Fgdd\u002F[system-name].md\n\n---\n\n## 4. Section-by-Section Design\n\nWalk through each section in order. For **each section**, follow this cycle:\n\n### The Section Cycle\n\n```\nContext  ->  Questions  ->  Options  ->  Decision  ->  Draft  ->  Approval  ->  Write\n```\n\n1. **Context**: State what this section needs to contain, and surface any relevant\n   decisions from dependency GDDs that constrain it.\n\n2. **Questions**: Ask clarifying questions specific to this section. Use\n   `AskUserQuestion` for constrained questions, conversational text for open-ended\n   exploration.\n\n3. **Options**: Where the section involves design choices (not just documentation),\n   present 2-4 approaches with pros\u002Fcons. Explain reasoning in conversation text,\n   then use `AskUserQuestion` to capture the decision.\n\n4. **Decision**: User picks an approach or provides custom direction.\n\n5. **Draft**: Write the section content in conversation text for review. Flag any\n   provisional assumptions about undesigned dependencies.\n\n6. **Approval**: Ask \"Approve this section, or would you like changes?\"\n\n7. **Write**: Use the Edit tool to replace the `[To be designed]` placeholder with\n   the approved content. Confirm the write.\n\nAfter writing each section, update `production\u002Fsession-state\u002Factive.md` with the\ncompleted section name.\n\n### Section-Specific Guidance\n\nEach section has unique design considerations and may benefit from specialist agents:\n\n---\n\n### Section A: Overview\n\n**Goal**: One paragraph a stranger could read and understand.\n\n**Questions to ask**:\n- What is this system in one sentence?\n- How does a player interact with it? (active\u002Fpassive\u002Fautomatic)\n- Why does this system exist — what would the game lose without it?\n\n**Cross-reference**: Check that the description aligns with how the systems index\ndescribes it. Flag discrepancies.\n\n---\n\n### Section B: Player Fantasy\n\n**Goal**: The emotional target — what the player should *feel*.\n\n**Questions to ask**:\n- What emotion or power fantasy does this serve?\n- What reference games nail this feeling? What specifically creates it?\n- Is this a \"system you love engaging with\" or \"infrastructure you don't notice\"?\n\n**Cross-reference**: Must align with the game pillars. If the system serves a pillar,\nquote the relevant pillar text.\n\n---\n\n### Section C: Detailed Design (Core Rules, States, Interactions)\n\n**Goal**: Unambiguous specification a programmer could implement without questions.\n\nThis is usually the largest section. Break it into sub-sections:\n\n1. **Core Rules**: The fundamental mechanics. Use numbered rules for sequential\n   processes, bullets for properties.\n2. **States and Transitions**: If the system has states, map every state and\n   every valid transition. Use a table.\n3. **Interactions with Other Systems**: For each dependency (upstream and downstream),\n   specify what data flows in, what flows out, and who owns the interface.\n\n**Questions to ask**:\n- Walk me through a typical use of this system, step by step\n- What are the decision points the player faces?\n- What can the player NOT do? (Constraints are as important as capabilities)\n\n**Agent delegation**: For complex mechanics, use the Task tool to delegate to\n`game-designer` for high-level design review, or `systems-designer` for detailed\nmechanical modeling. Provide the full context gathered in Phase 2.\n\n**Cross-reference**: For each interaction listed, verify it matches what the\ndependency GDD specifies. If the dependency says \"damage is calculated as X\" and\nthis system expects something different, flag the conflict.\n\n---\n\n### Section D: Formulas\n\n**Goal**: Every mathematical formula, with variables defined, ranges specified,\nand edge cases noted.\n\n**Questions to ask**:\n- What are the core calculations this system performs?\n- Should scaling be linear, logarithmic, or stepped?\n- What should the output ranges be at early\u002Fmid\u002Flate game?\n\n**Agent delegation**: For formula-heavy systems (combat, economy, progression),\ndelegate to `systems-designer` via the Task tool. Provide:\n- The Core Rules from Section C (already written to file)\n- Tuning goals from the user\n- Balance context from dependency GDDs\n\nThe agent should return proposed formulas with variable tables and expected output\nranges. Present these to the user for review before approving.\n\n**Cross-reference**: If a dependency GDD defines a formula whose output feeds into\nthis system, reference it explicitly. Don't reinvent — connect.\n\n---\n\n### Section E: Edge Cases\n\n**Goal**: Explicitly handle unusual situations so they don't become bugs.\n\n**Questions to ask**:\n- What happens at zero? At maximum? At negative values?\n- What happens when two effects trigger simultaneously?\n- What happens if the player tries to exploit this? (Identify degenerate strategies)\n\n**Agent delegation**: For systems with complex interactions, delegate to\n`systems-designer` to identify edge cases from the formula space. For narrative\nsystems, consult `narrative-director` for story-breaking edge cases.\n\n**Cross-reference**: Check edge cases against dependency GDDs. If combat says\n\"damage cannot go below 1\" but this system can reduce damage to 0, that's a\nconflict to resolve.\n\n---\n\n### Section F: Dependencies\n\n**Goal**: Map every system connection with direction and nature.\n\nThis section is partially pre-filled from the context gathering phase. Present the\nknown dependencies from the systems index and ask:\n- Are there dependencies I'm missing?\n- For each dependency, what's the specific data interface?\n- Which dependencies are hard (system cannot function without it) vs. soft\n  (enhanced by it but works without it)?\n\n**Cross-reference**: This section must be bidirectionally consistent. If this system\nlists \"depends on Combat\", then the Combat GDD should list \"depended on by [this\nsystem]\". Flag any one-directional dependencies for correction.\n\n---\n\n### Section G: Tuning Knobs\n\n**Goal**: Every designer-adjustable value, with safe ranges and extreme behaviors.\n\n**Questions to ask**:\n- What values should designers be able to tweak without code changes?\n- For each knob, what breaks if it's set too high? Too low?\n- Which knobs interact with each other? (Changing A makes B irrelevant)\n\n**Agent delegation**: If formulas are complex, delegate to `systems-designer`\nto derive tuning knobs from the formula variables.\n\n**Cross-reference**: If a dependency GDD lists tuning knobs that affect this system,\nreference them here. Don't create duplicate knobs — point to the source of truth.\n\n---\n\n### Section H: Acceptance Criteria\n\n**Goal**: Testable conditions that prove the system works as designed.\n\n**Questions to ask**:\n- What's the minimum set of tests that prove this works?\n- What performance budget does this system get? (frame time, memory)\n- What would a QA tester check first?\n\n**Cross-reference**: Include criteria that verify cross-system interactions work,\nnot just this system in isolation.\n\n---\n\n### Optional Sections: Visual\u002FAudio, UI Requirements, Open Questions\n\nThese sections are included in the template but aren't part of the 8 required\nsections. Offer them after the required sections are done:\n\nUse `AskUserQuestion`:\n- \"The 8 required sections are complete. Do you want to also define Visual\u002FAudio\n  requirements, UI requirements, or capture open questions?\"\n  - Options: \"Yes, all three\", \"Just open questions\", \"Skip — I'll add these later\"\n\nFor **Visual\u002FAudio**: Coordinate with `art-director` and `audio-director` if detail\nis needed. Often a brief note suffices at the GDD stage.\n\nFor **UI Requirements**: Coordinate with `ux-designer` for complex UI systems.\n\nFor **Open Questions**: Capture anything that came up during design that wasn't\nfully resolved. Each question should have an owner and target resolution date.\n\n---\n\n## 5. Post-Design Validation\n\nAfter all sections are written:\n\n### 5a: Self-Check\n\nRead back the complete GDD from file (not from conversation memory — the file is\nthe source of truth). Verify:\n- All 8 required sections have real content (not placeholders)\n- Formulas reference defined variables\n- Edge cases have resolutions\n- Dependencies are listed with interfaces\n- Acceptance criteria are testable\n\n### 5b: Offer Design Review\n\nPresent a completion summary:\n\n> **GDD Complete: [System Name]**\n> - Sections written: [list]\n> - Provisional assumptions: [list any assumptions about undesigned dependencies]\n> - Cross-system conflicts found: [list or \"none\"]\n\nUse `AskUserQuestion`:\n- \"Run `\u002Fdesign-review` now to validate the GDD?\"\n  - Options: \"Yes, run review now\", \"I'll review it myself first\", \"Skip review\"\n\nIf yes, invoke the design-review skill on the completed file.\n\n### 5c: Update Systems Index\n\nAfter the GDD is complete (and optionally reviewed):\n\n- Read the systems index\n- Update the target system's row:\n  - If design-review was run and verdict is APPROVED: Status → \"Approved\"\n  - If design-review was run and verdict is NEEDS REVISION: Status → \"In Review\"\n  - If design-review was skipped: Status → \"Designed\" (pending review)\n  - If the user chose \"I'll review it myself first\": Status → \"Designed\"\n  - Design Doc: link to `design\u002Fgdd\u002F[system-name].md`\n- Update the Progress Tracker counts\n\nAsk: \"May I update the systems index at `design\u002Fgdd\u002Fsystems-index.md`?\"\n\n### 5d: Update Session State\n\nUpdate `production\u002Fsession-state\u002Factive.md` with:\n- Task: [system-name] GDD\n- Status: Complete (or In Review if design-review was run)\n- File: design\u002Fgdd\u002F[system-name].md\n- Sections: All 8 written\n- Next: [suggest next system from design order]\n\n### 5e: Suggest Next Steps\n\nUse `AskUserQuestion`:\n- \"What's next?\"\n  - Options:\n    - \"Design next system ([next-in-order])\" — if undesigned systems remain\n    - \"Fix review findings\" — if design-review flagged issues\n    - \"Stop here for this session\"\n    - \"Run `\u002Fgate-check`\" — if enough MVP systems are designed\n\n---\n\n## 6. Specialist Agent Routing\n\nThis skill delegates to specialist agents for domain expertise. The main session\norchestrates the overall flow; agents provide expert content.\n\n| System Category | Primary Agent | Supporting Agent(s) |\n|----------------|---------------|---------------------|\n| Combat, damage, health | `game-designer` | `systems-designer` (formulas), `ai-programmer` (enemy AI) |\n| Economy, loot, crafting | `economy-designer` | `systems-designer` (curves), `game-designer` (loops) |\n| Progression, XP, skills | `game-designer` | `systems-designer` (curves), `economy-designer` (sinks) |\n| Dialogue, quests, lore | `game-designer` | `narrative-director` (story), `writer` (content) |\n| UI systems (HUD, menus) | `game-designer` | `ux-designer` (flows), `ui-programmer` (feasibility) |\n| Audio systems | `game-designer` | `audio-director` (direction), `sound-designer` (specs) |\n| AI, pathfinding, behavior | `game-designer` | `ai-programmer` (implementation), `systems-designer` (scoring) |\n| Level\u002Fworld systems | `game-designer` | `level-designer` (spatial), `world-builder` (lore) |\n| Camera, input, controls | `game-designer` | `ux-designer` (feel), `gameplay-programmer` (feasibility) |\n\n**When delegating via Task tool**:\n- Provide: system name, game concept summary, dependency GDD excerpts, the specific\n  section being worked on, and what question needs expert input\n- The agent returns analysis\u002Fproposals to the main session\n- The main session presents the agent's output to the user via `AskUserQuestion`\n- The user decides; the main session writes to file\n- Agents do NOT write to files directly — the main session owns all file writes\n\n---\n\n## 7. Recovery & Resume\n\nIf the session is interrupted (compaction, crash, new session):\n\n1. Read `production\u002Fsession-state\u002Factive.md` — it records the current system and\n   which sections are complete\n2. Read `design\u002Fgdd\u002F[system-name].md` — sections with real content are done;\n   sections with `[To be designed]` still need work\n3. Resume from the next incomplete section — no need to re-discuss completed ones\n\nThis is why incremental writing matters: every approved section survives any\ndisruption.\n\n---\n\n## Collaborative Protocol\n\nThis skill follows the collaborative design principle at every step:\n\n1. **Question -> Options -> Decision -> Draft -> Approval** for every section\n2. **AskUserQuestion** at every decision point (Explain -> Capture pattern):\n   - Phase 2: \"Ready to start, or need more context?\"\n   - Phase 3: \"May I create the skeleton?\"\n   - Phase 4 (each section): Design questions, approach options, draft approval\n   - Phase 5: \"Run design review? Update systems index? What's next?\"\n3. **\"May I write to [filepath]?\"** before the skeleton and before each section write\n4. **Incremental writing**: Each section is written to file immediately after approval\n5. **Session state updates**: After every section write\n6. **Cross-referencing**: Every section checks existing GDDs for conflicts\n7. **Specialist routing**: Complex sections get expert agent input, presented to\n   the user for decision — never written silently\n\n**Never** auto-generate the full GDD and present it as a fait accompli.\n**Never** write a section without user approval.\n**Never** contradict an existing approved GDD without flagging the conflict.\n**Always** show where decisions come from (dependency GDDs, pillars, user choices).\n","When this skill is invoked:\n\n## 1. Parse Arguments & Validate\n\nA system name argument is **required**. If missing, fail with:\n> \"Usage: `\u002Fdesign-system \u003Csystem-name>` — e.g., `\u002Fdesign-system combat-system`\n> Run `\u002Fmap-systems` first to create the systems index, then use this skill\n> to write individual system GDDs.\"\n\nNormalize the system name to kebab-case for the filename (e.g., \"combat system\"\nbecomes `combat-system`).\n\n---\n\n## 2. Gather Context (Read Phase)\n\nRead all relevant context **before** asking the user anything. This is the skill's\nprimary advantage over ad-hoc design — it arrives informed.\n\n### 2a: Required Reads\n\n- **Game concept**: Read `design\u002Fgdd\u002Fgame-concept.md` — fail if missing:\n  > \"No game concept found. Run `\u002Fbrainstorm` first.\"\n- **Systems index**: Read `design\u002Fgdd\u002Fsystems-index.md` — fail if missing:\n  > \"No systems index found. Run `\u002Fmap-systems` first to map your systems.\"\n- **Target system**: Find the system in the index. If not listed, warn:\n  > \"[system-name] is not in the systems index. Would you like to add it, or\n  > design it as an off-index system?\"\n\n### 2b: Dependency Reads\n\nFrom the systems index, identify:\n- **Upstream dependencies**: Systems this one depends on. Read their GDDs if they\n  exist (these contain decisions this system must respect).\n- **Downstream dependents**: Systems that depend on this one. Read their GDDs if\n  they exist (these contain expectations this system must satisfy).\n\nFor each dependency GDD that exists, extract and hold in context:\n- Key interfaces (what data flows between the systems)\n- Formulas that reference this system's outputs\n- Edge cases that assume this system's behavior\n- Tuning knobs that feed into this system\n\n### 2c: Optional Reads\n\n- **Game pillars**: Read `design\u002Fgdd\u002Fgame-pillars.md` if it exists\n- **Existing GDD**: Read `design\u002Fgdd\u002F[system-name].md` if it exists (resume, don't\n  restart from scratch)\n- **Related GDDs**: Glob `design\u002Fgdd\u002F*.md` and read any that are thematically related\n  (e.g., if designing \"status-effects\", also read \"combat-system\" even if it's not\n  a direct dependency)\n\n### 2d: Present Context Summary\n\nBefore starting design work, present a brief summary to the user:\n\n> **Designing: [System Name]**\n> - Priority: [from index] | Layer: [from index]\n> - Depends on: [list, noting which have GDDs vs. undesigned]\n> - Depended on by: [list, noting which have GDDs vs. undesigned]\n> - Existing decisions to respect: [key constraints from dependency GDDs]\n> - Pillar alignment: [which pillar(s) this system primarily serves]\n\nIf any upstream dependencies are undesigned, warn:\n> \"[dependency] doesn't have a GDD yet. We'll need to make assumptions about\n> its interface. Consider designing it first, or we can define the expected\n> contract and flag it as provisional.\"\n\nUse `AskUserQuestion`:\n- \"Ready to start designing [system-name]?\"\n  - Options: \"Yes, let's go\", \"Show me more context first\", \"Design a dependency first\"\n\n---\n\n## 3. Create File Skeleton\n\nOnce the user confirms, **immediately** create the GDD file with empty section\nheaders. This ensures incremental writes have a target.\n\nUse the template structure from `.claude\u002Fdocs\u002Ftemplates\u002Fgame-design-document.md`:\n\n```markdown\n# [System Name]\n\n> **Status**: In Design\n> **Author**: [user + agents]\n> **Last Updated**: [today's date]\n> **Implements Pillar**: [from context]\n\n## Overview\n\n[To be designed]\n\n## Player Fantasy\n\n[To be designed]\n\n## Detailed Design\n\n### Core Rules\n\n[To be designed]\n\n### States and Transitions\n\n[To be designed]\n\n### Interactions with Other Systems\n\n[To be designed]\n\n## Formulas\n\n[To be designed]\n\n## Edge Cases\n\n[To be designed]\n\n## Dependencies\n\n[To be designed]\n\n## Tuning Knobs\n\n[To be designed]\n\n## Visual\u002FAudio Requirements\n\n[To be designed]\n\n## UI Requirements\n\n[To be designed]\n\n## Acceptance Criteria\n\n[To be designed]\n\n## Open Questions\n\n[To be designed]\n```\n\nAsk: \"May I create the skeleton file at `design\u002Fgdd\u002F[system-name].md`?\"\n\nAfter writing, update `production\u002Fsession-state\u002Factive.md` with:\n- Task: Designing [system-name] GDD\n- Current section: Starting (skeleton created)\n- File: design\u002Fgdd\u002F[system-name].md\n\n---\n\n## 4. Section-by-Section Design\n\nWalk through each section in order. For **each section**, follow this cycle:\n\n### The Section Cycle\n\n```\nContext  ->  Questions  ->  Options  ->  Decision  ->  Draft  ->  Approval  ->  Write\n```\n\n1. **Context**: State what this section needs to contain, and surface any relevant\n   decisions from dependency GDDs that constrain it.\n\n2. **Questions**: Ask clarifying questions specific to this section. Use\n   `AskUserQuestion` for constrained questions, conversational text for open-ended\n   exploration.\n\n3. **Options**: Where the section involves design choices (not just documentation),\n   present 2-4 approaches with pros\u002Fcons. Explain reasoning in conversation text,\n   then use `AskUserQuestion` to capture the decision.\n\n4. **Decision**: User picks an approach or provides custom direction.\n\n5. **Draft**: Write the section content in conversation text for review. Flag any\n   provisional assumptions about undesigned dependencies.\n\n6. **Approval**: Ask \"Approve this section, or would you like changes?\"\n\n7. **Write**: Use the Edit tool to replace the `[To be designed]` placeholder with\n   the approved content. Confirm the write.\n\nAfter writing each section, update `production\u002Fsession-state\u002Factive.md` with the\ncompleted section name.\n\n### Section-Specific Guidance\n\nEach section has unique design considerations and may benefit from specialist agents:\n\n---\n\n### Section A: Overview\n\n**Goal**: One paragraph a stranger could read and understand.\n\n**Questions to ask**:\n- What is this system in one sentence?\n- How does a player interact with it? (active\u002Fpassive\u002Fautomatic)\n- Why does this system exist — what would the game lose without it?\n\n**Cross-reference**: Check that the description aligns with how the systems index\ndescribes it. Flag discrepancies.\n\n---\n\n### Section B: Player Fantasy\n\n**Goal**: The emotional target — what the player should *feel*.\n\n**Questions to ask**:\n- What emotion or power fantasy does this serve?\n- What reference games nail this feeling? What specifically creates it?\n- Is this a \"system you love engaging with\" or \"infrastructure you don't notice\"?\n\n**Cross-reference**: Must align with the game pillars. If the system serves a pillar,\nquote the relevant pillar text.\n\n---\n\n### Section C: Detailed Design (Core Rules, States, Interactions)\n\n**Goal**: Unambiguous specification a programmer could implement without questions.\n\nThis is usually the largest section. Break it into sub-sections:\n\n1. **Core Rules**: The fundamental mechanics. Use numbered rules for sequential\n   processes, bullets for properties.\n2. **States and Transitions**: If the system has states, map every state and\n   every valid transition. Use a table.\n3. **Interactions with Other Systems**: For each dependency (upstream and downstream),\n   specify what data flows in, what flows out, and who owns the interface.\n\n**Questions to ask**:\n- Walk me through a typical use of this system, step by step\n- What are the decision points the player faces?\n- What can the player NOT do? (Constraints are as important as capabilities)\n\n**Agent delegation**: For complex mechanics, use the Task tool to delegate to\n`game-designer` for high-level design review, or `systems-designer` for detailed\nmechanical modeling. Provide the full context gathered in Phase 2.\n\n**Cross-reference**: For each interaction listed, verify it matches what the\ndependency GDD specifies. If the dependency says \"damage is calculated as X\" and\nthis system expects something different, flag the conflict.\n\n---\n\n### Section D: Formulas\n\n**Goal**: Every mathematical formula, with variables defined, ranges specified,\nand edge cases noted.\n\n**Questions to ask**:\n- What are the core calculations this system performs?\n- Should scaling be linear, logarithmic, or stepped?\n- What should the output ranges be at early\u002Fmid\u002Flate game?\n\n**Agent delegation**: For formula-heavy systems (combat, economy, progression),\ndelegate to `systems-designer` via the Task tool. Provide:\n- The Core Rules from Section C (already written to file)\n- Tuning goals from the user\n- Balance context from dependency GDDs\n\nThe agent should return proposed formulas with variable tables and expected output\nranges. Present these to the user for review before approving.\n\n**Cross-reference**: If a dependency GDD defines a formula whose output feeds into\nthis system, reference it explicitly. Don't reinvent — connect.\n\n---\n\n### Section E: Edge Cases\n\n**Goal**: Explicitly handle unusual situations so they don't become bugs.\n\n**Questions to ask**:\n- What happens at zero? At maximum? At negative values?\n- What happens when two effects trigger simultaneously?\n- What happens if the player tries to exploit this? (Identify degenerate strategies)\n\n**Agent delegation**: For systems with complex interactions, delegate to\n`systems-designer` to identify edge cases from the formula space. For narrative\nsystems, consult `narrative-director` for story-breaking edge cases.\n\n**Cross-reference**: Check edge cases against dependency GDDs. If combat says\n\"damage cannot go below 1\" but this system can reduce damage to 0, that's a\nconflict to resolve.\n\n---\n\n### Section F: Dependencies\n\n**Goal**: Map every system connection with direction and nature.\n\nThis section is partially pre-filled from the context gathering phase. Present the\nknown dependencies from the systems index and ask:\n- Are there dependencies I'm missing?\n- For each dependency, what's the specific data interface?\n- Which dependencies are hard (system cannot function without it) vs. soft\n  (enhanced by it but works without it)?\n\n**Cross-reference**: This section must be bidirectionally consistent. If this system\nlists \"depends on Combat\", then the Combat GDD should list \"depended on by [this\nsystem]\". Flag any one-directional dependencies for correction.\n\n---\n\n### Section G: Tuning Knobs\n\n**Goal**: Every designer-adjustable value, with safe ranges and extreme behaviors.\n\n**Questions to ask**:\n- What values should designers be able to tweak without code changes?\n- For each knob, what breaks if it's set too high? Too low?\n- Which knobs interact with each other? (Changing A makes B irrelevant)\n\n**Agent delegation**: If formulas are complex, delegate to `systems-designer`\nto derive tuning knobs from the formula variables.\n\n**Cross-reference**: If a dependency GDD lists tuning knobs that affect this system,\nreference them here. Don't create duplicate knobs — point to the source of truth.\n\n---\n\n### Section H: Acceptance Criteria\n\n**Goal**: Testable conditions that prove the system works as designed.\n\n**Questions to ask**:\n- What's the minimum set of tests that prove this works?\n- What performance budget does this system get? (frame time, memory)\n- What would a QA tester check first?\n\n**Cross-reference**: Include criteria that verify cross-system interactions work,\nnot just this system in isolation.\n\n---\n\n### Optional Sections: Visual\u002FAudio, UI Requirements, Open Questions\n\nThese sections are included in the template but aren't part of the 8 required\nsections. Offer them after the required sections are done:\n\nUse `AskUserQuestion`:\n- \"The 8 required sections are complete. Do you want to also define Visual\u002FAudio\n  requirements, UI requirements, or capture open questions?\"\n  - Options: \"Yes, all three\", \"Just open questions\", \"Skip — I'll add these later\"\n\nFor **Visual\u002FAudio**: Coordinate with `art-director` and `audio-director` if detail\nis needed. Often a brief note suffices at the GDD stage.\n\nFor **UI Requirements**: Coordinate with `ux-designer` for complex UI systems.\n\nFor **Open Questions**: Capture anything that came up during design that wasn't\nfully resolved. Each question should have an owner and target resolution date.\n\n---\n\n## 5. Post-Design Validation\n\nAfter all sections are written:\n\n### 5a: Self-Check\n\nRead back the complete GDD from file (not from conversation memory — the file is\nthe source of truth). Verify:\n- All 8 required sections have real content (not placeholders)\n- Formulas reference defined variables\n- Edge cases have resolutions\n- Dependencies are listed with interfaces\n- Acceptance criteria are testable\n\n### 5b: Offer Design Review\n\nPresent a completion summary:\n\n> **GDD Complete: [System Name]**\n> - Sections written: [list]\n> - Provisional assumptions: [list any assumptions about undesigned dependencies]\n> - Cross-system conflicts found: [list or \"none\"]\n\nUse `AskUserQuestion`:\n- \"Run `\u002Fdesign-review` now to validate the GDD?\"\n  - Options: \"Yes, run review now\", \"I'll review it myself first\", \"Skip review\"\n\nIf yes, invoke the design-review skill on the completed file.\n\n### 5c: Update Systems Index\n\nAfter the GDD is complete (and optionally reviewed):\n\n- Read the systems index\n- Update the target system's row:\n  - If design-review was run and verdict is APPROVED: Status → \"Approved\"\n  - If design-review was run and verdict is NEEDS REVISION: Status → \"In Review\"\n  - If design-review was skipped: Status → \"Designed\" (pending review)\n  - If the user chose \"I'll review it myself first\": Status → \"Designed\"\n  - Design Doc: link to `design\u002Fgdd\u002F[system-name].md`\n- Update the Progress Tracker counts\n\nAsk: \"May I update the systems index at `design\u002Fgdd\u002Fsystems-index.md`?\"\n\n### 5d: Update Session State\n\nUpdate `production\u002Fsession-state\u002Factive.md` with:\n- Task: [system-name] GDD\n- Status: Complete (or In Review if design-review was run)\n- File: design\u002Fgdd\u002F[system-name].md\n- Sections: All 8 written\n- Next: [suggest next system from design order]\n\n### 5e: Suggest Next Steps\n\nUse `AskUserQuestion`:\n- \"What's next?\"\n  - Options:\n    - \"Design next system ([next-in-order])\" — if undesigned systems remain\n    - \"Fix review findings\" — if design-review flagged issues\n    - \"Stop here for this session\"\n    - \"Run `\u002Fgate-check`\" — if enough MVP systems are designed\n\n---\n\n## 6. Specialist Agent Routing\n\nThis skill delegates to specialist agents for domain expertise. The main session\norchestrates the overall flow; agents provide expert content.\n\n| System Category | Primary Agent | Supporting Agent(s) |\n|----------------|---------------|---------------------|\n| Combat, damage, health | `game-designer` | `systems-designer` (formulas), `ai-programmer` (enemy AI) |\n| Economy, loot, crafting | `economy-designer` | `systems-designer` (curves), `game-designer` (loops) |\n| Progression, XP, skills | `game-designer` | `systems-designer` (curves), `economy-designer` (sinks) |\n| Dialogue, quests, lore | `game-designer` | `narrative-director` (story), `writer` (content) |\n| UI systems (HUD, menus) | `game-designer` | `ux-designer` (flows), `ui-programmer` (feasibility) |\n| Audio systems | `game-designer` | `audio-director` (direction), `sound-designer` (specs) |\n| AI, pathfinding, behavior | `game-designer` | `ai-programmer` (implementation), `systems-designer` (scoring) |\n| Level\u002Fworld systems | `game-designer` | `level-designer` (spatial), `world-builder` (lore) |\n| Camera, input, controls | `game-designer` | `ux-designer` (feel), `gameplay-programmer` (feasibility) |\n\n**When delegating via Task tool**:\n- Provide: system name, game concept summary, dependency GDD excerpts, the specific\n  section being worked on, and what question needs expert input\n- The agent returns analysis\u002Fproposals to the main session\n- The main session presents the agent's output to the user via `AskUserQuestion`\n- The user decides; the main session writes to file\n- Agents do NOT write to files directly — the main session owns all file writes\n\n---\n\n## 7. Recovery & Resume\n\nIf the session is interrupted (compaction, crash, new session):\n\n1. Read `production\u002Fsession-state\u002Factive.md` — it records the current system and\n   which sections are complete\n2. Read `design\u002Fgdd\u002F[system-name].md` — sections with real content are done;\n   sections with `[To be designed]` still need work\n3. Resume from the next incomplete section — no need to re-discuss completed ones\n\nThis is why incremental writing matters: every approved section survives any\ndisruption.\n\n---\n\n## Collaborative Protocol\n\nThis skill follows the collaborative design principle at every step:\n\n1. **Question -> Options -> Decision -> Draft -> Approval** for every section\n2. **AskUserQuestion** at every decision point (Explain -> Capture pattern):\n   - Phase 2: \"Ready to start, or need more context?\"\n   - Phase 3: \"May I create the skeleton?\"\n   - Phase 4 (each section): Design questions, approach options, draft approval\n   - Phase 5: \"Run design review? Update systems index? What's next?\"\n3. **\"May I write to [filepath]?\"** before the skeleton and before each section write\n4. **Incremental writing**: Each section is written to file immediately after approval\n5. **Session state updates**: After every section write\n6. **Cross-referencing**: Every section checks existing GDDs for conflicts\n7. **Specialist routing**: Complex sections get expert agent input, presented to\n   the user for decision — never written silently\n\n**Never** auto-generate the full GDD and present it as a fait accompli.\n**Never** write a section without user approval.\n**Never** contradict an existing approved GDD without flagging the conflict.\n**Always** show where decisions come from (dependency GDDs, pillars, user choices).\n",{"name":5,"description":7,"allowed-tools":55,"argument-hint":56,"user-invocable":57},"Read, Glob, Grep, Write, Edit, Task, AskUserQuestion, TodoWrite","\u003Csystem-name> (e.g., 'combat-system', 'inventory', 'dialogue')",true,"main","18d0e63d1313ca87098f614aa7c1e2dcf6de79c7","backend\u002Fconfig_packs\u002Fgame-dev\u002Fshared\u002Fskills\u002Fdesign-system",1,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system","https:\u002F\u002Fgithub.com\u002Fwelflau","2026-11-12 14:55:20",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":57},[67,70,73],{"tool":68,"command":69},"npx","npx skills add welflau\u002Fai-dev-system --skill design-system",{"tool":71,"command":72},"bunx","bunx skills add welflau\u002Fai-dev-system --skill design-system",{"tool":74,"command":75},"pnpm","pnpm dlx skills add welflau\u002Fai-dev-system --skill design-system","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fconfig_packs\u002Fgame-dev\u002Fshared\u002Fskills\u002Fdesign-system\u002FSKILL.md",[],[79,111,140,164,187,211],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":93,"publishedAt":110},"01M6HS9Z4B0YA8CJCS2Y2F04Y3","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Fwebapp-testing\u002FSKILL.md",[87,90],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":91,"categoryName":92,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,34],"testing","webapp testing","webapp","frontend","screenshots","playwright","web","debugging","toolkit","browser","ui","logs","applications","behavior","local","with","2026-11-11 15:11:14",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":110},"01M6HRAGMG7JF0HXYHMA5QHS8A","internal-comms","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Finternal-comms\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Finternal-comms\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通",[122,123,124,125,126,45,127,128,129,130,131,132,133,134,135,136,137,138,139],"internal comms","comms","status","help","SET","use","reports","me","incident","leadership","project","resources","communications","internal communications","formats","sort","my","updates",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":50},"01M6HSTDP4M3JFXEBK91VFB4PA","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fweb-artifacts-builder\u002FSKILL.md",[147],{"categoryNo":91,"categoryName":92,"taxonomyType":20,"taxonomyTypeDesc":21},[149,100,150,151,152,97,153,154,155,156,157,158,49,159,127,160,161,162,163,34,31],"web artifacts builder","artifacts","artifacts builder","builder","css","components","react","routing","state management","state","Tailwind","single-file","simple","ui components","multi",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":168,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":50},"01M6HSDXH0JSP8R3QTNY9XZ8HN","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Ffrontend-design\u002FSKILL.md",[171,172,173],{"categoryNo":91,"categoryName":92,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[97,29,175,153,100,154,155,176,177,178,150,179,106,180,127,181,182,183,184,109,185,186],"frontend design","react components","create","code","examples","landing","ui design","pages","aesthetics","web ui","generic","when",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":191,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":50},"01M6HSA77QYVP7A72HREGTDN2C","algorithmic-art","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Falgorithmic-art\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Falgorithmic-art\u002FSKILL.md",[194],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[196,197,198,177,178,199,200,201,202,127,203,204,205,206,109,33,207,208,209,210,186],"algorithmic art","Art","algorithmic","flow","js","work","interactive","generative art","exploration","systems","users","request","generative","copyright","fields",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":215,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":50},"01M6HS9HE0X390Y6RQKTY1YNGJ","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fexternal_plugins\u002Ftheme-factory\u002FSKILL.md",[218],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[220,221,222,223,102,224,150,126,225,226,180,227,228,182,229,109,230,231,232,34,233,234],"theme factory","factory","theme","docs","generate","fly","slides","styling","artifact","themes","you","fonts","can","apply","new"]