[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HSMZ53ZXPK6SERSCMPNN82":3,"skill-same:01M6HSMZ53ZXPK6SERSCMPNN82":126},{"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":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6HSMZ53ZXPK6SERSCMPNN82","godot-data-driven-config",null,"Create or extend data-driven config tables (WeaponData, EnemyData, LevelData, etc.) in a Godot 4 project so that designers can tweak numbers in .tres files via natural language. Use this skill whenever the user says something like \"give weapons a config table\", \"extract hardcoded numbers into data\", \"add a new enemy type\", \"designer wants to tune damage\u002Fhp\u002Fspeed\", \"add WeaponData\u002FPlayerData\u002FEnemyData\", or asks to make Godot values editable without touching code.","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\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000033","数据分析师","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],"config","data","godot data driven config","driven","godot","new","extend","data-driven","can","editable","tables","make","add","project","speed","natural language","files","use","table","designer","code","create","2026-11-10 10:12:30",false,"---\nname: godot-data-driven-config\ndescription: Create or extend data-driven config tables (WeaponData, EnemyData, LevelData, etc.) in a Godot 4 project so that designers can tweak numbers in .tres files via natural language. Use this skill whenever the user says something like \"give weapons a config table\", \"extract hardcoded numbers into data\", \"add a new enemy type\", \"designer wants to tune damage\u002Fhp\u002Fspeed\", \"add WeaponData\u002FPlayerData\u002FEnemyData\", or asks to make Godot values editable without touching code.\n---\n\n# Godot Data-Driven Config Skill\n\n## What this skill does\n\nTurns hardcoded `const` \u002F magic numbers inside `.gd` files into a clean **Resource-based config layer** that designers can edit via `.tres` or the Godot Inspector. Also generates a CLI validator (`bash tools\u002Fvalidate_data.sh`) so a human or CI can check \"did I break the config table?\" in one command.\n\n## When to invoke\n\nTrigger on intents like:\n- \"Create a WeaponData \u002F EnemyData \u002F LevelData \u002F SkillData for this project\"\n- \"Move these hardcoded numbers into a config table\"\n- \"I want designers to tune damage\u002Fhp\u002Fspeed without touching code\"\n- \"Add a new weapon\u002Fenemy type through data\"\n- \"Build an AI-native Godot config workflow\"\n\n## Canonical file layout (ALWAYS use this)\n\n```\nres:\u002F\u002Fdata\u002F\n├── specs\u002F                       # JSON specs, source of truth (git-tracked)\n│   ├── weapon.spec.json\n│   └── ...\n├── resources\u002F\n│   ├── \u003Cname>_data.gd           # class_name \u003CName>Data extends Resource\n│   └── data_manager.gd          # Autoload (AUTOGENERATED — do not hand-edit AUTOGEN regions)\n├── \u003Cname>s\u002F                     # plural dir, one .tres per entry\n│   └── default_\u003Cname>.tres\ntools\u002F\n├── validate_data.gd             # Godot-side CLI validator (autogen)\n└── validate_data.sh             # bash wrapper (exit code fix-up)\nproject.godot                    # [autoload] DataManager=\"*res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd\"\n```\n\nRationale: plural-dir + `id` field makes `DirAccess` scanning trivial. Specs under `data\u002Fspecs\u002F*.spec.json` are the **source of truth**; regenerating `data_manager.gd` \u002F `validate_data.gd` is always a pure function of that directory, so nothing can drift.\n\n## Required workflow\n\n### Step 1 — Discover & propose\n\n1. Read target `.gd` files; collect hardcoded constants and literals.\n2. Ask the user which category (weapon\u002Fplayer\u002Fenemy\u002Flevel\u002Fskill\u002Fitem\u002F…). Each category becomes one `\u003CName>Data` class.\n3. Produce a **field mapping table** (source constant → new field → range). Present it, wait for OK (max 1 round of confirmation).\n\n### Step 2 — Write spec JSON under `data\u002Fspecs\u002F`\n\nEvery category is described by exactly one JSON file matching `schemas\u002Ffield_spec.schema.json`. Commit these to git — they are the source of truth and diff well.\n\nMinimal valid spec:\n```json\n{\n  \"name\": \"weapon\",\n  \"default_id\": \"default_pistol\",\n  \"fields\": [\n    { \"key\": \"id\", \"type\": \"StringName\", \"default\": \"&\\\"\\\"\", \"group\": \"Identity\" },\n    { \"key\": \"damage\", \"type\": \"int\", \"default\": 10, \"range\": [0, 9999, 1] }\n  ],\n  \"validators\": [\"damage >= 0\"]\n}\n```\n\n### Step 3 — Run `scaffold.py` once per new\u002Fupdated category\n\n```bash\npython3 ~\u002F.codebuddy\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fscaffold.py \\\n    --project-root \u003Cabs Godot project path> \\\n    --spec \u003Cabs path to spec>.spec.json\n```\n\nThe script:\n- copies the spec into `res:\u002F\u002Fdata\u002Fspecs\u002F` (creates source-of-truth file)\n- writes `res:\u002F\u002Fdata\u002Fresources\u002F\u003Cname>_data.gd` (first time only; re-run with `--force-class` to overwrite)\n- writes `res:\u002F\u002Fdata\u002F\u003Cname>s\u002Fdefault_\u003Cname>.tres` (first time only; `--force-tres` to overwrite)\n- **rebuilds** `res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd` from **all** `data\u002Fspecs\u002F*.spec.json` — you never lose a previously-added category\n- **rebuilds** `res:\u002F\u002Ftools\u002Fvalidate_data.gd` (duck-typed against `Resource`, so cold-start without `.godot\u002F` cache still works)\n- writes `res:\u002F\u002Ftools\u002Fvalidate_data.sh` wrapper\n- patches `[autoload]` in `project.godot` idempotently\n\n### Step 4 — Migrate consumer `.gd` files\n\nFor each file with hardcoded values:\n1. Add at top of class:\n   ```gdscript\n   @export var \u003Cname>_data: \u003CName>Data\n   ```\n2. In `_ready()`:\n   ```gdscript\n   if \u003Cname>_data == null:\n       \u003Cname>_data = DataManager.get_\u003Cname>()\n   ```\n3. Replace literal(s): `JUMP_SPEED` → `\u003Cname>_data.jump_speed` etc.\n4. **Keep purely-technical consts** unchanged (collision masks, shader paths, blend-tree parameter strings).\n5. **DO NOT** edit `.tscn` unless necessary — the `DataManager` fallback covers unbound cases.\n\n### Step 5 — Validate\n\n```bash\nbash tools\u002Fvalidate_data.sh\n# exit 0 = OK\n# exit 1 = validation failed (stdout\u002Fstderr has reasons)\n# exit 2 = environment issue\n```\n\nOn **cold clone** (no `.godot\u002F` dir), the wrapper auto-refreshes the class cache once via `godot --headless --editor --quit` — designers\u002FCI need no special knowledge.\n\n### Step 6 — Document\n\nAppend to `PROJECT_OVERVIEW.md` or `README.md`:\n- The mapping table from Step 1\n- Designer workflow: \"edit `.tres` → run `bash tools\u002Fvalidate_data.sh` → F5\".\n- Validator command.\n\n## Hard rules\n\n- **One Resource class per category**, never a god-class.\n- Numeric fields MUST have `@export_range`.\n- Every `\u003CName>Data` MUST have an `id: StringName` field; filename stem is used as fallback id.\n- `DataManager` is ALWAYS an Autoload named `DataManager`.\n- `data_manager.gd` returns `Resource` (not `\u003CName>Data`) from getters; callers cast with `as WeaponData` if they want static typing. This keeps cold-start safe.\n- DO NOT mutate a Resource at runtime (shared reference). To modify: `var copy = data.duplicate(); copy.x = ...`.\n- DO NOT try to `MultiplayerSynchronizer`-sync a Resource. Instead, guarantee the same `.tres` exists on all peers (git-managed).\n- Validator never uses `exit_code` because Godot bug #88055 drops it under `--script`. Use the `VALIDATION_RESULT=OK|FAIL:n` stdout marker (the generated `validate_data.sh` does this).\n- DO NOT hand-edit the `# region *_AUTOGEN` blocks; `scaffold.py` rewrites them on every run.\n\n## Cold-start \u002F CI notes\n\n- Godot's `global_script_class_cache.cfg` is created by the editor. For headless\u002FCI, the first run needs `godot --headless --editor --quit` to populate it (the generated wrapper does this automatically when `.godot\u002F` is missing).\n- Validator is intentionally written to NOT depend on `class_name` resolution (uses `Resource` base + `res.get(\"field\")` duck-typing), so even if the cache is stale it still works.\n\n## Anti-patterns to avoid\n\n- ❌ Using CSV\u002FJSON\u002FYAML loaders at runtime — Godot's native `.tres` is already text, git-friendly, type-safe, and Inspector-editable.\n- ❌ Putting everything in one god-resource — harder to diff, no grouping, single-file merge conflicts.\n- ❌ Hardcoding defaults in the Resource script AND in the `.tres` at different values — keep `.tres` authoritative; script defaults only act as fallback when a consumer never binds a resource.\n- ❌ Reading `.tres` with `FileAccess` \u002F `JSON.parse` — always use `load()` \u002F `preload()`.\n\n## Smoke-test before declaring done\n\nRun `scripts\u002Fselftest.sh` (in this skill) which:\n1. Creates a fresh temp Godot project.\n2. Runs `scaffold.py` with every example spec.\n3. Refreshes class cache + runs the validator.\n4. Injects a bad value and confirms the validator now exits 1.\n5. Cleans up.\n\n```bash\nbash ~\u002F.codebuddy\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fselftest.sh\n```\n\n## Deliverables checklist\n\nWhen you finish, confirm ALL of:\n- [ ] `res:\u002F\u002Fdata\u002Fspecs\u002F\u003Cname>.spec.json` exists and is committed\n- [ ] `res:\u002F\u002Fdata\u002Fresources\u002F\u003Cname>_data.gd` with `class_name` + typed `@export` fields\n- [ ] `res:\u002F\u002Fdata\u002F\u003Cname>s\u002Fdefault_\u003Cname>.tres` with sensible defaults\n- [ ] `res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd` exists and references the new category\n- [ ] `project.godot` has `DataManager` in `[autoload]`\n- [ ] Consumer `.gd` reference `\u003Cname>_data.xxx` (no more magic numbers)\n- [ ] `bash tools\u002Fvalidate_data.sh` → exit 0\n- [ ] `PROJECT_OVERVIEW.md` \u002F `README.md` updated\n\n## Files in this skill\n\n```\nSKILL.md                                  this file\nQUICKREF.md                               one-page cheat sheet for the AI\nschemas\u002Ffield_spec.schema.json            JSON schema for designer-facing spec\ntemplates\u002F\n  data_class.gd.tmpl                      Resource class template\n  data_resource.tres.tmpl                 .tres template\n  data_manager.gd.tmpl                    Autoload template (uses Resource base)\n  validate_data.gd.tmpl                   CLI validator template (duck-typed)\n  validate_data.sh.tmpl                   bash wrapper (exit-code fix-up)\nscripts\u002F\n  scaffold.py                             end-to-end generator\n  selftest.sh                             self-test \u002F regression check\nexamples\u002F\n  weapon_spec.json\n  enemy_spec.json\n```\n","# Godot Data-Driven Config Skill\n\n## What this skill does\n\nTurns hardcoded `const` \u002F magic numbers inside `.gd` files into a clean **Resource-based config layer** that designers can edit via `.tres` or the Godot Inspector. Also generates a CLI validator (`bash tools\u002Fvalidate_data.sh`) so a human or CI can check \"did I break the config table?\" in one command.\n\n## When to invoke\n\nTrigger on intents like:\n- \"Create a WeaponData \u002F EnemyData \u002F LevelData \u002F SkillData for this project\"\n- \"Move these hardcoded numbers into a config table\"\n- \"I want designers to tune damage\u002Fhp\u002Fspeed without touching code\"\n- \"Add a new weapon\u002Fenemy type through data\"\n- \"Build an AI-native Godot config workflow\"\n\n## Canonical file layout (ALWAYS use this)\n\n```\nres:\u002F\u002Fdata\u002F\n├── specs\u002F                       # JSON specs, source of truth (git-tracked)\n│   ├── weapon.spec.json\n│   └── ...\n├── resources\u002F\n│   ├── \u003Cname>_data.gd           # class_name \u003CName>Data extends Resource\n│   └── data_manager.gd          # Autoload (AUTOGENERATED — do not hand-edit AUTOGEN regions)\n├── \u003Cname>s\u002F                     # plural dir, one .tres per entry\n│   └── default_\u003Cname>.tres\ntools\u002F\n├── validate_data.gd             # Godot-side CLI validator (autogen)\n└── validate_data.sh             # bash wrapper (exit code fix-up)\nproject.godot                    # [autoload] DataManager=\"*res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd\"\n```\n\nRationale: plural-dir + `id` field makes `DirAccess` scanning trivial. Specs under `data\u002Fspecs\u002F*.spec.json` are the **source of truth**; regenerating `data_manager.gd` \u002F `validate_data.gd` is always a pure function of that directory, so nothing can drift.\n\n## Required workflow\n\n### Step 1 — Discover & propose\n\n1. Read target `.gd` files; collect hardcoded constants and literals.\n2. Ask the user which category (weapon\u002Fplayer\u002Fenemy\u002Flevel\u002Fskill\u002Fitem\u002F…). Each category becomes one `\u003CName>Data` class.\n3. Produce a **field mapping table** (source constant → new field → range). Present it, wait for OK (max 1 round of confirmation).\n\n### Step 2 — Write spec JSON under `data\u002Fspecs\u002F`\n\nEvery category is described by exactly one JSON file matching `schemas\u002Ffield_spec.schema.json`. Commit these to git — they are the source of truth and diff well.\n\nMinimal valid spec:\n```json\n{\n  \"name\": \"weapon\",\n  \"default_id\": \"default_pistol\",\n  \"fields\": [\n    { \"key\": \"id\", \"type\": \"StringName\", \"default\": \"&\\\"\\\"\", \"group\": \"Identity\" },\n    { \"key\": \"damage\", \"type\": \"int\", \"default\": 10, \"range\": [0, 9999, 1] }\n  ],\n  \"validators\": [\"damage >= 0\"]\n}\n```\n\n### Step 3 — Run `scaffold.py` once per new\u002Fupdated category\n\n```bash\npython3 ~\u002F.codebuddy\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fscaffold.py \\\n    --project-root \u003Cabs Godot project path> \\\n    --spec \u003Cabs path to spec>.spec.json\n```\n\nThe script:\n- copies the spec into `res:\u002F\u002Fdata\u002Fspecs\u002F` (creates source-of-truth file)\n- writes `res:\u002F\u002Fdata\u002Fresources\u002F\u003Cname>_data.gd` (first time only; re-run with `--force-class` to overwrite)\n- writes `res:\u002F\u002Fdata\u002F\u003Cname>s\u002Fdefault_\u003Cname>.tres` (first time only; `--force-tres` to overwrite)\n- **rebuilds** `res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd` from **all** `data\u002Fspecs\u002F*.spec.json` — you never lose a previously-added category\n- **rebuilds** `res:\u002F\u002Ftools\u002Fvalidate_data.gd` (duck-typed against `Resource`, so cold-start without `.godot\u002F` cache still works)\n- writes `res:\u002F\u002Ftools\u002Fvalidate_data.sh` wrapper\n- patches `[autoload]` in `project.godot` idempotently\n\n### Step 4 — Migrate consumer `.gd` files\n\nFor each file with hardcoded values:\n1. Add at top of class:\n   ```gdscript\n   @export var \u003Cname>_data: \u003CName>Data\n   ```\n2. In `_ready()`:\n   ```gdscript\n   if \u003Cname>_data == null:\n       \u003Cname>_data = DataManager.get_\u003Cname>()\n   ```\n3. Replace literal(s): `JUMP_SPEED` → `\u003Cname>_data.jump_speed` etc.\n4. **Keep purely-technical consts** unchanged (collision masks, shader paths, blend-tree parameter strings).\n5. **DO NOT** edit `.tscn` unless necessary — the `DataManager` fallback covers unbound cases.\n\n### Step 5 — Validate\n\n```bash\nbash tools\u002Fvalidate_data.sh\n# exit 0 = OK\n# exit 1 = validation failed (stdout\u002Fstderr has reasons)\n# exit 2 = environment issue\n```\n\nOn **cold clone** (no `.godot\u002F` dir), the wrapper auto-refreshes the class cache once via `godot --headless --editor --quit` — designers\u002FCI need no special knowledge.\n\n### Step 6 — Document\n\nAppend to `PROJECT_OVERVIEW.md` or `README.md`:\n- The mapping table from Step 1\n- Designer workflow: \"edit `.tres` → run `bash tools\u002Fvalidate_data.sh` → F5\".\n- Validator command.\n\n## Hard rules\n\n- **One Resource class per category**, never a god-class.\n- Numeric fields MUST have `@export_range`.\n- Every `\u003CName>Data` MUST have an `id: StringName` field; filename stem is used as fallback id.\n- `DataManager` is ALWAYS an Autoload named `DataManager`.\n- `data_manager.gd` returns `Resource` (not `\u003CName>Data`) from getters; callers cast with `as WeaponData` if they want static typing. This keeps cold-start safe.\n- DO NOT mutate a Resource at runtime (shared reference). To modify: `var copy = data.duplicate(); copy.x = ...`.\n- DO NOT try to `MultiplayerSynchronizer`-sync a Resource. Instead, guarantee the same `.tres` exists on all peers (git-managed).\n- Validator never uses `exit_code` because Godot bug #88055 drops it under `--script`. Use the `VALIDATION_RESULT=OK|FAIL:n` stdout marker (the generated `validate_data.sh` does this).\n- DO NOT hand-edit the `# region *_AUTOGEN` blocks; `scaffold.py` rewrites them on every run.\n\n## Cold-start \u002F CI notes\n\n- Godot's `global_script_class_cache.cfg` is created by the editor. For headless\u002FCI, the first run needs `godot --headless --editor --quit` to populate it (the generated wrapper does this automatically when `.godot\u002F` is missing).\n- Validator is intentionally written to NOT depend on `class_name` resolution (uses `Resource` base + `res.get(\"field\")` duck-typing), so even if the cache is stale it still works.\n\n## Anti-patterns to avoid\n\n- ❌ Using CSV\u002FJSON\u002FYAML loaders at runtime — Godot's native `.tres` is already text, git-friendly, type-safe, and Inspector-editable.\n- ❌ Putting everything in one god-resource — harder to diff, no grouping, single-file merge conflicts.\n- ❌ Hardcoding defaults in the Resource script AND in the `.tres` at different values — keep `.tres` authoritative; script defaults only act as fallback when a consumer never binds a resource.\n- ❌ Reading `.tres` with `FileAccess` \u002F `JSON.parse` — always use `load()` \u002F `preload()`.\n\n## Smoke-test before declaring done\n\nRun `scripts\u002Fselftest.sh` (in this skill) which:\n1. Creates a fresh temp Godot project.\n2. Runs `scaffold.py` with every example spec.\n3. Refreshes class cache + runs the validator.\n4. Injects a bad value and confirms the validator now exits 1.\n5. Cleans up.\n\n```bash\nbash ~\u002F.codebuddy\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fselftest.sh\n```\n\n## Deliverables checklist\n\nWhen you finish, confirm ALL of:\n- [ ] `res:\u002F\u002Fdata\u002Fspecs\u002F\u003Cname>.spec.json` exists and is committed\n- [ ] `res:\u002F\u002Fdata\u002Fresources\u002F\u003Cname>_data.gd` with `class_name` + typed `@export` fields\n- [ ] `res:\u002F\u002Fdata\u002F\u003Cname>s\u002Fdefault_\u003Cname>.tres` with sensible defaults\n- [ ] `res:\u002F\u002Fdata\u002Fresources\u002Fdata_manager.gd` exists and references the new category\n- [ ] `project.godot` has `DataManager` in `[autoload]`\n- [ ] Consumer `.gd` reference `\u003Cname>_data.xxx` (no more magic numbers)\n- [ ] `bash tools\u002Fvalidate_data.sh` → exit 0\n- [ ] `PROJECT_OVERVIEW.md` \u002F `README.md` updated\n\n## Files in this skill\n\n```\nSKILL.md                                  this file\nQUICKREF.md                               one-page cheat sheet for the AI\nschemas\u002Ffield_spec.schema.json            JSON schema for designer-facing spec\ntemplates\u002F\n  data_class.gd.tmpl                      Resource class template\n  data_resource.tres.tmpl                 .tres template\n  data_manager.gd.tmpl                    Autoload template (uses Resource base)\n  validate_data.gd.tmpl                   CLI validator template (duck-typed)\n  validate_data.sh.tmpl                   bash wrapper (exit-code fix-up)\nscripts\u002F\n  scaffold.py                             end-to-end generator\n  selftest.sh                             self-test \u002F regression check\nexamples\u002F\n  weapon_spec.json\n  enemy_spec.json\n```\n",{"name":5,"description":7},"main","18d0e63d1313ca87098f614aa7c1e2dcf6de79c7","backend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config",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":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add welflau\u002Fai-dev-system --skill godot-data-driven-config",{"tool":68,"command":69},"bunx","bunx skills add welflau\u002Fai-dev-system --skill godot-data-driven-config",{"tool":71,"command":72},"pnpm","pnpm dlx skills add welflau\u002Fai-dev-system --skill godot-data-driven-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002FSKILL.md",true,[76,82,86,90,94,100,104,110,114,118,122],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"examples\u002Fenemy_spec.json","REFERENCE","参考文档",1625,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Fexamples\u002Fenemy_spec.json",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"examples\u002Fweapon_spec.json",1376,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Fexamples\u002Fweapon_spec.json",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"QUICKREF.md",2316,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002FQUICKREF.md",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"schemas\u002Ffield_spec.schema.json",2763,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Fschemas\u002Ffield_spec.schema.json",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fscaffold.py","SCRIPT","脚本",13911,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fscaffold.py",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fselftest.sh",4024,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Fscripts\u002Fselftest.sh",{"path":105,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":108,"sourceHtmlUrl":109},"templates\u002Fdata_class.gd.tmpl","OTHER","其他",163,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Ftemplates\u002Fdata_class.gd.tmpl",{"path":111,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":112,"sourceHtmlUrl":113},"templates\u002Fdata_manager.gd.tmpl",2548,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Ftemplates\u002Fdata_manager.gd.tmpl",{"path":115,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":116,"sourceHtmlUrl":117},"templates\u002Fdata_resource.tres.tmpl",212,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Ftemplates\u002Fdata_resource.tres.tmpl",{"path":119,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":120,"sourceHtmlUrl":121},"templates\u002Fvalidate_data.gd.tmpl",2732,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Ftemplates\u002Fvalidate_data.gd.tmpl",{"path":123,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":124,"sourceHtmlUrl":125},"templates\u002Fvalidate_data.sh.tmpl",1701,"https:\u002F\u002Fgithub.com\u002Fwelflau\u002Fai-dev-system\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fmarketplace\u002Fcodebuddy-plugins-official\u002Fplugins\u002Fmagicai-hub\u002Fskills\u002Fgodot-data-driven-config\u002Ftemplates\u002Fvalidate_data.sh.tmpl",[127,160,188,214,240,265],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":132,"sourceHtmlUrl":133,"categories":134,"keywords":141,"publishedAt":159},"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",[135,138],{"categoryNo":136,"categoryName":137,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"testing","webapp testing","webapp","frontend","screenshots","playwright","web","debugging","toolkit","browser","ui","logs","applications","behavior","local","with","for","2026-11-11 15:11:14",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":164,"sourceHtmlUrl":165,"categories":166,"keywords":170,"publishedAt":159},"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",[167],{"categoryNo":168,"categoryName":169,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通",[171,172,173,174,175,176,45,177,178,179,180,41,181,182,183,184,185,186,187],"internal comms","comms","status","help","SET","write","reports","me","incident","leadership","resources","communications","internal communications","formats","sort","my","updates",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":196,"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",[195],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},[197,148,198,199,200,145,201,202,203,204,205,206,207,208,45,209,210,211,212,158,213],"web artifacts builder","artifacts","artifacts builder","builder","css","components","react","routing","state management","state","file","Tailwind","single-file","simple","ui components","multi","single",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":218,"sourceHtmlUrl":219,"categories":220,"keywords":228,"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",[221,222,225],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":223,"categoryName":224,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":226,"categoryName":227,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师",[145,229,230,201,148,202,203,231,49,48,198,232,154,233,45,234,235,236,237,157,238,239],"design","frontend design","react components","examples","landing","ui design","pages","aesthetics","web ui","generic","when",{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":244,"sourceHtmlUrl":245,"categories":246,"keywords":248,"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",[247],{"categoryNo":223,"categoryName":224,"taxonomyType":20,"taxonomyTypeDesc":21},[249,250,251,49,48,252,253,254,255,45,256,257,258,259,157,260,261,262,263,264,239],"algorithmic art","Art","algorithmic","flow","js","work","interactive","generative art","exploration","systems","users","Existing","request","generative","copyright","fields",{"skillNo":266,"name":267,"nameZh":6,"description":268,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":131,"licenseFileUrl":269,"sourceHtmlUrl":270,"categories":271,"keywords":273,"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",[272],{"categoryNo":223,"categoryName":224,"taxonomyType":20,"taxonomyTypeDesc":21},[274,275,276,277,150,278,198,175,279,280,233,281,282,235,283,157,284,285,36,158,286,33],"theme factory","factory","theme","docs","generate","fly","slides","styling","artifact","themes","you","fonts","apply"]