[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79BVSWH7EYPB692DWZE3H52":3,"skill-same:01M79BVSWH7EYPB692DWZE3H52":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M79BVSWH7EYPB692DWZE3H52","3d-browser-game",null,"Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and independent playtests.","DanMcInerney\u002Forchflows","DanMcInerney","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1813669?v=4","01M79BVQ4JBV7DXVBCKT076EHN","Dan McInerney","01M79BVQ5KD3TMZ6N78W990MQG",126,"MIT","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fexample-workflows\u002F3d-browser-game\u002Fskills\u002F3d-browser-game\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: 3d-browser-game\ndescription: Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and independent playtests.\ndisable-model-invocation: true\n---\n\nThe coordinator applies [library context](..\u002F..\u002Freferences\u002Flibrary-context.md). Inputs: player brief, existing project, target conditions, workspace and constraints. Choose and record unspecified creative details; ask only when a missing choice blocks progress. A bounded phase uses its prerequisites and returns reached work without claiming a finished game.\n\nUse shared creative direction and one integration owner. Production staffing follows core execution rules; only the two playtests require fresh independent reviewers. Missing capabilities block dependent work.\n\n## Checkpoints\n\nUse [evidence](..\u002F..\u002Freferences\u002Fevidence.md) for candidate identities and `ready`, `needs change` or `unverified` conclusions. Freeze each candidate until its independent playtest report completes. These are work gates, not user approval prompts.\n\nEach checkpoint permits at most one necessary repair pass: reproduce material findings, fix shared causes, rebuild and replay affected situations plus start–play–outcome–retry. Recapture changed visuals and remeasure affected performance. Preserve the original report and identify the delivered revision; subsequent checks are maker verification, not renewed independent acceptance.\n\nAn unchanged ready candidate needs no repair, rebuild or replay. Pre-checkpoint QA\u002Ftuning is ordinary production. If a checkpoint remains needs change or unverified, stop dependent production and return the best runnable state, findings and precise next action.\n\n## 1. Establish scope and capabilities\n\nRecord the player promise, requirements versus defaults, browser\u002Fdevice\u002Finput, session scope and observable completion criteria. Preserve existing intent and architecture; bound a larger release without silently dropping requirements. Select `browser-game` for design.\n\nProbe install\u002Fbuild\u002Fpreview, rendered browser input\u002Fcaptures and Blender source-to-GLB loading in Three.js under the [test interface](..\u002F..\u002Freferences\u002Ftest-interface.md) and library capability rules. Probe promised audio. Remove disposable probe content from the finished game. Continue only with a feasible ordinary-play route and recorded capability results.\n\n## 2. Produce and test the core\n\nCompare at least three materially different mechanics; choose rules, controls, tunable parameters and completion states. Before implementation, write experiment predictions and observable success\u002Ffailure scenarios. Set load, frame-time and asset\u002Fcontent budget hypotheses for the agreed device.\n\nBuild a Three.js graybox under the [test interface](..\u002F..\u002Freferences\u002Ftest-interface.md) and [Three.js reference](..\u002F..\u002Freferences\u002Fthreejs.md). Complete the session with responsive controls, readable placeholders, real collision\u002Fprogression, an outcome and ordinary-input restart. Verify rule behavior, interface and production boot before experiments; control defects must not distort them.\n\nRun two focused mechanics experiments. Each predicts how one rule\u002Fparameter change affects decisions, compares observed baseline and changed behavior in the same scenario, and records the chosen setting and contrary evidence. Include alternate strategies, misuse and recovery. If meaningful decisions remain absent, report needs change before independent review.\n\nThe core handoff includes the runnable graybox, mechanics comparison\u002Fchoice, scenario predictions, two observed before\u002Fafter experiments, verified controls\u002Finterface and a complete ordinary session. Final assets wait for the core checkpoint.\n\n## 3. Independently establish the core\n\nApply [playtest-3d-browser-game](..\u002Fplaytest-3d-browser-game\u002FSKILL.md) in `core` mode to the frozen candidate with its required inputs and evidence. Missing uncoached\u002Fadaptive browser play is unverified. Apply the checkpoint rule after the completed report.\n\nOnly a ready core advances. Record established rules, camera, timing and collider contracts for art\u002Fcontent; later changes require affected gameplay checks.\n\n## 4. Produce and integrate\n\nDerive art direction and the [Blender handoff](..\u002F..\u002Freferences\u002Fblender.md) from the ready core. Apply [make-blender-game-assets](..\u002Fmake-blender-game-assets\u002FSKILL.md) with the art brief, actual baseline, runtime loader and owned output directory. Content\u002Fprogression may run concurrently on separate files under the proven rules. Gather both completed outcomes before integration.\n\nIntegrate inspected exports through the production loader; finish agreed content, UI, feedback and session flow under applicable game, Blender and Three.js criteria. Preserve or recheck timing, collision, camera and readability affected by integration. Required content cannot remain a promised later feature.\n\nRun scenario QA\u002Fregression play with `browser-game.playtesting`; measure and optimize representative production gameplay under the references. Fix known material defects before final review. Supply editable sources, reproducible exports, runtime asset views, complete-session\u002Fbranch evidence, behavior checks, target-relative load\u002Fperformance measurements and explicit coverage gaps. Unvisited states and unsupported targets remain unverified.\n\n## 5. Independently review and deliver\n\nApply the playtest workflow in `final` mode to the exact frozen production candidate, using a fresh reviewer different from the core reviewer. Supply the brief, public instructions, candidate\u002Frun location, test route, core review\u002Frepairs, asset evidence and measured conditions as that workflow directs. Apply the checkpoint rule after its completed report; graybox review does not accept production.\n\nReturn the game\u002Fpreview prominently, editable game\u002FBlender sources, build\u002Frun\u002Ftest\u002Fre-export commands, controls, scenarios, design\u002Fasset notes, independent reports and evidence. State ready, needs change or unverified against the requested scope, with gaps and next actions. Requested public deployment uses a hosting skill; local preview is not hosting.\n","The coordinator applies [library context](..\u002F..\u002Freferences\u002Flibrary-context.md). Inputs: player brief, existing project, target conditions, workspace and constraints. Choose and record unspecified creative details; ask only when a missing choice blocks progress. A bounded phase uses its prerequisites and returns reached work without claiming a finished game.\n\nUse shared creative direction and one integration owner. Production staffing follows core execution rules; only the two playtests require fresh independent reviewers. Missing capabilities block dependent work.\n\n## Checkpoints\n\nUse [evidence](..\u002F..\u002Freferences\u002Fevidence.md) for candidate identities and `ready`, `needs change` or `unverified` conclusions. Freeze each candidate until its independent playtest report completes. These are work gates, not user approval prompts.\n\nEach checkpoint permits at most one necessary repair pass: reproduce material findings, fix shared causes, rebuild and replay affected situations plus start–play–outcome–retry. Recapture changed visuals and remeasure affected performance. Preserve the original report and identify the delivered revision; subsequent checks are maker verification, not renewed independent acceptance.\n\nAn unchanged ready candidate needs no repair, rebuild or replay. Pre-checkpoint QA\u002Ftuning is ordinary production. If a checkpoint remains needs change or unverified, stop dependent production and return the best runnable state, findings and precise next action.\n\n## 1. Establish scope and capabilities\n\nRecord the player promise, requirements versus defaults, browser\u002Fdevice\u002Finput, session scope and observable completion criteria. Preserve existing intent and architecture; bound a larger release without silently dropping requirements. Select `browser-game` for design.\n\nProbe install\u002Fbuild\u002Fpreview, rendered browser input\u002Fcaptures and Blender source-to-GLB loading in Three.js under the [test interface](..\u002F..\u002Freferences\u002Ftest-interface.md) and library capability rules. Probe promised audio. Remove disposable probe content from the finished game. Continue only with a feasible ordinary-play route and recorded capability results.\n\n## 2. Produce and test the core\n\nCompare at least three materially different mechanics; choose rules, controls, tunable parameters and completion states. Before implementation, write experiment predictions and observable success\u002Ffailure scenarios. Set load, frame-time and asset\u002Fcontent budget hypotheses for the agreed device.\n\nBuild a Three.js graybox under the [test interface](..\u002F..\u002Freferences\u002Ftest-interface.md) and [Three.js reference](..\u002F..\u002Freferences\u002Fthreejs.md). Complete the session with responsive controls, readable placeholders, real collision\u002Fprogression, an outcome and ordinary-input restart. Verify rule behavior, interface and production boot before experiments; control defects must not distort them.\n\nRun two focused mechanics experiments. Each predicts how one rule\u002Fparameter change affects decisions, compares observed baseline and changed behavior in the same scenario, and records the chosen setting and contrary evidence. Include alternate strategies, misuse and recovery. If meaningful decisions remain absent, report needs change before independent review.\n\nThe core handoff includes the runnable graybox, mechanics comparison\u002Fchoice, scenario predictions, two observed before\u002Fafter experiments, verified controls\u002Finterface and a complete ordinary session. Final assets wait for the core checkpoint.\n\n## 3. Independently establish the core\n\nApply [playtest-3d-browser-game](..\u002Fplaytest-3d-browser-game\u002FSKILL.md) in `core` mode to the frozen candidate with its required inputs and evidence. Missing uncoached\u002Fadaptive browser play is unverified. Apply the checkpoint rule after the completed report.\n\nOnly a ready core advances. Record established rules, camera, timing and collider contracts for art\u002Fcontent; later changes require affected gameplay checks.\n\n## 4. Produce and integrate\n\nDerive art direction and the [Blender handoff](..\u002F..\u002Freferences\u002Fblender.md) from the ready core. Apply [make-blender-game-assets](..\u002Fmake-blender-game-assets\u002FSKILL.md) with the art brief, actual baseline, runtime loader and owned output directory. Content\u002Fprogression may run concurrently on separate files under the proven rules. Gather both completed outcomes before integration.\n\nIntegrate inspected exports through the production loader; finish agreed content, UI, feedback and session flow under applicable game, Blender and Three.js criteria. Preserve or recheck timing, collision, camera and readability affected by integration. Required content cannot remain a promised later feature.\n\nRun scenario QA\u002Fregression play with `browser-game.playtesting`; measure and optimize representative production gameplay under the references. Fix known material defects before final review. Supply editable sources, reproducible exports, runtime asset views, complete-session\u002Fbranch evidence, behavior checks, target-relative load\u002Fperformance measurements and explicit coverage gaps. Unvisited states and unsupported targets remain unverified.\n\n## 5. Independently review and deliver\n\nApply the playtest workflow in `final` mode to the exact frozen production candidate, using a fresh reviewer different from the core reviewer. Supply the brief, public instructions, candidate\u002Frun location, test route, core review\u002Frepairs, asset evidence and measured conditions as that workflow directs. Apply the checkpoint rule after its completed report; graybox review does not accept production.\n\nReturn the game\u002Fpreview prominently, editable game\u002FBlender sources, build\u002Frun\u002Ftest\u002Fre-export commands, controls, scenarios, design\u002Fasset notes, independent reports and evidence. State ready, needs change or unverified against the requested scope, with gaps and next actions. Requested public deployment uses a hosting skill; local preview is not hosting.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","b968ece14ad2bc25901c0c9dac6c40199169dd4d","example-workflows\u002F3d-browser-game\u002Fskills\u002F3d-browser-game",10,"https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows","https:\u002F\u002Fgithub.com\u002FDanMcInerney","https:\u002F\u002Fmcinerney.ai\u002F","Agent builder and security engineer","2026-11-10 10:33:52",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add DanMcInerney\u002Forchflows --skill 3d-browser-game",{"tool":40,"command":41},"bunx","bunx skills add DanMcInerney\u002Forchflows --skill 3d-browser-game",{"tool":43,"command":44},"pnpm","pnpm dlx skills add DanMcInerney\u002Forchflows --skill 3d-browser-game","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fexample-workflows\u002F3d-browser-game\u002Fskills\u002F3d-browser-game\u002FSKILL.md",[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",168,"https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fexample-workflows\u002F3d-browser-game\u002Fskills\u002F3d-browser-game\u002Fagents\u002Fopenai.yaml",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79BZ818G63WMWPF1AQNF4BD","style-demo","Create a small Python example under this library's style preferences.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Fcases\u002Fdynamic-review\u002Fpackages\u002Fstyle-fixture\u002Fskills\u002Fstyle-demo\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79BZ5RAV938VG1TPFR1ACXS","verified-invoice","Review an existing invoice against source data, with at most one repair and the caller's required checks.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Fcases\u002Fcomposition\u002Fpackages\u002Fconfidence-fixture\u002Fskills\u002Fverified-invoice\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79BZ1JT9HJT9P6V472V30AY","invoice-packet","Prepare a checked internal invoice and a public summary from an existing invoice and its source.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Fcases\u002Fcomposition\u002Fpackages\u002Fconfidence-fixture\u002Fskills\u002Finvoice-packet\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79BYX0VKW8QT4DYGJPCFYGZ","orch-work","Delegate a requested result to a fresh native child agent with relevant guidance. Use when a workflow names it or the user selects it; ordinary requests use orch-dynamic-workflow. Top-level coordinators only.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fskills\u002Forch-work\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79BYR1M7YV1P43KWW7HGEGC","orch-review","Delegate independent review of identified work to a fresh native child who did not make it, without repairs. Use when a workflow names it or the user selects it; ordinary requests use orch-dynamic-workflow. Top-level coordinators only.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fskills\u002Forch-review\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79BYKJ7EDW7106T7232GY6K","orch-dynamic-workflow","Plan and complete ordinary top-level tasks with core guidance and proportionate independent review, unless the user selects a workflow or primitive. Not for child assignments or questions about the library.","https:\u002F\u002Fgithub.com\u002FDanMcInerney\u002Forchflows\u002Fblob\u002Fmain\u002Fskills\u002Forch-dynamic-workflow\u002FSKILL.md",[],[]]