[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ERY94G7SWJ5X3X0D9MHKVN":3,"skill-same:01M6ERY94G7SWJ5X3X0D9MHKVN":132},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6ERY94G7SWJ5X3X0D9MHKVN","build-proof-to-model-assets",null,"Produce reviewed 3D assets through original-source classification, a human-approved six-angle proof set, native Pixal3D multi-view reconstruction and audited Blender finishing. Use for PROOF_TO_MODEL asset production, revisions, recovery and review evidence.","TimothyMeadows\u002FHephaera","TimothyMeadows","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4072037?v=4","01M6ERVE3WV9X55S1NT4W5FDGA","Timothy D Meadows II","01M6ERVE8H7CBATH6KYFDKG5CJ",4,"MIT","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"build proof to model assets","proof","model","assets","build","asset production","for","native","multi","asset","blender","human","evidence","review","use","view","3D","classification","recovery","SET","Production","produce","2026-11-10 10:12:30",false,"---\nname: build-proof-to-model-assets\ndescription: Produce reviewed 3D assets through original-source classification, a human-approved six-angle proof set, native Pixal3D multi-view reconstruction and audited Blender finishing. Use for PROOF_TO_MODEL asset production, revisions, recovery and review evidence.\nengines: [AGNOSTIC]\n---\n\n# Build Proof to Model Assets\n\n## When to use\n\nUse when PROOF_TO_MODEL is resolved for 2D-to-3D asset production or when resuming its staged native workflow. Do not invoke reconstruction for ordinary CSS\u002FSVG interfaces or silently change a selected pipeline.\n\n## Workflow\n\n1. Read architecture, STYLE.md, `.styles\u002F.pipelines\u002Fproof-to-model\u002FPIPELINE.md` and its recipe\u002Ftoolchain\u002Fschema. Resolve selection with `select-art-pipeline`, recording prompt evidence when applicable.\n2. Inspect configured libraries with `use-external-asset-library`; preserve repository-local copy receipts and ancestry. Record scale, interfaces, rights, geometry\u002Ftexture\u002Fcollision budgets and rigging\u002Fanimation applicability.\n3. Consult command\u002Fsubcommand help. Use `init` to preserve authorized originals; use `doctor` and dry-run `setup` to inspect prerequisites. Execute setup only with explicit authorization and license evidence. Never accept licenses or install drivers.\n4. First inspect and research only the registered original images. Read [source-subject-classification.md](references\u002Fsource-subject-classification.md) for entities, observed\u002Finferred anatomy or structure, materials, occlusion and unresolved interpretations. Register the actual report with `classify`; native registration does not perform vision or research.\n5. Read [multiview-proof-contract.md](references\u002Fmultiview-proof-contract.md) to plan front, subject-right, back, subject-left, top and bottom with one pose, identity and camera convention. If the sole source genuinely covers one angle, generate five missing views; an oblique\u002Fcropped source remains an anchor and may require six. New images\u002Frevisions require explicit CLOUD\u002FLOCAL selection, MEDIA.md, rights and bounded spending authorization. Use the available session media capability, then register actual artifacts with `prepare-proofs`; the native command is not an image generator.\n6. Show originals and all six current proofs, resolve consequential inferred features, and obtain human approval bound to the complete set. Preserve rejected candidates and revise only selected views. Record `proof-set` approval before `preprocess` using the current `status` fingerprint named `proofSet`; preserve real alpha or explicit BiRefNet, every mask, common square padding and adjusted camera FOV. Inspect and approve preprocessing before `reconstruct`, which must consume all six separate images and the pinned MV model set.\n7. Run `finish` for UV\u002Fbake, LOD\u002Fcollision and editable blend\u002FGLB outputs. Default finishing requires measured successful QuadriFlow; optional schemaVersion1 settings may select bounded working-low preparation. For explicitly selected rigid\u002Farticulated finishing, read [rigid-part-finishing.md](references\u002Frigid-part-finishing.md): schemaVersion2 consumes reviewed authored HIGH\u002FLOW pairs, exact part\u002Frepair ancestry and a supported native memory policy. Preserve the detailed high sources, actual material\u002Fatlas correspondence and all budgets. Settings never rewrite conditioning contracts, relax failed bounds or select a fallback automatically. Use only the fixed audited\u002Fhash-bound Blender 4.5 LTS bundle; this exception does not authorize arbitrary batch scripts or relax standalone BLENDER rules.\n8. Run `review` and `validate`; inspect independent re-import findings, original-source comparisons and six matching-camera proof\u002Frender pairs. Nominal camera alignment does not establish likeness or anatomical correctness. Route required rig\u002Fanimation work through subject-specific skills with evidence before declaring readiness.\n9. Use `record` for current independent reviewer and separate human acceptance\u002Frejection receipts. Check `status`; changed inputs invalidate affected proofs, approvals and dependent results. Use `promote` only after explicit current human acceptance and task authorization.\n\nFor model-to-animation production, hand the reviewed model to `build-model-animations`. Preserve original-only classification as source evidence; record new topology\u002Farticulation findings separately. Animation readiness may require neutral-pose or geometry repair work, especially fused limbs\u002Fequipment. Its motion package and complete-clip\u002Fruntime review do not inherit proof-set or static-asset acceptance.\n\n## Guardrails\n\n- Use the exact initialized and explicitly built `runtime\u002Fbubo` dependency through Hephaera's verified launcher. No sibling checkout or source-run fallback is allowed. Native process guards are not an OS sandbox.\n- No threshold matte fallback, placeholder stages, automatic human approval, hidden downloads, silent pipeline changes or unreviewed promotion.\n- Keep stage state under `.hephaera\u002F.cache\u002Ftasks\u002F\u003Ctask>\u002F`, candidates under `.art-staging\u002Fproof-to-model\u002F`, tools under ignored `.local\u002Ftools\u002Fproof-to-model\u002F`, and reviewed runtime packages under `assets\u002Fmodels\u002F`.\n- Preserve failed attempts and immutable originals, hashes, model\u002Ftool\u002Fscript\u002Frecipe identity and logs. An exhausted finishing budget requires an actual human decision and a current hash-bound `--finish-budget` receipt for exactly one more attempt; never reset counters or manufacture approval. Distinguish simulated-process tests from live engine and Blender acceptance.\n- Large solver inputs may use explicitly selected, measured `quadriFlow.simplification` with world-box vertices held by exact identity\u002Fcoordinate checks, per-part input caps and full vertex\u002Fsurface error checks. Preserve source preparation and all topology\u002Fcomponent guards; never increase tolerances or caps automatically. Smaller input does not bound QuadriFlow's internal growth or certify visual quality.\n- Generated\u002Frevised proofs and reconstruction renders never become classification evidence. Hidden anatomy and unseen surfaces remain inferred design completions after approval.\n- Single-view diagnostics require explicit `--mode single-view-diagnostic` and use the separate `proof` approval kind; that receipt cannot approve a v2 proof set. No SV fallback, four-image subset or contact sheet may stand in for the six inference frames.\n","# Build Proof to Model Assets\n\n## When to use\n\nUse when PROOF_TO_MODEL is resolved for 2D-to-3D asset production or when resuming its staged native workflow. Do not invoke reconstruction for ordinary CSS\u002FSVG interfaces or silently change a selected pipeline.\n\n## Workflow\n\n1. Read architecture, STYLE.md, `.styles\u002F.pipelines\u002Fproof-to-model\u002FPIPELINE.md` and its recipe\u002Ftoolchain\u002Fschema. Resolve selection with `select-art-pipeline`, recording prompt evidence when applicable.\n2. Inspect configured libraries with `use-external-asset-library`; preserve repository-local copy receipts and ancestry. Record scale, interfaces, rights, geometry\u002Ftexture\u002Fcollision budgets and rigging\u002Fanimation applicability.\n3. Consult command\u002Fsubcommand help. Use `init` to preserve authorized originals; use `doctor` and dry-run `setup` to inspect prerequisites. Execute setup only with explicit authorization and license evidence. Never accept licenses or install drivers.\n4. First inspect and research only the registered original images. Read [source-subject-classification.md](references\u002Fsource-subject-classification.md) for entities, observed\u002Finferred anatomy or structure, materials, occlusion and unresolved interpretations. Register the actual report with `classify`; native registration does not perform vision or research.\n5. Read [multiview-proof-contract.md](references\u002Fmultiview-proof-contract.md) to plan front, subject-right, back, subject-left, top and bottom with one pose, identity and camera convention. If the sole source genuinely covers one angle, generate five missing views; an oblique\u002Fcropped source remains an anchor and may require six. New images\u002Frevisions require explicit CLOUD\u002FLOCAL selection, MEDIA.md, rights and bounded spending authorization. Use the available session media capability, then register actual artifacts with `prepare-proofs`; the native command is not an image generator.\n6. Show originals and all six current proofs, resolve consequential inferred features, and obtain human approval bound to the complete set. Preserve rejected candidates and revise only selected views. Record `proof-set` approval before `preprocess` using the current `status` fingerprint named `proofSet`; preserve real alpha or explicit BiRefNet, every mask, common square padding and adjusted camera FOV. Inspect and approve preprocessing before `reconstruct`, which must consume all six separate images and the pinned MV model set.\n7. Run `finish` for UV\u002Fbake, LOD\u002Fcollision and editable blend\u002FGLB outputs. Default finishing requires measured successful QuadriFlow; optional schemaVersion1 settings may select bounded working-low preparation. For explicitly selected rigid\u002Farticulated finishing, read [rigid-part-finishing.md](references\u002Frigid-part-finishing.md): schemaVersion2 consumes reviewed authored HIGH\u002FLOW pairs, exact part\u002Frepair ancestry and a supported native memory policy. Preserve the detailed high sources, actual material\u002Fatlas correspondence and all budgets. Settings never rewrite conditioning contracts, relax failed bounds or select a fallback automatically. Use only the fixed audited\u002Fhash-bound Blender 4.5 LTS bundle; this exception does not authorize arbitrary batch scripts or relax standalone BLENDER rules.\n8. Run `review` and `validate`; inspect independent re-import findings, original-source comparisons and six matching-camera proof\u002Frender pairs. Nominal camera alignment does not establish likeness or anatomical correctness. Route required rig\u002Fanimation work through subject-specific skills with evidence before declaring readiness.\n9. Use `record` for current independent reviewer and separate human acceptance\u002Frejection receipts. Check `status`; changed inputs invalidate affected proofs, approvals and dependent results. Use `promote` only after explicit current human acceptance and task authorization.\n\nFor model-to-animation production, hand the reviewed model to `build-model-animations`. Preserve original-only classification as source evidence; record new topology\u002Farticulation findings separately. Animation readiness may require neutral-pose or geometry repair work, especially fused limbs\u002Fequipment. Its motion package and complete-clip\u002Fruntime review do not inherit proof-set or static-asset acceptance.\n\n## Guardrails\n\n- Use the exact initialized and explicitly built `runtime\u002Fbubo` dependency through Hephaera's verified launcher. No sibling checkout or source-run fallback is allowed. Native process guards are not an OS sandbox.\n- No threshold matte fallback, placeholder stages, automatic human approval, hidden downloads, silent pipeline changes or unreviewed promotion.\n- Keep stage state under `.hephaera\u002F.cache\u002Ftasks\u002F\u003Ctask>\u002F`, candidates under `.art-staging\u002Fproof-to-model\u002F`, tools under ignored `.local\u002Ftools\u002Fproof-to-model\u002F`, and reviewed runtime packages under `assets\u002Fmodels\u002F`.\n- Preserve failed attempts and immutable originals, hashes, model\u002Ftool\u002Fscript\u002Frecipe identity and logs. An exhausted finishing budget requires an actual human decision and a current hash-bound `--finish-budget` receipt for exactly one more attempt; never reset counters or manufacture approval. Distinguish simulated-process tests from live engine and Blender acceptance.\n- Large solver inputs may use explicitly selected, measured `quadriFlow.simplification` with world-box vertices held by exact identity\u002Fcoordinate checks, per-part input caps and full vertex\u002Fsurface error checks. Preserve source preparation and all topology\u002Fcomponent guards; never increase tolerances or caps automatically. Smaller input does not bound QuadriFlow's internal growth or certify visual quality.\n- Generated\u002Frevised proofs and reconstruction renders never become classification evidence. Hidden anatomy and unseen surfaces remain inferred design completions after approval.\n- Single-view diagnostics require explicit `--mode single-view-diagnostic` and use the separate `proof` approval kind; that receipt cannot approve a v2 proof set. No SV fallback, four-image subset or contact sheet may stand in for the six inference frames.\n",{"name":5,"engines":46,"description":7},[47],"AGNOSTIC","main","f819d9a9c7d641d8c7e14b59560a4fd358ec4630","skills\u002Fbuild-proof-to-model-assets",3,"https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera","https:\u002F\u002Fhephaera.com\u002F","https:\u002F\u002Fgithub.com\u002FTimothyMeadows","http:\u002F\u002Fwww.timothymeadows.com","Software & AI Systems Architect | Distributed Systems & Agentic Platforms","2026-11-13 03:52:23",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add TimothyMeadows\u002FHephaera --skill build-proof-to-model-assets",{"tool":64,"command":65},"bunx","bunx skills add TimothyMeadows\u002FHephaera --skill build-proof-to-model-assets",{"tool":67,"command":68},"pnpm","pnpm dlx skills add TimothyMeadows\u002FHephaera --skill build-proof-to-model-assets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002FSKILL.md",true,[72,78,82,86,90,94,98,102,106,110,114,120,124,128],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",326,"https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fmanifest-spec.md",4596,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Fmanifest-spec.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fmultiview-proof-contract.md",5726,"https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002Freferences\u002Fmultiview-proof-contract.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fphase-prompts.md",10949,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Fphase-prompts.md",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Frigid-part-finishing.md",2508,"https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002Freferences\u002Frigid-part-finishing.md",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Froute-audit-build-prompt.md",10897,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Froute-audit-build-prompt.md",{"path":99,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fsetup-and-install.md",5243,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Fsetup-and-install.md",{"path":103,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fsource-subject-classification.md",4359,"https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-proof-to-model-assets\u002Freferences\u002Fsource-subject-classification.md",{"path":107,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fstate-and-signoff.md",4593,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Fstate-and-signoff.md",{"path":111,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fzenwrite-portions.md",2481,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Freferences\u002Fzenwrite-portions.md",{"path":115,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Fbuild-route-manifest.mjs","SCRIPT","脚本",6314,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Fscripts\u002Fbuild-route-manifest.mjs",{"path":121,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Fbuild-route-manifest.zenwrite.mjs",8359,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Fscripts\u002Fbuild-route-manifest.zenwrite.mjs",{"path":125,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Fgen-route-specs.mjs",5532,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Fscripts\u002Fgen-route-specs.mjs",{"path":129,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":130,"sourceHtmlUrl":131},"scripts\u002Finstall.sh",1442,"https:\u002F\u002Fgithub.com\u002FJoshuaShepherd\u002Fmy-skills\u002Fblob\u002Fmain\u002Froute-audit\u002Fscripts\u002Finstall.sh",[133,155,176,195,214,233],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":41},"01M70V3EJ7JDFDFJ3XTKRGKRBP","verify-web3-game-lifecycle","Verify a game's selected Web3 asset, wallet, ownership and trading lifecycle with contract properties, canonical recovery, actual target evidence and separate release readiness.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fverify-web3-game-lifecycle\u002FSKILL.md",[],[140,141,142,143,144,145,31,146,147,148,37,149,150,151,152,28,153,154],"game","verify","lifecycle","verify web3 game lifecycle","web3","with","readiness","release readiness","Wallet","properties","release","contract","canonical","ownership","trading",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":41},"01M70V3CS767H4M1FP4C2A7K51","verify-onchain-game-assets","Verify exact on-chain game collection ownership and quantities at canonical blocks, reconcile inventory events, and design honest match admission. Use for ERC721\u002FERC1155 inventory, reorg recovery, reservations, or transfer-during-match rules.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fverify-onchain-game-assets\u002FSKILL.md",[],[140,162,141,163,22,164,165,25,166,167,168,169,33,170,171,172,37,173,174,175],"onchain","game assets","verify onchain game assets","chain","inventory","reservations","design","erc721","Rules","collection","on-chain","at","blocks","reconcile",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":41},"01M70TZYWE48MTM8CGGDMWSJDN","plan-web3-game-assets","Define an opt-in Ethereum, Base or Immutable game-asset lifecycle, including token identity, supply, rights, custody, game eligibility and chain-specific dependencies.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fplan-web3-game-assets\u002FSKILL.md",[],[140,183,163,22,184,144,185,186,187,188,165,189,142,190,191,192,193,28,194],"plan","plan web3 game assets","supply","opt","immutable","rights","dependencies","token","base","define","ethereum","identity",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":41},"01M70TYYZ7SPZ7PE6A6GQ5RXQ9","integrate-game-wallets","Integrate explicit player-wallet connection, scoped SIWE authentication, authority invalidation and reviewed target-specific handoff without application-held player keys.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fintegrate-game-wallets\u002FSKILL.md",[],[140,202,203,204,205,148,206,207,208,209,210,211,212,213],"integrate game wallets","integrate","wallets","siwe","keys","authentication","player","scoped","connection","authority","application","handoff",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"publishedAt":41},"01M70TYX656BP1R0KWMYRX437R","integrate-game-asset-trading","Integrate explicitly selected game asset settlement with exact unsigned intents, scoped approvals, idempotent operations and canonical receipt reconciliation. Use for NFT listing, buying, cancellation, retries or marketplace integration.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fintegrate-game-asset-trading\u002FSKILL.md",[],[140,221,203,28,154,222,223,25,209,224,33,225,226,145,227,228,229,230,231,232],"integrate game asset trading","reconciliation","idempotent operations","retries","listing","idempotent","nft","approvals","operations","marketplace","integration","intents",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":239,"publishedAt":41},"01M70TWV3J83RAJMA7BC62CPAH","build-evm-game-contracts","Author and verify host-owned EVM game collections and explicit mint, burn, craft or admin rules with pinned Solidity tooling. Use for contract source and deployment candidates; deployment and player signing require separate authorization.","https:\u002F\u002Fgithub.com\u002FTimothyMeadows\u002FHephaera\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evm-game-contracts\u002FSKILL.md",[],[140,240,23,241,242,25,243,208,244,151,245,33,170,246,145,247,248,141,249,250],"evm","build evm game contracts","contracts","deployment","collections","host","author","admin","signing","mint","tooling"]