Come usare
- Copia il comando e controlla il pacchetto prima di installarlo nel tuo ambiente agente.
- Controlla strumenti, credenziali e ambienti richiesti nel documento originale.
- Descrivi input e risultato desiderato; confronta l’output con le fonti.
npx skills add https://github.com/thanhnguyxnorg/blendops --skill glb-web-handoffPrima di iniziare
- L’installazione non include abbonamenti, quote API o accesso ai file.
- Stelle e installazioni indicano attività, non un test indipendente di qualità o sicurezza.
Contenuto dal repository con titoli, esempi, codice, tabelle, link e immagini preservati.
glb-web-handoff
Purpose
Define reliable handoff language and checks for GLB/web scenarios without overclaiming.
Quick start
- confirm this skill fits your goal
- provide required inputs first
- keep runtime claims evidence-bound
- follow suggested next-skill handoff
When to use
- when writing the GLB/web handoff summary after upstream validation from
scene-readinessand evidence classification fromrender-export-evidence - when summarizing per-artifact export statuses and web compatibility assumptions/caveats (transform/scale/origin, material/texture portability, loader/extensions, stack, performance)
- when preparing truthful next checks before passing final wording to
plain-language-response
When not to use
<!-- blendops:generated:start exclusions -->
- to claim GLB or export success without concrete evidence → use
../scene-readiness/SKILL.md(Delegates out-of-scope requests to scene-readiness) - to replace runtime export verification → use
../render-export-evidence/SKILL.md(Delegates out-of-scope requests to render-export-evidence) - to validate upstream scene readiness → use
../scene-readiness/SKILL.md(use scene-readiness) - to classify raw render/export artifact evidence → use
../render-export-evidence/SKILL.md(use render-export-evidence) - to define mobile or file-size performance budgets → use
../mobile-glb-budget/SKILL.md(use mobile-glb-budget) - to define animation playback or rig contracts → use
../glb-animation-handoff/SKILL.md(use glb-animation-handoff) - to write the final user-facing response wording → use
../plain-language-response/SKILL.md(use plain-language-response)
<!-- blendops:generated:end exclusions -->
Trigger phrases
<!-- blendops:generated:start triggers -->
- "prepare web handoff"
- "is GLB ready"
- "summarize export status"
<!-- blendops:generated:end triggers -->
Prerequisites / readiness
- upstream readiness output from
scene-readinessavailable (or marked unverified) - classified artifact evidence state from
render-export-evidenceknown - runtime mode known (within the 2-path + CLI appendix runtime model)
Input schema
Required inputs
- per-artifact status evidence from
render-export-evidence(with provenance to the current run for any pre-existing files) - upstream readiness summary from
scene-readiness - handoff target context and known compatibility assumptions
Optional inputs
- size/performance budget outputs from
mobile-glb-budget - animation handoff notes from
glb-animation-handoff - expected downstream web stack details
Assumptions to confirm
- transform/scale/origin assumptions
- material/texture portability assumptions
- loader/extensions assumptions
- target web stack assumptions
- performance assumptions and caveats
- truth states are downgrade-only (never upgrade):
- Runtime:
Not Run | Attempted | Produced | Verified | Failed - Artifacts:
Not Run | Not Produced | Produced | Verified | Failed(defaultNot Produced)
Output schema
Primary output
- truthful GLB/web handoff summary with explicit Runtime status and per-artifact statuses
Secondary output
- compatibility assumptions and caveats covering transform/scale/origin, material/texture portability, loader/extensions, stack, and performance
Evidence / caveat output
- explicit Runtime status (
Not Run | Attempted | Produced | Verified | Failed) and per-artifact status (Not Run | Not Produced | Produced | Verified | Failed, defaultNot Produced), downgrade-only - provenance confirmation tying any
ProducedorVerifiedartifact to the current run - unresolved risk notes, next checks, and cross-skill handoffs
Required laws
- ../../laws/evidence-before-done.md
- ../../laws/official-runtime-only.md
- ../../laws/non-blender-user-language.md
- ../../laws/no-arbitrary-python-interface.md
Official runtime boundary
Never claim GLB or export success without concrete evidence tied to the current run, and never replace runtime export verification. Keep runtime vocabulary strictly within the 2-path (Path 1 Official Blender Lab MCP 5.1+, Path 2 community mcp-for-blender) + CLI appendix model. This skill never runs Blender or Python and never upgrades Runtime or Artifact truth states (downgrade-only).
Operating procedure
- Enumerate expected handoff artifacts (GLB, preview renders, reports) and check current-run provenance for any pre-existing files.
- Inspect the GLB 2.0 binary container with
scripts/inspect-glb.mjs(blendops glb-inspect) and generate/validate the structured handoff manifest (schemas/glb-web-handoff-manifest.schema.json) viascripts/generate-glb-handoff-report.mjs(blendops glb-handoff) across all four validation tiers (Tier 1 Container Structural, Tier 2 Khronos glTF 2.0 Specification, Tier 3 Visual Quality, Tier 4 Live Blender Runtime). - Record Runtime status (
Not Run | Attempted | Produced | Verified | Failed) and mark each artifact status (Not Produced | Produced | Verified | Failed, defaultNot Produced) usingrender-export-evidencewithout upgrading any state. - Document transform/scale/origin assumptions and caveats (
+Y up, +Z forward, -X right,1 unit = 1 meter, non-identity or negative root scale checks). - Document material/texture portability assumptions and caveats (embedded
bufferViewvs external URI textures, KTX2/WebP transcoders, alpha modes). - Document loader/extensions and target web stack compatibility assumptions (
DRACOLoader,MeshoptDecoder,KTX2Loader, Three.js / React Three Fiber integration modules indocs/examples/glb-web-handoff/README.md) without inventing unsupported guarantees. - Document performance caveats and uncertainty (incorporating
mobile-glb-budgetif size budgets apply, andglb-animation-handoffif animation contracts apply). - Verify compliance with evidence boundaries and upstream
scene-readinessfindings, then hand off toplain-language-responsefor final user-facing wording.
Decision tree
- If concrete current-run GLB evidence is classified by
render-export-evidence-> reportProducedorVerified(matching evidence, never upgraded) + full compatibility caveats. - If a GLB file exists on disk but lacks provenance to the current run -> do not claim
ProducedorVerified; downgrade toNot Producedwith a provenance caveat. - If runtime was not executed -> mark Runtime
Not Runand artifactsNot Runor defaultNot Produced. - If runtime was
AttemptedorFailedand no valid GLB was exported -> mark artifactNot ProducedorFailedwith failure notes and next checks. - If size budgets or animation contracts are needed -> route to
mobile-glb-budgetorglb-animation-handoffrespectively. - Once handoff summary is complete -> hand off to
plain-language-responsefor final user-facing wording.
Playbooks
- Playbook A: text-only planning path
- Playbook B: runtime-ready path with evidence gating
- Playbook C: blocked runtime path with caveat-first reporting
Mode handling
Text-only mode
- document handoff expectations, compatibility assumptions, and caveats only
- mark Runtime
Not Runand artifactsNot RunorNot Produced(defaultNot Produced)
Runtime-ready mode
- report evidence-linked Runtime status (
Not Run | Attempted | Produced | Verified | Failed) and per-artifact statuses (Not Run | Not Produced | Produced | Verified | Failed, defaultNot Produced) with current-run provenance and downgrade-only enforcement
Blocked runtime mode
- make zero production or verification claims; keep artifacts at
Not Produced,Not Run, orFailed - provide blocker-driven next checks and compatibility caveats
Validation checklist
- [ ] Runtime status (
Not Run | Attempted | Produced | Verified | Failed) explicit - [ ] GLB and preview per-artifact statuses (
Not Produced | Produced | Verified | Failed, defaultNot Produced) explicit - [ ] current-run provenance verified for any pre-existing files (synthetic test fixtures remain
Not Produced) - [ ] truth states strictly downgrade-only (never upgraded)
- [ ] 4-tier validation summary explicit (Container Structural, glTF 2.0 Specification, Visual Quality, Live Runtime)
- [ ] transform/scale/origin assumptions documented
- [ ] material/texture portability caveats documented
- [ ] loader/extensions assumptions documented (
DRACOLoader,MeshoptDecoder,KTX2Loader) - [ ] target stack assumptions documented (
threejs,react-three-fiber,model-viewer,babylonjs) - [ ] performance caveats documented
- [ ] no unsupported readiness guarantees or role blur with evidence/quality/budget/animation/response skills
- [ ] actionable next checks and handoff to
plain-language-responseincluded
Pass / Warn / Fail rubric
| Category | Pass | Warn | Fail |
|---|---|---|---|
| Artifact truth | Status matches evidence | Partial evidence | Claims without evidence |
| Compatibility clarity | Assumptions/caveats complete | Some gaps | Missing assumptions |
| Web handoff usability | Clear next actions | Partial actionability | Confusing or incomplete |
| Evidence boundary | No overclaims | Minor ambiguity | Contradictory claims |
Failure handling
- Missing evidence: mark Runtime
Not Run(orAttempted) and artifactsNot Produced(default) orNot Run, then route torender-export-evidence/ list missing checks. - Failed export evidence: mark Runtime/artifact
FailedorNot Produced(downgrade-only), record failure reason, and list next checks. - Pre-existing file without current-run provenance: refuse
Produced/Verifiedstatus, keep atNot Produced, and require a fresh verified export run. - Unknown compatibility in any of the 5 categories: mark
Warnwith an explicit caveat rather than assuming support.
Troubleshooting
- Existing files found: verify provenance before claiming produced.
- Missing scale/origin assumptions: add as blocker.
- Missing stack assumptions: mark handoff as conditional.
Best practices
- Always pair every per-artifact status with its matching compatibility caveats.
- Enforce downgrade-only truth states and verify current-run provenance before accepting any file as
ProducedorVerified. - Keep handoff notes in plain language and hand off final user-facing phrasing to
plain-language-response.
Good examples
"Runtime status: Not Run. Artifact statuses: GLB Not Produced (default), Preview Not Produced. Compatibility assumptions & caveats: transform/scale/origin (1 unit = 1m, Z-up to Y-up conversion unverified), material/texture portability (procedural nodes must be baked before GLB export), loader/extensions (unverified compression/extension support), stack (target web viewer unspecified), performance (draw-call and file-size budget unverified; route to mobile-glb-budget if constrained). Next checks: run export via configured runtime path, classify evidence with render-export-evidence, and pass summary to plain-language-response."
Bad examples
“GLB is ready for production.” (no artifact proof)
User-facing response template
- Runtime status (
Not Run | Attempted | Produced | Verified | Failed) - Per-artifact statuses (
Not Run | Not Produced | Produced | Verified | Failed, defaultNot Produced) with current-run provenance notes - Compatibility assumptions and caveats:
- Transform / scale / origin
- Material / texture portability
- Loader / extensions
- Target stack
- Performance
- Unverified risks and next checks
- Cross-skill handoff (to
plain-language-responsefor final user-facing wording)
Anti-patterns
- skipping required laws or runtime boundary statements
- claiming runtime/artifact success without evidence
- using non-official runtime setup paths
- producing jargon-heavy final output without explanation
Cross-skill handoff
<!-- blendops:generated:start handoffs -->
- [upstream_reference] Upstream scene readiness validation →
../scene-readiness/SKILL.md - [upstream_reference] Upstream artifact evidence classification →
../render-export-evidence/SKILL.md - [upstream_reference] Mobile and file-size budget constraints →
../mobile-glb-budget/SKILL.md - [upstream_reference] Animation playback and rig handoff contracts →
../glb-animation-handoff/SKILL.md - [progression] Final user-facing response wording →
../plain-language-response/SKILL.md
<!-- blendops:generated:end handoffs -->
Non-goals
- Generating Python scripts or executing Blender exports
- Replacing runtime export verification
- Upgrading Runtime or Artifact truth states or accepting pre-existing files without current-run provenance
- Classifying raw render/export evidence (
render-export-evidence) or validating upstream scene quality (scene-readiness) - Defining size budgets (
mobile-glb-budget), animation contracts (glb-animation-handoff), or final user-facing wording (plain-language-response) - Making unsupported web stack or loader compatibility guarantees
References
- https://www.blender.org/lab/mcp-server/
- https://claude.com/resources/tutorials/using-the-blender-connector-in-claude
- https://docs.blender.org/manual/en/latest/advanced/command_line/index.html
- `../../schemas/glb-web-handoff-manifest.schema.json`
- `../../scripts/inspect-glb.mjs`
- `../../scripts/generate-glb-handoff-report.mjs`
- `../../docs/examples/glb-web-handoff/README.md`