scene-readiness
Purpose
Evaluate scene/workflow readiness honestly and consistently before any success claim.
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
- before readiness, export, or handoff claims to get a broad multi-category review
- after planning passes or after focused domain checkers have run
- during text-only or runtime evaluation reporting
When not to use
- as a replacement for evidence collection → use
../product-hero-scene-planner/SKILL.md (Delegates out-of-scope requests to product-hero-scene-planner)
- to fabricate confidence in missing artifacts → use
../lighting-material-plan/SKILL.md (Delegates out-of-scope requests to lighting-material-plan)
Trigger phrases
- "quality-check this scene"
- "is this ready"
- "evaluate pass warn fail"
Prerequisites / readiness
- plan output and acceptance criteria set available (e.g., from
acceptance-criteria-builder)
- runtime truth state known (
Not Run | Attempted | Produced | Verified | Failed; stays Not Run unless a real attempt was recorded)
- artifact truth state known (
Not Run | Not Produced | Produced | Verified | Failed; defaults to Not Produced unless concrete output evidence exists)
- optional outputs from focused checkers (
material-quality-checker, lighting-quality-checker, composition-quality-checker, polycount-budget-checker) and render-export-evidence
Input schema
Required inputs
- scene plan summary
- intended output criteria
- current runtime truth state (
Not Run | Attempted | Produced | Verified | Failed)
- current artifact truth state ledger (
Not Run | Not Produced | Produced | Verified | Failed, default Not Produced)
Optional inputs
- focused domain reports from
composition-quality-checker, lighting-quality-checker, material-quality-checker, and polycount-budget-checker
- artifact evidence classification from
render-export-evidence
- target quality threshold and destination-specific constraints
Assumptions to confirm
- whether a real runtime attempt was recorded (otherwise runtime stays
Not Run)
- whether artifacts have verified provenance to the current run vs. being pre-existing files
Output schema
Primary output
- category-level pass/warn/fail matrix
Secondary output
- overall readiness verdict (
Ready | Conditionally Ready | Not Ready, or Not Run when no runtime attempt happened) kept strictly separate from runtime/artifact truth states
- consolidated blockers and remediation steps traced from category scores
Evidence / caveat output
- downgrade-only runtime and artifact truth-state ledger (with provenance noted for any pre-existing files)
- explicit caveats, unknowns, and plain-language user impact
Required laws
- ../../laws/evidence-before-done.md
- ../../laws/non-blender-user-language.md
- ../../laws/official-runtime-only.md
- ../../laws/no-arbitrary-python-interface.md
Official runtime boundary
Review-only skill: never executes Blender, never runs or emits Python, and never produces artifacts. Runtime truth state stays Not Run unless a real attempt was recorded; artifact truth state defaults to Not Produced unless concrete output evidence from the current run exists. Truth states are downgrade-only (never upgrade). Text-only and blocked modes must remain explicit.
Operating procedure
- Confirm run mode, runtime truth state (
Not Run | Attempted | Produced | Verified | Failed), and artifact truth state (Not Run | Not Produced | Produced | Verified | Failed), verifying provenance to the current run for any existing files.
- Score Subject clarity against brief/plan intent.
- Score Composition/camera readiness (consume
composition-quality-checker output if available; do not redo deep domain validation).
- Score Lighting/material readiness (consume
lighting-quality-checker and material-quality-checker outputs if available; do not redo deep domain validation).
- Score Scale, transforms, and geometry budget readiness (consume
polycount-budget-checker output if available).
- Score Evidence and export readiness (consume
render-export-evidence classification if available; verify readiness for pre-handoff-verification and glb-web-handoff without taking over their roles).
- Assign independent Pass / Warn / Fail scores per category and trace how each contributes to the final outcome.
- Apply downgrade-only rules to truth states if gaps or missing provenance are found.
- Produce the final readiness verdict (
Ready | Conditionally Ready | Not Ready, or Not Run when no runtime attempt happened), keeping the verdict scale separate from runtime and artifact truth states.
Decision tree
- If no runtime attempt happened → Runtime truth state stays
Not Run, artifacts stay Not Produced, and readiness verdict is Not Run or Conditionally Ready (never Ready).
- If any critical category scores Fail or claims contradict evidence → Readiness verdict is
Not Ready.
- If all critical categories Pass, runtime/artifact evidence is
Verified for the current run, and no blockers remain → Readiness verdict is Ready.
- If critical categories Pass with minor warnings, or planning is complete while runtime/artifacts are unverified → Readiness verdict is
Conditionally Ready.
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
- evaluate planning quality across categories only
- keep runtime truth state at
Not Run and artifact truth states at Not Produced
- cap readiness verdict at
Conditionally Ready or Not Run (never Ready)
Runtime-ready mode
- consume artifact classifications from
render-export-evidence and domain checks from focused quality checkers
- require current-run provenance before accepting
Produced or Verified artifact states
Blocked runtime mode
- keep readiness verdict conservative (
Not Ready, Conditionally Ready, or Not Run)
- preserve exact runtime/artifact truth states (downgrade-only) and list blockers and next actions
Validation checklist
Pass / Warn / Fail rubric
| Category |
Pass |
Warn |
Fail |
| Subject clarity |
Clear focal hierarchy aligned with brief |
Minor ambiguity in secondary elements |
Unclear focal subject or intent mismatch |
| Composition/camera |
Coherent framing; passes composition-quality-checker if run |
Minor framing gaps; needs review |
Framing fails user goal or missing camera plan |
| Lighting/material |
Supports intent; passes lighting-quality-checker / material-quality-checker if run |
Minor tuning needed or focused checks pending |
Major lookdev mismatch or broken shading/lighting plan |
| Scale/geometry budget |
Real-world scale, clean transforms, passes polycount-budget-checker if run |
Unconfirmed transforms or near budget limit |
Wrong scale, unapplied transforms, or over budget |
| Evidence & handoff readiness |
Claims match render-export-evidence with current-run provenance |
Partial evidence or pre-handoff checks pending |
Claims contradict evidence, or pre-existing files claimed as new |
Failure handling
- Missing runtime attempt or evidence: keep runtime truth state
Not Run, keep artifact truth state Not Produced (downgrade-only, never upgrade), and cap readiness verdict at Conditionally Ready or Not Run.
- Critical category Fail: set readiness verdict to
Not Ready with traced remediation steps.
- Unverified or pre-existing files without current-run provenance: refuse
Produced/Verified attribution for this run and log a Warn/Fail caveat.
- Unknowns in domain specifics: log Warn with explicit caveat and recommend the appropriate focused checker (
material-quality-checker, lighting-quality-checker, composition-quality-checker, or polycount-budget-checker).
Troubleshooting
- If all categories pass but no artifacts exist: ensure verdict is not Ready.
- If pre-existing files found: do not attribute to current run without linkage.
- If plan quality high but runtime blocked: use Conditionally Ready or Not Run.
Best practices
- score categories independently before final verdict
- keep caveats visible in final summary
- preserve traceability from category score to verdict
Good examples
"Readiness Verdict: Conditionally Ready. All planning categories pass, but Runtime Truth State is Not Run and Artifact Truth State is Not Produced for this pass."
Bad examples
“Looks good overall, ship it.” (no rubric, no evidence mapping)
User-facing response template
- Current status
- What passed
- What needs follow-up
- Next best action
Anti-patterns
- conflating the readiness verdict scale (
Ready | Conditionally Ready | Not Ready | Not Run) with runtime or artifact truth states
- upgrading runtime or artifact truth states, or attributing pre-existing files to the current run without provenance
- redoing deep per-domain validation instead of consuming
material-quality-checker, lighting-quality-checker, composition-quality-checker, or polycount-budget-checker
- usurping artifact classification from
render-export-evidence, gate ownership from pre-handoff-verification, or web packaging from glb-web-handoff
- skipping required laws, using Path 2 without caveats, treating CLI fallback as a peer path, or emitting jargon/Python
Cross-skill handoff
- [upstream_reference] Focused domain validation (if gaps found) (composition-quality-checker) →
../composition-quality-checker/SKILL.md
- [upstream_reference] Focused domain validation (if gaps found) (lighting-quality-checker) →
../lighting-quality-checker/SKILL.md
- [upstream_reference] Focused domain validation (if gaps found) (material-quality-checker) →
../material-quality-checker/SKILL.md
- [upstream_reference] Focused domain validation (if gaps found) (polycount-budget-checker) →
../polycount-budget-checker/SKILL.md
- [progression] Evidence classification →
../render-export-evidence/SKILL.md
- [progression] Handoff gate →
../pre-handoff-verification/SKILL.md
- [conditional] Web delivery (when applicable) →
../glb-web-handoff/SKILL.md
- [progression] Final communication →
../plain-language-response/SKILL.md
Non-goals
- executing Blender or running/generating Python code
- producing or classifying raw render/export artifacts (owned by
render-export-evidence)
- replacing focused domain validators (
material-quality-checker, lighting-quality-checker, composition-quality-checker, polycount-budget-checker)
- owning final handoff gating (
pre-handoff-verification) or web handoff packaging (glb-web-handoff)
- making evidence-free readiness claims
References
1---2name: scene-readiness3description: Run multi-category scene readiness gates (mesh, UVs, PBR, bake caches, camera, silhouette match) with PASS/WARN/FAIL verdicts before export.4metadata:5 source: https://skillmd.com/skills/thanhnguyxnorg/scene-readiness6---78# scene-readiness910## Purpose11Evaluate scene/workflow readiness honestly and consistently before any success claim.1213## Quick start14- confirm this skill fits your goal15- provide required inputs first16- keep runtime claims evidence-bound17- follow suggested next-skill handoff1819## When to use20- before readiness, export, or handoff claims to get a broad multi-category review21- after planning passes or after focused domain checkers have run22- during text-only or runtime evaluation reporting2324## When not to use25<!-- blendops:generated:start exclusions -->26- as a replacement for evidence collection → use `../product-hero-scene-planner/SKILL.md` (Delegates out-of-scope requests to product-hero-scene-planner)27- to fabricate confidence in missing artifacts → use `../lighting-material-plan/SKILL.md` (Delegates out-of-scope requests to lighting-material-plan)28<!-- blendops:generated:end exclusions -->2930## Trigger phrases31<!-- blendops:generated:start triggers -->32- "quality-check this scene"33- "is this ready"34- "evaluate pass warn fail"35<!-- blendops:generated:end triggers -->3637## Prerequisites / readiness38- plan output and acceptance criteria set available (e.g., from `acceptance-criteria-builder`)39- runtime truth state known (`Not Run | Attempted | Produced | Verified | Failed`; stays `Not Run` unless a real attempt was recorded)40- artifact truth state known (`Not Run | Not Produced | Produced | Verified | Failed`; defaults to `Not Produced` unless concrete output evidence exists)41- optional outputs from focused checkers (`material-quality-checker`, `lighting-quality-checker`, `composition-quality-checker`, `polycount-budget-checker`) and `render-export-evidence`4243## Input schema4445### Required inputs46- scene plan summary47- intended output criteria48- current runtime truth state (`Not Run | Attempted | Produced | Verified | Failed`)49- current artifact truth state ledger (`Not Run | Not Produced | Produced | Verified | Failed`, default `Not Produced`)5051### Optional inputs52- focused domain reports from `composition-quality-checker`, `lighting-quality-checker`, `material-quality-checker`, and `polycount-budget-checker`53- artifact evidence classification from `render-export-evidence`54- target quality threshold and destination-specific constraints5556### Assumptions to confirm57- whether a real runtime attempt was recorded (otherwise runtime stays `Not Run`)58- whether artifacts have verified provenance to the current run vs. being pre-existing files5960## Output schema6162### Primary output63- category-level pass/warn/fail matrix6465### Secondary output66- overall readiness verdict (`Ready | Conditionally Ready | Not Ready`, or `Not Run` when no runtime attempt happened) kept strictly separate from runtime/artifact truth states67- consolidated blockers and remediation steps traced from category scores6869### Evidence / caveat output70- downgrade-only runtime and artifact truth-state ledger (with provenance noted for any pre-existing files)71- explicit caveats, unknowns, and plain-language user impact7273## Required laws74- ../../laws/evidence-before-done.md75- ../../laws/non-blender-user-language.md76- ../../laws/official-runtime-only.md77- ../../laws/no-arbitrary-python-interface.md7879## Official runtime boundary80Review-only skill: never executes Blender, never runs or emits Python, and never produces artifacts. Runtime truth state stays `Not Run` unless a real attempt was recorded; artifact truth state defaults to `Not Produced` unless concrete output evidence from the current run exists. Truth states are downgrade-only (never upgrade). Text-only and blocked modes must remain explicit.8182## Operating procedure831. Confirm run mode, runtime truth state (`Not Run | Attempted | Produced | Verified | Failed`), and artifact truth state (`Not Run | Not Produced | Produced | Verified | Failed`), verifying provenance to the current run for any existing files.842. Score **Subject clarity** against brief/plan intent.853. Score **Composition/camera** readiness (consume `composition-quality-checker` output if available; do not redo deep domain validation).864. Score **Lighting/material** readiness (consume `lighting-quality-checker` and `material-quality-checker` outputs if available; do not redo deep domain validation).875. Score **Scale, transforms, and geometry budget** readiness (consume `polycount-budget-checker` output if available).886. Score **Evidence and export readiness** (consume `render-export-evidence` classification if available; verify readiness for `pre-handoff-verification` and `glb-web-handoff` without taking over their roles).897. Assign independent Pass / Warn / Fail scores per category and trace how each contributes to the final outcome.908. Apply downgrade-only rules to truth states if gaps or missing provenance are found.919. Produce the final readiness verdict (`Ready | Conditionally Ready | Not Ready`, or `Not Run` when no runtime attempt happened), keeping the verdict scale separate from runtime and artifact truth states.9293## Decision tree94- If no runtime attempt happened → Runtime truth state stays `Not Run`, artifacts stay `Not Produced`, and readiness verdict is `Not Run` or `Conditionally Ready` (never `Ready`).95- If any critical category scores Fail or claims contradict evidence → Readiness verdict is `Not Ready`.96- If all critical categories Pass, runtime/artifact evidence is `Verified` for the current run, and no blockers remain → Readiness verdict is `Ready`.97- If critical categories Pass with minor warnings, or planning is complete while runtime/artifacts are unverified → Readiness verdict is `Conditionally Ready`.9899## Playbooks100- Playbook A: text-only planning path101- Playbook B: runtime-ready path with evidence gating102- Playbook C: blocked runtime path with caveat-first reporting103104## Mode handling105106### Text-only mode107- evaluate planning quality across categories only108- keep runtime truth state at `Not Run` and artifact truth states at `Not Produced`109- cap readiness verdict at `Conditionally Ready` or `Not Run` (never `Ready`)110111### Runtime-ready mode112- consume artifact classifications from `render-export-evidence` and domain checks from focused quality checkers113- require current-run provenance before accepting `Produced` or `Verified` artifact states114115### Blocked runtime mode116- keep readiness verdict conservative (`Not Ready`, `Conditionally Ready`, or `Not Run`)117- preserve exact runtime/artifact truth states (downgrade-only) and list blockers and next actions118119## Validation checklist120- [ ] run mode explicitly labeled121- [ ] runtime truth state (`Not Run | Attempted | Produced | Verified | Failed`) and artifact truth state (`Not Run | Not Produced | Produced | Verified | Failed`) recorded separately from the readiness verdict122- [ ] truth states are downgrade-only (never upgraded) and pre-existing files require current-run provenance123- [ ] category rubric scored independently with clear traceability to the final verdict124- [ ] focused checker outputs consumed without redoing their domain work125- [ ] blocker list complete and caveats include plain-language user impact126- [ ] final readiness verdict (`Ready | Conditionally Ready | Not Ready | Not Run`) justified without unsupported success claims127- [ ] no uncaveated Path 2 guidance; CLI appendix never treated as a peer path128- [ ] plain-language summary and next-skill handoffs provided129130## Pass / Warn / Fail rubric131132| Category | Pass | Warn | Fail |133|---|---|---|---|134| Subject clarity | Clear focal hierarchy aligned with brief | Minor ambiguity in secondary elements | Unclear focal subject or intent mismatch |135| Composition/camera | Coherent framing; passes `composition-quality-checker` if run | Minor framing gaps; needs review | Framing fails user goal or missing camera plan |136| Lighting/material | Supports intent; passes `lighting-quality-checker` / `material-quality-checker` if run | Minor tuning needed or focused checks pending | Major lookdev mismatch or broken shading/lighting plan |137| Scale/geometry budget | Real-world scale, clean transforms, passes `polycount-budget-checker` if run | Unconfirmed transforms or near budget limit | Wrong scale, unapplied transforms, or over budget |138| Evidence & handoff readiness | Claims match `render-export-evidence` with current-run provenance | Partial evidence or pre-handoff checks pending | Claims contradict evidence, or pre-existing files claimed as new |139140## Failure handling141- Missing runtime attempt or evidence: keep runtime truth state `Not Run`, keep artifact truth state `Not Produced` (downgrade-only, never upgrade), and cap readiness verdict at `Conditionally Ready` or `Not Run`.142- Critical category Fail: set readiness verdict to `Not Ready` with traced remediation steps.143- Unverified or pre-existing files without current-run provenance: refuse `Produced`/`Verified` attribution for this run and log a Warn/Fail caveat.144- Unknowns in domain specifics: log Warn with explicit caveat and recommend the appropriate focused checker (`material-quality-checker`, `lighting-quality-checker`, `composition-quality-checker`, or `polycount-budget-checker`).145146## Troubleshooting147- If all categories pass but no artifacts exist: ensure verdict is not Ready.148- If pre-existing files found: do not attribute to current run without linkage.149- If plan quality high but runtime blocked: use Conditionally Ready or Not Run.150151## Best practices152- score categories independently before final verdict153- keep caveats visible in final summary154- preserve traceability from category score to verdict155156## Good examples157"Readiness Verdict: Conditionally Ready. All planning categories pass, but Runtime Truth State is `Not Run` and Artifact Truth State is `Not Produced` for this pass."158159## Bad examples160“Looks good overall, ship it.” (no rubric, no evidence mapping)161162## User-facing response template163- Current status164- What passed165- What needs follow-up166- Next best action167168## Anti-patterns169- conflating the readiness verdict scale (`Ready | Conditionally Ready | Not Ready | Not Run`) with runtime or artifact truth states170- upgrading runtime or artifact truth states, or attributing pre-existing files to the current run without provenance171- redoing deep per-domain validation instead of consuming `material-quality-checker`, `lighting-quality-checker`, `composition-quality-checker`, or `polycount-budget-checker`172- usurping artifact classification from `render-export-evidence`, gate ownership from `pre-handoff-verification`, or web packaging from `glb-web-handoff`173- skipping required laws, using Path 2 without caveats, treating CLI fallback as a peer path, or emitting jargon/Python174175## Cross-skill handoff176<!-- blendops:generated:start handoffs -->177- [upstream_reference] Focused domain validation (if gaps found) (composition-quality-checker) → `../composition-quality-checker/SKILL.md`178- [upstream_reference] Focused domain validation (if gaps found) (lighting-quality-checker) → `../lighting-quality-checker/SKILL.md`179- [upstream_reference] Focused domain validation (if gaps found) (material-quality-checker) → `../material-quality-checker/SKILL.md`180- [upstream_reference] Focused domain validation (if gaps found) (polycount-budget-checker) → `../polycount-budget-checker/SKILL.md`181- [progression] Evidence classification → `../render-export-evidence/SKILL.md`182- [progression] Handoff gate → `../pre-handoff-verification/SKILL.md`183- [conditional] Web delivery (when applicable) → `../glb-web-handoff/SKILL.md`184- [progression] Final communication → `../plain-language-response/SKILL.md`185<!-- blendops:generated:end handoffs -->186187## Non-goals188- executing Blender or running/generating Python code189- producing or classifying raw render/export artifacts (owned by `render-export-evidence`)190- replacing focused domain validators (`material-quality-checker`, `lighting-quality-checker`, `composition-quality-checker`, `polycount-budget-checker`)191- owning final handoff gating (`pre-handoff-verification`) or web handoff packaging (`glb-web-handoff`)192- making evidence-free readiness claims193194## References195- https://www.blender.org/lab/mcp-server/196- https://claude.com/resources/tutorials/using-the-blender-connector-in-claude197- https://docs.blender.org/manual/en/latest/advanced/command_line/index.html