asset-discovery
Purpose
Decide where the assets in a scene will come from before the scene planner commits to a layout. Asset acquisition decisions affect poly budget, web GLB size, licensing, and time-to-handoff. This skill produces a per-asset plan with explicit confidence labels and licensing notes — without installing tools, running Blender, or fetching anything.
This skill is BlendOps-specific (no direct analog in Anthropic Superpowers or BMad), driven by a real Blender domain need.
Quick start
- read the 8-slot brief from
intent-to-3d-brief-writer
- enumerate every asset class needed (subjects, props, environment, materials, HDRIs)
- pick a strategy per asset class (procedural / library / generative / photogrammetry)
- record license + confidence label per choice
- hand off to scene planner
When to use
- after the 3D brief is locked, before any scene plan
- when scene assets aren't trivially given (e.g. user says "shoe" but doesn't supply a shoe model)
- when poly budget / GLB size / brand-licensing constraints exist
- when planner needs to know upfront whether assets are procedural or external
When not to use
- the user supplied all assets in the brief (skip; route directly to planner) → use
../intent-to-3d-brief-writer/SKILL.md (skip; route directly to planner)
- runtime is already executing and assets are already in the scene → use
../product-hero-scene-planner/SKILL.md (route to evidence skill)
- the request is iteration on an existing scene (assets are already chosen) → use
../render-export-evidence/SKILL.md (assets are already chosen)
Trigger phrases
- "what assets do we need"
- "where do the models come from"
- "asset plan before scene planning"
- "do we generate or import"
- "surface asset license risks before planning"
Prerequisites / readiness
- 8-slot brief from
intent-to-3d-brief-writer (or equivalent)
- list of constraint slots (performance, brand, time)
- no Blender runtime required
- works in text-only mode
Input schema
Required inputs
- 8-slot brief from
intent-to-3d-brief-writer (subject, mood, deliverables, constraints, evidence, acceptance, audience, owner)
- list of asset classes implied by the brief (e.g., hero subject, lighting, floor, environment backdrop)
Optional inputs
- known asset libraries the user has access to (approved brand library, internal library, user-supplied files)
- license preferences (public domain only, commercial allowed, brand-restricted)
- prior similar scenes to match asset choices
Assumptions to confirm
- the operator can defer fetching or generation to a later runtime step
- license restrictions matter for the deliverable (risks surfaced here; verdicts handled by
asset-license-checker)
- truth states start at Runtime
Not Run and Artifact Not Produced for plan-only work (downgrade-only, never upgrade)
Output schema
Primary output
- per-asset-class plan with strategy + source candidate + license + confidence + risk notes
| Asset class |
Strategy |
Source candidate |
License |
Confidence |
Risk notes |
| Hero shoe model |
generative |
Path 2 community mcp-for-blender (formerly ahujasid/blender-mcp) Hyper3D / Hunyuan3D integration |
TBD |
linked-only |
poly budget; Path 2 caveat; needs asset-license-checker verdict |
| Floor + props |
procedural |
built-in procedural setup |
N/A |
verified-read |
poly budget |
| Lighting fixtures |
procedural |
built-in area light setup |
N/A |
verified-read |
none |
| Environment backdrop |
library |
approved environment library |
commercial-OK / TBD |
verified-read |
filesize; style check via asset-style-check |
Secondary output
- budget reconciliation summary compared against
mobile-glb-budget and polycount-budget-checker
- explicit list of assets the operator must obtain before any runtime step
- license risk callouts for
asset-license-checker to adjudicate
Evidence / caveat output
- Runtime status:
Not Run
- Artifact status:
Not Produced
- Truth states are downgrade-only, never upgrade
- No asset is downloaded, generated, fetched, or installed by this skill
Required laws
- ../../laws/official-runtime-only.md
- ../../laws/evidence-before-done.md
- ../../laws/non-blender-user-language.md
- ../../laws/no-arbitrary-python-interface.md
Official runtime boundary
This skill does not download, generate, fetch, or install any asset. It does not run Blender, configure any MCP path, or touch the network. It produces a plain-language plan in markdown.
If the chosen strategy is generative, it is Path 2-only (community mcp-for-blender, formerly ahujasid/blender-mcp, Hyper3D / Hunyuan3D integrations) with per-path caveats (see docs/unofficial-runtime-bridges.md). Actual generation happens in a runtime step, never here.
Operating procedure
- Read the 8-slot brief from
intent-to-3d-brief-writer.
- Enumerate every asset class implied (subjects, props, environment, materials, lighting backdrops, effects).
- For each asset class, pick one acquisition strategy:
- procedural — created inside Blender via built-in procedural rules; no external asset file.
- library — existing approved library or user-supplied asset.
- generative — Hyper3D / Hunyuan3D (Path 2-only via community
mcp-for-blender, formerly ahujasid/blender-mcp, with per-path caveats); actual generation happens in a runtime step, never here.
- photogrammetry — user-supplied scan; cleanup required before scene assembly.
- For each pick: record source candidate, license, confidence label (
verified-read / linked-only / unknown), and risk notes.
- Reconcile per-class polycount and file-size estimates against
mobile-glb-budget (and polycount-budget-checker). Flag any overage risk explicitly.
- List every asset that must be obtained before runtime; surface license risks for
asset-license-checker (do not issue license verdicts here) and flag multi-source combinations for asset-style-check.
- Hand off the asset plan + brief to the target scene planner (
product-hero-scene-planner, character-portrait, environment-shot, interior-scene, or product-grid-scene-planner).
Decision tree
- subject is brand-specific (e.g., exact branded product) -> strategy must be
library (user-supplied / brand library); never generative without explicit brand authorization
- mood is highly specific -> backdrop =
library, color and surface treatments = procedural
- tight web or mobile budget constraint -> reconcile against
mobile-glb-budget; favor procedural over heavy external imports
- iteration-loop deliverable -> favor
procedural (fast and reproducible to adjust)
- one-shot marketing render ->
library or generative (Path 2-only with caveats) is acceptable once license risk is cleared by asset-license-checker
Playbooks
- Playbook A: "Cyberpunk shoe web hero" — shoe = generative or user-supplied; floor + props = procedural; HDRI = library; budget = web-tight
- Playbook B: "Brand product render" — subject = brand library only; environment = procedural; license = brand-restricted
- Playbook C: "Iteration sketch" — everything procedural; library only for HDRI
Mode handling
Text-only mode
- plan only, no fetch / generate / install
- Runtime status:
Not Run
- Artifact status:
Not Produced
- Truth states are downgrade-only, never upgrade
Runtime-ready mode
- plan stays text-only; downstream runtime steps consume the plan
- if
generative strategy is chosen, route to runtime-readiness first to confirm Path 2 (mcp-for-blender, formerly ahujasid/blender-mcp, Hyper3D / Hunyuan3D integrations) readiness and caveats
Blocked runtime mode
- plan is still produced with Runtime
Not Run and Artifact Not Produced
- mark
generative options blocked; favor procedural or library via asset-fallback-strategy
Validation checklist
Pass / Warn / Fail rubric
| Category |
Pass |
Warn |
Fail |
| Asset coverage |
All implied assets listed |
1-2 missing with note |
3+ missing |
| License records |
Every asset has license entry |
Some TBD with follow-up |
Missing license entries |
| Confidence labels |
Every choice labeled |
Partial labels |
No labels |
| Budget reconciliation |
Summed and compared |
Summed without comparison |
Not summed |
| Runtime claim |
None |
None |
Asset claimed to be fetched / generated by this skill |
Failure handling
- license unknown: mark
TBD, surface the risk note, and route to asset-license-checker before the scene planner commits
- generative strategy requested but Path 2 readiness unknown or unavailable: route to
runtime-readiness (and asset-fallback-strategy if blocked)
- conflicting constraints (e.g., high-detail scan vs. tight mobile budget): surface conflict against
mobile-glb-budget and route back to intent-to-3d-brief-writer if constraints must be relaxed
Troubleshooting
- if the asset list is too long, group by class and propose tiered approach (essentials vs. nice-to-have)
- if the user has no preference, default to procedural-first per BlendOps
evidence-before-done (procedural is reproducible)
Best practices
- procedural-first when license / budget pressure is high
- library-second when matching mood matters
- generative as a last resort, always with explicit caveats
- never fetch from this skill
Good examples
- "Cyberpunk shoe brief. Asset plan: hero shoe =
generative via Path 2 mcp-for-blender (formerly ahujasid/blender-mcp) Hyper3D/Hunyuan3D integration (license = TBD, risk surfaced for asset-license-checker; confidence = linked-only); floor + props = procedural (license = N/A; confidence = verified-read); environment lighting = library (approved studio backdrop; license = commercial-OK; confidence = verified-read). Budget reconciliation: estimated footprint checked against mobile-glb-budget. Obtain-before-runtime list: hero shoe mesh and environment backdrop. Runtime: Not Run, Artifact: Not Produced."
Bad examples
- "Just use any free shoe model from the internet, we'll figure out license later." (no source named, no license, no confidence label, license risk ignored)
User-facing response template
- Brief recap (one line)
- Asset table (markdown)
- Budget summary
- License risks called out
- Generative caveats if applicable
- Handoff: scene planner with this asset plan + brief
Anti-patterns
- downloading, fetching, generating, or installing any asset from this skill
- issuing final license verdicts instead of surfacing license risk for
asset-license-checker
- skipping style consistency handoffs (
asset-style-check) when mixing procedural, library, and generative sources
- claiming generative strategy works in Path 1 or without checking Path 2 caveats via
runtime-readiness
- referring to the community bridge as bare
blender-mcp instead of mcp-for-blender (formerly ahujasid/blender-mcp)
- upgrading truth states above Runtime
Not Run or Artifact Not Produced
Cross-skill handoff
- [upstream_reference] Before this skill →
../intent-to-3d-brief-writer/SKILL.md
- [alternative] Scene planners (primary handoff with brief + asset plan) (character-portrait) →
../character-portrait/SKILL.md
- [alternative] Scene planners (primary handoff with brief + asset plan) (environment-shot) →
../environment-shot/SKILL.md
- [alternative] Scene planners (primary handoff with brief + asset plan) (interior-scene) →
../interior-scene/SKILL.md
- [alternative] Scene planners (primary handoff with brief + asset plan) (product-grid-scene-planner) →
../product-grid-scene-planner/SKILL.md
- [alternative] Scene planners (primary handoff with brief + asset plan) (product-hero-scene-planner) →
../product-hero-scene-planner/SKILL.md
- [progression] License verdicts →
../asset-license-checker/SKILL.md
- [progression] Style re-checks →
../asset-style-check/SKILL.md
- [progression] Budget reconciliation (mobile-glb-budget) →
../mobile-glb-budget/SKILL.md
- [progression] Budget reconciliation (polycount-budget-checker) →
../polycount-budget-checker/SKILL.md
- [upstream_reference] Generative readiness →
../runtime-readiness/SKILL.md
- [fallback] Fallback / constraint updates (asset-fallback-strategy) →
../asset-fallback-strategy/SKILL.md
Non-goals
- fetching / downloading / installing assets
- running Blender or generative tools
- making the scene plan
- license adjudication beyond surfacing risk
References
- BlendOps law: ../../laws/official-runtime-only.md
- BlendOps law: ../../laws/evidence-before-done.md
- BlendOps doc on Path 2 generative integrations: ../../docs/unofficial-runtime-bridges.md
- Skill system: ../../docs/skill-system.md
1---2name: asset-discovery3description: Plan the asset acquisition strategy (procedural, library, generative, photogrammetry) for a Blender scene without installing or executing. Use after the brief, before scene planning.4metadata:5 source: https://skillmd.com/skills/thanhnguyxnorg/asset-discovery6---78# asset-discovery910## Purpose1112Decide where the assets in a scene will come from before the scene planner commits to a layout. Asset acquisition decisions affect poly budget, web GLB size, licensing, and time-to-handoff. This skill produces a per-asset plan with explicit confidence labels and licensing notes — without installing tools, running Blender, or fetching anything.1314This skill is BlendOps-specific (no direct analog in Anthropic Superpowers or BMad), driven by a real Blender domain need.1516## Quick start1718- read the 8-slot brief from `intent-to-3d-brief-writer`19- enumerate every asset class needed (subjects, props, environment, materials, HDRIs)20- pick a strategy per asset class (procedural / library / generative / photogrammetry)21- record license + confidence label per choice22- hand off to scene planner2324## When to use2526- after the 3D brief is locked, before any scene plan27- when scene assets aren't trivially given (e.g. user says "shoe" but doesn't supply a shoe model)28- when poly budget / GLB size / brand-licensing constraints exist29- when planner needs to know upfront whether assets are procedural or external3031## When not to use32<!-- blendops:generated:start exclusions -->33- the user supplied all assets in the brief (skip; route directly to planner) → use `../intent-to-3d-brief-writer/SKILL.md` (skip; route directly to planner)34- runtime is already executing and assets are already in the scene → use `../product-hero-scene-planner/SKILL.md` (route to evidence skill)35- the request is iteration on an existing scene (assets are already chosen) → use `../render-export-evidence/SKILL.md` (assets are already chosen)36<!-- blendops:generated:end exclusions -->3738## Trigger phrases39<!-- blendops:generated:start triggers -->40- "what assets do we need"41- "where do the models come from"42- "asset plan before scene planning"43- "do we generate or import"44- "surface asset license risks before planning"45<!-- blendops:generated:end triggers -->4647## Prerequisites / readiness4849- 8-slot brief from `intent-to-3d-brief-writer` (or equivalent)50- list of constraint slots (performance, brand, time)51- no Blender runtime required52- works in text-only mode5354## Input schema5556### Required inputs5758- 8-slot brief from `intent-to-3d-brief-writer` (subject, mood, deliverables, constraints, evidence, acceptance, audience, owner)59- list of asset classes implied by the brief (e.g., hero subject, lighting, floor, environment backdrop)6061### Optional inputs6263- known asset libraries the user has access to (approved brand library, internal library, user-supplied files)64- license preferences (public domain only, commercial allowed, brand-restricted)65- prior similar scenes to match asset choices6667### Assumptions to confirm6869- the operator can defer fetching or generation to a later runtime step70- license restrictions matter for the deliverable (risks surfaced here; verdicts handled by `asset-license-checker`)71- truth states start at Runtime `Not Run` and Artifact `Not Produced` for plan-only work (downgrade-only, never upgrade)7273## Output schema7475### Primary output7677- per-asset-class plan with strategy + source candidate + license + confidence + risk notes7879| Asset class | Strategy | Source candidate | License | Confidence | Risk notes |80|---|---|---|---|---|---|81| Hero shoe model | generative | Path 2 community `mcp-for-blender` (formerly `ahujasid/blender-mcp`) Hyper3D / Hunyuan3D integration | TBD | linked-only | poly budget; Path 2 caveat; needs `asset-license-checker` verdict |82| Floor + props | procedural | built-in procedural setup | N/A | verified-read | poly budget |83| Lighting fixtures | procedural | built-in area light setup | N/A | verified-read | none |84| Environment backdrop | library | approved environment library | commercial-OK / TBD | verified-read | filesize; style check via `asset-style-check` |8586### Secondary output8788- budget reconciliation summary compared against `mobile-glb-budget` and `polycount-budget-checker`89- explicit list of assets the operator must obtain before any runtime step90- license risk callouts for `asset-license-checker` to adjudicate9192### Evidence / caveat output9394- Runtime status: `Not Run`95- Artifact status: `Not Produced`96- Truth states are downgrade-only, never upgrade97- No asset is downloaded, generated, fetched, or installed by this skill9899## Required laws100101- ../../laws/official-runtime-only.md102- ../../laws/evidence-before-done.md103- ../../laws/non-blender-user-language.md104- ../../laws/no-arbitrary-python-interface.md105106## Official runtime boundary107108This skill does not download, generate, fetch, or install any asset. It does not run Blender, configure any MCP path, or touch the network. It produces a plain-language plan in markdown.109110If the chosen strategy is `generative`, it is Path 2-only (community `mcp-for-blender`, formerly `ahujasid/blender-mcp`, Hyper3D / Hunyuan3D integrations) with per-path caveats (see `docs/unofficial-runtime-bridges.md`). Actual generation happens in a runtime step, never here.111112## Operating procedure1131141. Read the 8-slot brief from `intent-to-3d-brief-writer`.1152. Enumerate every asset class implied (subjects, props, environment, materials, lighting backdrops, effects).1163. For each asset class, pick one acquisition strategy:117 - **procedural** — created inside Blender via built-in procedural rules; no external asset file.118 - **library** — existing approved library or user-supplied asset.119 - **generative** — Hyper3D / Hunyuan3D (Path 2-only via community `mcp-for-blender`, formerly `ahujasid/blender-mcp`, with per-path caveats); actual generation happens in a runtime step, never here.120 - **photogrammetry** — user-supplied scan; cleanup required before scene assembly.1214. For each pick: record source candidate, license, confidence label (`verified-read` / `linked-only` / `unknown`), and risk notes.1225. Reconcile per-class polycount and file-size estimates against `mobile-glb-budget` (and `polycount-budget-checker`). Flag any overage risk explicitly.1236. List every asset that must be obtained before runtime; surface license risks for `asset-license-checker` (do not issue license verdicts here) and flag multi-source combinations for `asset-style-check`.1247. Hand off the asset plan + brief to the target scene planner (`product-hero-scene-planner`, `character-portrait`, `environment-shot`, `interior-scene`, or `product-grid-scene-planner`).125126## Decision tree127128- subject is brand-specific (e.g., exact branded product) -> strategy must be `library` (user-supplied / brand library); never `generative` without explicit brand authorization129- mood is highly specific -> backdrop = `library`, color and surface treatments = `procedural`130- tight web or mobile budget constraint -> reconcile against `mobile-glb-budget`; favor `procedural` over heavy external imports131- iteration-loop deliverable -> favor `procedural` (fast and reproducible to adjust)132- one-shot marketing render -> `library` or `generative` (Path 2-only with caveats) is acceptable once license risk is cleared by `asset-license-checker`133134## Playbooks135136- Playbook A: "Cyberpunk shoe web hero" — shoe = generative or user-supplied; floor + props = procedural; HDRI = library; budget = web-tight137- Playbook B: "Brand product render" — subject = brand library only; environment = procedural; license = brand-restricted138- Playbook C: "Iteration sketch" — everything procedural; library only for HDRI139140## Mode handling141142### Text-only mode143144- plan only, no fetch / generate / install145- Runtime status: `Not Run`146- Artifact status: `Not Produced`147- Truth states are downgrade-only, never upgrade148149### Runtime-ready mode150151- plan stays text-only; downstream runtime steps consume the plan152- if `generative` strategy is chosen, route to `runtime-readiness` first to confirm Path 2 (`mcp-for-blender`, formerly `ahujasid/blender-mcp`, Hyper3D / Hunyuan3D integrations) readiness and caveats153154### Blocked runtime mode155156- plan is still produced with Runtime `Not Run` and Artifact `Not Produced`157- mark `generative` options blocked; favor `procedural` or `library` via `asset-fallback-strategy`158159## Validation checklist160161- [ ] every implied asset class enumerated162- [ ] canonical strategy chosen per asset class (`procedural` / `library` / `generative` / `photogrammetry`)163- [ ] source candidate named per choice164- [ ] license recorded per choice with risks surfaced for `asset-license-checker` (no final license verdicts claimed here)165- [ ] confidence label (`verified-read` / `linked-only` / `unknown`) assigned per choice166- [ ] budget reconciled against `mobile-glb-budget` and brief constraints167- [ ] obtain-before-runtime asset list included168- [ ] generative strategy flagged as Path 2-only (`mcp-for-blender`, formerly `ahujasid/blender-mcp`, Hyper3D / Hunyuan3D) with per-path caveats169- [ ] no asset downloaded, fetched, installed, or generated by this skill170- [ ] truth states set to Runtime `Not Run` and Artifact `Not Produced` (downgrade-only, never upgrade)171172## Pass / Warn / Fail rubric173174| Category | Pass | Warn | Fail |175|---|---|---|---|176| Asset coverage | All implied assets listed | 1-2 missing with note | 3+ missing |177| License records | Every asset has license entry | Some `TBD` with follow-up | Missing license entries |178| Confidence labels | Every choice labeled | Partial labels | No labels |179| Budget reconciliation | Summed and compared | Summed without comparison | Not summed |180| Runtime claim | None | None | Asset claimed to be fetched / generated by this skill |181182## Failure handling183184- license unknown: mark `TBD`, surface the risk note, and route to `asset-license-checker` before the scene planner commits185- generative strategy requested but Path 2 readiness unknown or unavailable: route to `runtime-readiness` (and `asset-fallback-strategy` if blocked)186- conflicting constraints (e.g., high-detail scan vs. tight mobile budget): surface conflict against `mobile-glb-budget` and route back to `intent-to-3d-brief-writer` if constraints must be relaxed187188## Troubleshooting189190- if the asset list is too long, group by class and propose tiered approach (essentials vs. nice-to-have)191- if the user has no preference, default to procedural-first per BlendOps `evidence-before-done` (procedural is reproducible)192193## Best practices194195- procedural-first when license / budget pressure is high196- library-second when matching mood matters197- generative as a last resort, always with explicit caveats198- never fetch from this skill199200## Good examples201202- "Cyberpunk shoe brief. Asset plan: hero shoe = `generative` via Path 2 `mcp-for-blender` (formerly `ahujasid/blender-mcp`) Hyper3D/Hunyuan3D integration (license = `TBD`, risk surfaced for `asset-license-checker`; confidence = `linked-only`); floor + props = `procedural` (license = N/A; confidence = `verified-read`); environment lighting = `library` (approved studio backdrop; license = commercial-OK; confidence = `verified-read`). Budget reconciliation: estimated footprint checked against `mobile-glb-budget`. Obtain-before-runtime list: hero shoe mesh and environment backdrop. Runtime: `Not Run`, Artifact: `Not Produced`."203204## Bad examples205206- "Just use any free shoe model from the internet, we'll figure out license later." (no source named, no license, no confidence label, license risk ignored)207208## User-facing response template209210- Brief recap (one line)211- Asset table (markdown)212- Budget summary213- License risks called out214- Generative caveats if applicable215- Handoff: scene planner with this asset plan + brief216217## Anti-patterns218219- downloading, fetching, generating, or installing any asset from this skill220- issuing final license verdicts instead of surfacing license risk for `asset-license-checker`221- skipping style consistency handoffs (`asset-style-check`) when mixing procedural, library, and generative sources222- claiming generative strategy works in Path 1 or without checking Path 2 caveats via `runtime-readiness`223- referring to the community bridge as bare `blender-mcp` instead of `mcp-for-blender` (formerly `ahujasid/blender-mcp`)224- upgrading truth states above Runtime `Not Run` or Artifact `Not Produced`225226## Cross-skill handoff227<!-- blendops:generated:start handoffs -->228- [upstream_reference] **Before this skill** → `../intent-to-3d-brief-writer/SKILL.md`229- [alternative] **Scene planners (primary handoff with brief + asset plan)** (character-portrait) → `../character-portrait/SKILL.md`230- [alternative] **Scene planners (primary handoff with brief + asset plan)** (environment-shot) → `../environment-shot/SKILL.md`231- [alternative] **Scene planners (primary handoff with brief + asset plan)** (interior-scene) → `../interior-scene/SKILL.md`232- [alternative] **Scene planners (primary handoff with brief + asset plan)** (product-grid-scene-planner) → `../product-grid-scene-planner/SKILL.md`233- [alternative] **Scene planners (primary handoff with brief + asset plan)** (product-hero-scene-planner) → `../product-hero-scene-planner/SKILL.md`234- [progression] **License verdicts** → `../asset-license-checker/SKILL.md`235- [progression] **Style re-checks** → `../asset-style-check/SKILL.md`236- [progression] **Budget reconciliation** (mobile-glb-budget) → `../mobile-glb-budget/SKILL.md`237- [progression] **Budget reconciliation** (polycount-budget-checker) → `../polycount-budget-checker/SKILL.md`238- [upstream_reference] **Generative readiness** → `../runtime-readiness/SKILL.md`239- [fallback] **Fallback / constraint updates** (asset-fallback-strategy) → `../asset-fallback-strategy/SKILL.md`240<!-- blendops:generated:end handoffs -->241242## Non-goals243244- fetching / downloading / installing assets245- running Blender or generative tools246- making the scene plan247- license adjudication beyond surfacing risk248249## References250251- BlendOps law: ../../laws/official-runtime-only.md252- BlendOps law: ../../laws/evidence-before-done.md253- BlendOps doc on Path 2 generative integrations: ../../docs/unofficial-runtime-bridges.md254- Skill system: ../../docs/skill-system.md