Product hero scene planner

Skill ThanhNguyxnOrg/blendops/skills/product-hero-scene-planner

Generate a complete product-hero scene plan from non-Blender-user intent with explicit assumptions and gates.From its SKILL.md

Install

npx -y skills add ThanhNguyxnOrg/blendops --skill product-hero-scene-planner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.7 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

product-hero-scene-planner

Purpose

Turn user intent into a high-quality, gate-ready scene plan before runtime execution.

Canonical role: scene-planning for product-hero workflows in the BlendOps skill system. Use this with the composition, camera, lighting, and material planners instead of creating duplicate generic scene-planning skills.

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

product hero scenario requests
pre-runtime plan generation
requirements normalization for non-technical users

When not to use

to claim generated artifacts
to skip unresolved ambiguity

Trigger phrases

“plan a product hero scene”
“turn this into a Blender plan”
“prepare cyberpunk shoe scene plan”

Prerequisites / readiness

runtime status known (Ready/Partially Ready/Blocked/Unknown)
output destination clarified
no runtime execution required in this skill

Input schema

Required inputs

user prompt
output destination (web/app/game/render)

Optional inputs

style/mood references
product constraints
performance constraints

Assumptions to confirm

source model availability
quality priority (realtime vs marketing)
acceptable caveat level

Output schema

Primary output

full scene plan schema

Secondary output

clarification question set
assumptions register

Evidence / caveat output

unverified sections list
runtime dependency caveats

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

Planning-only skill. Runtime execution and artifact claims are out of scope here.

Operating procedure

Restate user intent and desired outcome.
Identify target audience/use-case profile.
Extract hard constraints (style, brand, performance).
Generate clarification questions for missing critical data.
Build subject model (primary object and context elements).
Build composition plan (focal hierarchy, framing, negative space).
Build camera plan (angle, lens intent, depth strategy).
Build lighting plan (key/fill/rim + mood intent).
Build material plan (lookdev intent + portability caveats).
Build environment plan (background/support elements).
Define render/export intent and web handoff intent.
Attach validation-gate expectations and caveat policy.

Decision tree

If destination is unknown → request destination first.
If constraints conflict → produce option A/B with trade-offs.
If runtime blocked → keep planning mode and mark artifacts Not Run.

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

complete planning output
artifact status remains Not Run

Runtime-ready mode

include handoff steps for downstream runtime phase
no success claim until evidence exists

Blocked runtime mode

deliver complete plan + blocker-aware next actions

Validation checklist

Pass / Warn / Fail rubric

Category	Pass	Warn	Fail
Intent capture	Complete and coherent	Minor ambiguity remains	Core intent unclear
Plan completeness	All schema sections present	Some sections shallow	Critical sections missing
Assumption transparency	Explicit assumptions/caveats	Partial assumptions	Hidden assumptions
Evidence boundary	No overclaims	Slight ambiguity	Runtime/output success claimed without evidence

Failure handling

Missing critical inputs: block and ask targeted questions.
Conflicting constraints: provide prioritized options with caveats.
Unknown runtime readiness: continue in text-only planning mode.

Troubleshooting

Prompt too broad: split by objective and destination.
Web + cinematic conflict: ask priority ranking.
No source model: include intake risk and fallback plan.

Best practices

preserve user language in summaries
keep plan modular and checklist-ready
surface unknowns early

Good examples

“Plan includes subject/composition/camera/lighting/material/environment plus explicit Not Run artifact status pending runtime phase.”

Bad examples

“Hero scene done.” (no structure, no caveats)

User-facing response template

What you asked for
Proposed plan
What is not verified yet
Next action

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

Next: blender-composition-camera-planner
Then: blender-lighting-material-planner
Then: blender-scene-quality-checker

Non-goals

runtime command execution
artifact success claims

References

What ships with it: 5 files

2.7 KB alongside SKILL.md

references/

EVAL.md960 B

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.