camera-composition
Purpose
Design high-quality composition/camera strategy for product hero scenes in plain, actionable language.
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
- expanding an upstream scene brief from
product-hero-scene-planner into detailed framing and camera direction
- defining focal hierarchy, viewer attention path, camera angle, focal length mood, and depth layering before lookdev
- aligning hero framing and negative space with web/UI copy overlays
When not to use
- as proof of rendered output quality or to validate an existing framing → use
../composition-quality-checker/SKILL.md (use composition-quality-checker)
- to design lighting rigs or surface materials/lookdev → use
../lighting-material-plan/SKILL.md (use lighting-material-plan)
- to lock final pixel resolution or output aspect specs → use
../resolution-aspect-decision/SKILL.md (use resolution-aspect-decision)
- to choose delivery file formats → use
../output-format-decision/SKILL.md (use output-format-decision)
- when subject intent is undefined → use
../product-hero-scene-planner/SKILL.md (Delegates out-of-scope requests to product-hero-scene-planner)
Trigger phrases
- "improve composition and camera"
- "choose hero framing"
- "set camera strategy for product hero"
Prerequisites / readiness
- upstream scene concept from
product-hero-scene-planner (or clear subject and destination context) available
- planning-only boundary accepted: runtime status remains
Not Run and artifacts remain Not Produced
Input schema
Required inputs
- subject intent (from
product-hero-scene-planner or user brief)
- target output context (web/app/game/render)
Optional inputs
- target aspect ratio constraints (from
resolution-aspect-decision if already locked)
- UI/copy overlay constraints
- cinematic vs neutral tone preference
Assumptions to confirm
- need for negative space
- focal detail priority
- camera motion vs static hero shot intent
Output schema
Primary output
- composition-camera plan with plain-language rationale
Secondary output
- fallback framing variant for uncertain constraints
Evidence / caveat output
- unresolved visual assumptions
- explicit truth states: Runtime
Not Run, Artifacts Not Produced (downgrade-only, never upgrade)
Required laws
- ../../laws/non-blender-user-language.md
- ../../laws/evidence-before-done.md
- ../../laws/official-runtime-only.md
- ../../laws/no-arbitrary-python-interface.md
Official runtime boundary
Planning-only skill: no Blender execution, no Python scripts, and no artifact generation. Runtime status stays Not Run and artifacts stay Not Produced (truth states are downgrade-only, never upgraded without verified evidence).
Operating procedure
- Define focal hierarchy (primary/secondary/background).
- Define hero-section objective and viewer attention path.
- Select aspect ratio framing strategy (deferring final resolution/aspect locks to
resolution-aspect-decision).
- Reserve negative space for UI/text overlays if needed.
- Choose camera angle preset family.
- Set focal length guidance by mood (dramatic vs neutral).
- Define depth layering (foreground/midground/background).
- Define target silhouette/readability checks (for later validation by
composition-quality-checker).
- Produce fallback framing variant for uncertainty.
- Translate plan into plain-language rationale.
Decision tree
- If copy overlay required → prioritize negative space and silhouette.
- If product detail priority high → tighter framing and controlled depth.
- If uncertainty high → provide two options and ask preference.
Playbooks
- Playbook A: Full brief path — expand upstream
product-hero-scene-planner output into primary framing + fallback variant (Runtime: Not Run, Artifacts: Not Produced).
- Playbook B: Overlay-heavy path — prioritize negative space and silhouette separation for UI/copy constraints (
Runtime: Not Run, Artifacts: Not Produced).
- Playbook C: High-uncertainty path — provide two distinct framing variants with trade-off rationale and explicit caveats (
Runtime: Not Run, Artifacts: Not Produced).
Mode handling
Text-only mode
- provide primary composition/camera plan and fallback variant in plain language
- report
Runtime: Not Run and Artifacts: Not Produced
Runtime-ready mode
- provide the composition/camera plan plus explicit target criteria for
composition-quality-checker to validate once a scene exists
- keep
Runtime: Not Run and Artifacts: Not Produced during planning
Blocked runtime mode
- deliver full composition/camera plan and fallback variant with explicit caveats
- keep
Runtime: Not Run and Artifacts: Not Produced; make no visual success claims
Validation checklist
Pass / Warn / Fail rubric
| Category |
Pass |
Warn |
Fail |
| Focal hierarchy |
Clear primary/secondary/background priority |
Partial hierarchy |
Missing hierarchy |
| Framing strategy |
Matches output context and includes fallback variant |
Generic framing or weak fallback |
Mismatched framing or missing fallback |
| Camera rationale |
Specific plain-language angle, focal-length mood, and depth layering |
Vague rationale or unexplained jargon |
No rationale or includes Python/execution commands |
| Role & truth boundary |
Stays in planning; reports Runtime: Not Run and Artifacts: Not Produced |
Mild boundary overlap with lookdev/validation |
Claims verified framing quality or upgrades truth states |
Failure handling
- Conflicting goals: provide trade-off options.
- Missing constraints: ask targeted follow-up.
- Unknown destination: use conservative web-hero defaults + caveat.
Troubleshooting
- Subject lost in frame: tighten framing focus, adjust camera angle preset, or increase spatial separation between foreground, midground, and background layers.
- No room for copy: widen negative space allowance and shift primary focal placement off-center.
- Flat spatial staging: adjust camera angle and focal-length perspective or increase depth-layer spacing (route lighting/material contrast issues to
lighting-material-plan).
- Existing scene framing needs pass/fail grading: hand off to
composition-quality-checker.
Best practices
- optimize for clarity before stylization
- tie each camera choice to user outcome
- preserve fallback path for uncertain constraints
Good examples
“Primary subject occupies center-right with left negative space for hero copy; camera 3/4 angle chosen for silhouette and depth readability.”
Bad examples
“Use cinematic camera.” (no context, no criteria)
User-facing response template
- Composition summary (focal hierarchy, attention path, negative space, depth layering, silhouette checks)
- Camera strategy summary (aspect strategy, angle preset, focal length by mood)
- Fallback framing variant
- Why this helps your goal (plain-language rationale)
- Truth states (
Runtime: Not Run, Artifacts: Not Produced) and unverified assumptions
- Recommended next skill handoff
Anti-patterns
- skipping required laws or runtime boundary statements
- claiming runtime/artifact success without evidence
- claiming runtime or artifact states above
Not Run / Not Produced (violating downgrade-only truth rules)
- writing Python code or Blender camera execution commands
- designing lighting rigs or material lookdev instead of handing off to
lighting-material-plan
- validating rendered/viewport composition instead of handing off to
composition-quality-checker
- locking final export resolution/aspect (
resolution-aspect-decision) or file formats (output-format-decision)
- producing jargon-heavy camera specs without plain-language rationale
Cross-skill handoff
- [upstream_reference] Upstream input from →
../product-hero-scene-planner/SKILL.md
- [conditional] Lateral output specs (if needed) (output-format-decision) →
../output-format-decision/SKILL.md
- [conditional] Lateral output specs (if needed) (resolution-aspect-decision) →
../resolution-aspect-decision/SKILL.md
- [progression] Next (lookdev & lighting) →
../lighting-material-plan/SKILL.md
- [progression] Then (validation) (scene-readiness) →
../scene-readiness/SKILL.md
- [progression] Then (validation) (composition-quality-checker) →
../composition-quality-checker/SKILL.md
Non-goals
- executing Blender commands, writing Python scripts, or generating scene/render artifacts
- designing lighting setups or materials (owned by
lighting-material-plan)
- validating or scoring completed scene framing (owned by
composition-quality-checker)
- locking output resolution/aspect standards (owned by
resolution-aspect-decision) or file formats (owned by output-format-decision)
References
1---2name: camera-composition3description: Plan hero camera framing, 35-105mm focal lengths, composition hierarchy, and web copy-safe negative space before lighting or rendering.4metadata:5 source: https://skillmd.com/skills/thanhnguyxnorg/camera-composition6---78# camera-composition910## Purpose11Design high-quality composition/camera strategy for product hero scenes in plain, actionable language.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- expanding an upstream scene brief from `product-hero-scene-planner` into detailed framing and camera direction21- defining focal hierarchy, viewer attention path, camera angle, focal length mood, and depth layering before lookdev22- aligning hero framing and negative space with web/UI copy overlays2324## When not to use25<!-- blendops:generated:start exclusions -->26- as proof of rendered output quality or to validate an existing framing → use `../composition-quality-checker/SKILL.md` (use composition-quality-checker)27- to design lighting rigs or surface materials/lookdev → use `../lighting-material-plan/SKILL.md` (use lighting-material-plan)28- to lock final pixel resolution or output aspect specs → use `../resolution-aspect-decision/SKILL.md` (use resolution-aspect-decision)29- to choose delivery file formats → use `../output-format-decision/SKILL.md` (use output-format-decision)30- when subject intent is undefined → use `../product-hero-scene-planner/SKILL.md` (Delegates out-of-scope requests to product-hero-scene-planner)31<!-- blendops:generated:end exclusions -->3233## Trigger phrases34<!-- blendops:generated:start triggers -->35- "improve composition and camera"36- "choose hero framing"37- "set camera strategy for product hero"38<!-- blendops:generated:end triggers -->3940## Prerequisites / readiness41- upstream scene concept from `product-hero-scene-planner` (or clear subject and destination context) available42- planning-only boundary accepted: runtime status remains `Not Run` and artifacts remain `Not Produced`4344## Input schema4546### Required inputs47- subject intent (from `product-hero-scene-planner` or user brief)48- target output context (web/app/game/render)4950### Optional inputs51- target aspect ratio constraints (from `resolution-aspect-decision` if already locked)52- UI/copy overlay constraints53- cinematic vs neutral tone preference5455### Assumptions to confirm56- need for negative space57- focal detail priority58- camera motion vs static hero shot intent5960## Output schema6162### Primary output63- composition-camera plan with plain-language rationale6465### Secondary output66- fallback framing variant for uncertain constraints6768### Evidence / caveat output69- unresolved visual assumptions70- explicit truth states: Runtime `Not Run`, Artifacts `Not Produced` (downgrade-only, never upgrade)7172## Required laws73- ../../laws/non-blender-user-language.md74- ../../laws/evidence-before-done.md75- ../../laws/official-runtime-only.md76- ../../laws/no-arbitrary-python-interface.md7778## Official runtime boundary79Planning-only skill: no Blender execution, no Python scripts, and no artifact generation. Runtime status stays `Not Run` and artifacts stay `Not Produced` (truth states are downgrade-only, never upgraded without verified evidence).8081## Operating procedure821. Define focal hierarchy (primary/secondary/background).832. Define hero-section objective and viewer attention path.843. Select aspect ratio framing strategy (deferring final resolution/aspect locks to `resolution-aspect-decision`).854. Reserve negative space for UI/text overlays if needed.865. Choose camera angle preset family.876. Set focal length guidance by mood (dramatic vs neutral).887. Define depth layering (foreground/midground/background).898. Define target silhouette/readability checks (for later validation by `composition-quality-checker`).909. Produce fallback framing variant for uncertainty.9110. Translate plan into plain-language rationale.9293## Decision tree94- If copy overlay required → prioritize negative space and silhouette.95- If product detail priority high → tighter framing and controlled depth.96- If uncertainty high → provide two options and ask preference.9798## Playbooks99- Playbook A: Full brief path — expand upstream `product-hero-scene-planner` output into primary framing + fallback variant (`Runtime: Not Run`, `Artifacts: Not Produced`).100- Playbook B: Overlay-heavy path — prioritize negative space and silhouette separation for UI/copy constraints (`Runtime: Not Run`, `Artifacts: Not Produced`).101- Playbook C: High-uncertainty path — provide two distinct framing variants with trade-off rationale and explicit caveats (`Runtime: Not Run`, `Artifacts: Not Produced`).102103## Mode handling104105### Text-only mode106- provide primary composition/camera plan and fallback variant in plain language107- report `Runtime: Not Run` and `Artifacts: Not Produced`108109### Runtime-ready mode110- provide the composition/camera plan plus explicit target criteria for `composition-quality-checker` to validate once a scene exists111- keep `Runtime: Not Run` and `Artifacts: Not Produced` during planning112113### Blocked runtime mode114- deliver full composition/camera plan and fallback variant with explicit caveats115- keep `Runtime: Not Run` and `Artifacts: Not Produced`; make no visual success claims116117## Validation checklist118- [ ] focal hierarchy explicit119- [ ] hero framing objective and attention path explicit120- [ ] aspect ratio framing strategy documented (without overriding `resolution-aspect-decision`)121- [ ] negative space policy documented122- [ ] camera angle preset rationale documented123- [ ] focal length guidance by mood documented124- [ ] depth layering (foreground/midground/background) documented125- [ ] target silhouette/readability checks documented for `composition-quality-checker`126- [ ] fallback framing variant documented127- [ ] plain-language rationale included throughout128- [ ] truth states explicitly set to `Runtime: Not Run` and `Artifacts: Not Produced`129130## Pass / Warn / Fail rubric131132| Category | Pass | Warn | Fail |133|---|---|---|---|134| Focal hierarchy | Clear primary/secondary/background priority | Partial hierarchy | Missing hierarchy |135| Framing strategy | Matches output context and includes fallback variant | Generic framing or weak fallback | Mismatched framing or missing fallback |136| Camera rationale | Specific plain-language angle, focal-length mood, and depth layering | Vague rationale or unexplained jargon | No rationale or includes Python/execution commands |137| Role & truth boundary | Stays in planning; reports `Runtime: Not Run` and `Artifacts: Not Produced` | Mild boundary overlap with lookdev/validation | Claims verified framing quality or upgrades truth states |138139## Failure handling140- Conflicting goals: provide trade-off options.141- Missing constraints: ask targeted follow-up.142- Unknown destination: use conservative web-hero defaults + caveat.143144## Troubleshooting145- Subject lost in frame: tighten framing focus, adjust camera angle preset, or increase spatial separation between foreground, midground, and background layers.146- No room for copy: widen negative space allowance and shift primary focal placement off-center.147- Flat spatial staging: adjust camera angle and focal-length perspective or increase depth-layer spacing (route lighting/material contrast issues to `lighting-material-plan`).148- Existing scene framing needs pass/fail grading: hand off to `composition-quality-checker`.149150## Best practices151- optimize for clarity before stylization152- tie each camera choice to user outcome153- preserve fallback path for uncertain constraints154155## Good examples156“Primary subject occupies center-right with left negative space for hero copy; camera 3/4 angle chosen for silhouette and depth readability.”157158## Bad examples159“Use cinematic camera.” (no context, no criteria)160161## User-facing response template162- Composition summary (focal hierarchy, attention path, negative space, depth layering, silhouette checks)163- Camera strategy summary (aspect strategy, angle preset, focal length by mood)164- Fallback framing variant165- Why this helps your goal (plain-language rationale)166- Truth states (`Runtime: Not Run`, `Artifacts: Not Produced`) and unverified assumptions167- Recommended next skill handoff168169## Anti-patterns170- skipping required laws or runtime boundary statements171- claiming runtime/artifact success without evidence172- claiming runtime or artifact states above `Not Run` / `Not Produced` (violating downgrade-only truth rules)173- writing Python code or Blender camera execution commands174- designing lighting rigs or material lookdev instead of handing off to `lighting-material-plan`175- validating rendered/viewport composition instead of handing off to `composition-quality-checker`176- locking final export resolution/aspect (`resolution-aspect-decision`) or file formats (`output-format-decision`)177- producing jargon-heavy camera specs without plain-language rationale178179## Cross-skill handoff180<!-- blendops:generated:start handoffs -->181- [upstream_reference] Upstream input from → `../product-hero-scene-planner/SKILL.md`182- [conditional] Lateral output specs (if needed) (output-format-decision) → `../output-format-decision/SKILL.md`183- [conditional] Lateral output specs (if needed) (resolution-aspect-decision) → `../resolution-aspect-decision/SKILL.md`184- [progression] Next (lookdev & lighting) → `../lighting-material-plan/SKILL.md`185- [progression] Then (validation) (scene-readiness) → `../scene-readiness/SKILL.md`186- [progression] Then (validation) (composition-quality-checker) → `../composition-quality-checker/SKILL.md`187<!-- blendops:generated:end handoffs -->188189## Non-goals190- executing Blender commands, writing Python scripts, or generating scene/render artifacts191- designing lighting setups or materials (owned by `lighting-material-plan`)192- validating or scoring completed scene framing (owned by `composition-quality-checker`)193- locking output resolution/aspect standards (owned by `resolution-aspect-decision`) or file formats (owned by `output-format-decision`)194195## References196- https://www.blender.org/lab/mcp-server/197- https://claude.com/resources/tutorials/using-the-blender-connector-in-claude198- https://docs.blender.org/manual/en/latest/advanced/command_line/index.html