agentleFS
codepawlcodepawl/crucible/skills/render-crucible-media/SKILL.md

render-crucible-media

Skill662 starsChanged yesterdayMITView on GitHub

Export a Crucible scene to PNG stills, render passes or an MP4 through the MCP render job tools (scene_render_submit, scene_render_status, scene_render_result) of the npm package @codepawlhq/crucible. Use when an agent must render an image or video of a scene, play a camera or light animation to video, cut shots with a timeline, add a score, write depth or object-ID passes, path trace a still, choose GPU or CPU and an encoder, or stay inside memory limits. Also for "render ảnh 3D", "render video 3D", "xuất mp4", "export Crucible", "render bị lỗi bộ nhớ", "chất lượng MSAA". Scene building is the build-crucible-scene skill.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep what you need, then scene_render_release to remove the job's files.

    line 24
  2. Distinctive:

    Every film round starts as a small, low-quality preview with sound.

    line 39
  3. Distinctive:

    Never record the screen.

    line 41
  4. Very specific:

    Use settings.motion: { "start": 0 } to play recipe tracks (camera, nodes, lights, sun, sky, effects).

    line 42
  5. Distinctive:

    Do not stop another session's process.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Export images and video from Crucible over MCP

A render job is an immutable snapshot of one scene (sessionId, else the last used) and stays tied to it. Edits made while it runs do not change it, and it does not change the scene's revision, pose or checkpoints. The MCP server must have been started with --jobs <abs private dir>; MP4 also needs ffmpeg on PATH or --ffmpeg <abs path>, and sound needs --audio <abs dir>. Without --jobs the submit call fails: tell the user which launch option is missing.

Steps

  1. scene_look first. Never submit a job for a scene you have not looked at.
  2. scene_inspect for the current revision.
  3. scene_render_submit with expectedRevision and settings. Start small: one image at 960x540.
  4. scene_render_status with the jobId until the state is terminal (completed, failed, cancelled, interrupted). Poll about every 5 to 10 seconds, and for video read the durable frame progress. Never loop tightly. Status and result answer in a short concise form by default; pass response_format: "detailed" for the full record.
  5. scene_render_result: output paths, sizes and metrics. Report the actual width and height, the backend and the seconds; memory limits can lower the size. detailed adds SHA-256 hashes and resource counters.
  6. Keep what you need, then scene_render_release to remove the job's files.
  7. scene_render_cancel stops a job; poll scene_render_status until it is cancelled before editing again.

Settings by task

TaskRead
Image, stills, video, motion clock, shots, audio, encoder, passes, path tracer${CLAUDE_SKILL_DIR}/references/jobs.md
Size, memory, GPU or CPU, time limits, verifying the file${CLAUDE_SKILL_DIR}/references/limits-and-checks.md
A job failed or the result looks wrong${CLAUDE_SKILL_DIR}/references/errors-and-recovery.md
Rendering in a source checkout with scripts/render-media.mjs (contributors only)${CLAUDE_SKILL_DIR}/references/rendering.md

Rules

  • Smallest output that meets the need: a still before a video, a 2 second slice before the full film. Every film round starts as a small, low-quality preview with sound; full quality only after sign-off.
  • Time is deterministic. A frame depends on its time only, so a seek gives the same pixels as the frame in a video. Never record the screen.
  • Use settings.motion: { "start": 0 } to play recipe tracks (camera, nodes, lights, sun, sky, effects). Without it the job holds the first pose, which is the usual reason a video is a still frame. A recipe with a timeline uses settings.timeline and rejects motion and animation.
  • A recipe whose only motion is physics (or cloth, particles) is filmed with the same motion: { "start": 0 }; the job plays the bake on the scene clock, so do not bake-motion first. Video duration defaults to the bake length.
  • Imported clips use settings.animation; the two clocks are independent.
  • For compositing, settings.transparent, settings.format (png16, exr) and settings.region are off by default; video runs up to 60 fps (references/jobs.md, Compositing output).
  • Path tracing (settings.renderer) is offline and slow: judge a still first. A video job takes it too, one trace per frame; passes, transparent, format and region need the rasterizer.
  • Do not stop another session's process. Heavy local exports run at below-normal priority, one job at a time.
  • A GLB for Blender is scene_export_glb, not a render job.

Deliver

The file path, its JSON metrics, the settings you sent and one frame you looked at. Say what was measured (frames, duration, seconds, dimensions) and what was judged by eye. Say whether anyone listened to the audio; a score needs provenance and measured loudness.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.