Skip to content
cccskills
FreePublished on GitHub

cdf-simulation

Component-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-geometry variation, good/clean SMT images, structural pose defects, and solder texture defects, from a board USD. Turns one matched prompt into one validated `cdf.CDFJob` build and its compiled JobOrder payload; it never executes a render itself. Requires a caller-supplied board USD and output root, asks for either when missing from an interactive request, and resolves optional details with fixed, documented defaults.

The English summary is being prepared. Showing the original description.

See how to install

Files included (9)

  • SKILL.md36.9 KB
  • BENCHMARK.md8.0 KB
  • evals/evals.json7.4 KB
  • references/class-filter-taxonomy.md2.3 KB
  • references/fixed-defaults.md17.7 KB
  • references/payload-contract.md11.4 KB
  • references/reference-flows.md17.1 KB
  • skill-card.md4.9 KB
  • skill.oms.sig5.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

cdf-simulation

Turns DIG Flow Catalog prompt templates and equivalent direct requests into cdf jobs through the declarative Python API. This skill is the component-owned guidance for cdf-simulation: a caller supplies a board USD and output root, this skill builds and compiles the job, and the caller can pass the payload to its own executor. Airflow may inject those required inputs, or the caller may provide them directly. If either is missing and interaction is possible, ask once. All optional ambiguity is resolved with fixed, documented defaults. If a request truly cannot be served (an unsupported defect type, a non-USD input), say so rather than guessing at a fake capability or silently doing nothing.

This skill does not execute. It produces a validated CDFJob build and its compiled JobOrder payload, then stops. An Airflow DAG or another executor chosen by the caller performs rendering.

Catalog coverage

This skill implements five DIG Flow Catalog rows, all taking a board USD as input:

#RowStatus
1Golden board (THT)Implemented
2Variation type (THT pin geometry)Implemented
3Good images (SMT)Implemented
4Structural defects (SMT)Implemented
5Texture defects (SMT solder)Implemented, except bridge (unsupported — see below)

Reference flows

Beside the catalog rows, the skill serves the five reference flows in references/reference-flows.md: complete inspection jobs, each phrased as one prompt whose compiled plan must equal the equivalent YAML config. A prompt carrying a flow marker -- a scan grid and "stitched", a defect on a named refdes ("shift on C33", "insufficient solder on J17", "missing-component defect on LS1"), "component-focus" or "pin-focus" crops -- is a flow, not a catalog row, and takes its fixed values from that file (they differ from the catalog defaults: shift is translate_range=0.5, rotate_z_range=5.0 with no variant_index, crops are ROI captures rather than postprocess.crop).

FlowPrompt marker
G golden scan"golden board dataset ... NxM scan ... stitched" (single board or panel)
C component defects"shift/tombstone/sideflip/reverse polarity on <refdes>" + "component-focus crops"
S SMT solder defects"insufficient/excess/interrupted/missing solder on <refdes>" + "component-focus crops"
M missing component"missing-component defect on <refdes>"
T THT solder defectssix THT solder defects on refdes + "pin-focus crops from the bottom" (single board or panel)

Fixed defaults

Every unspecified optional detail resolves to a documented default rather than a question. The full table -- board identity and paths, the rule that a named component must resolve on the attachment, THT board requirements, pin-variation magnitude ranges, the required structural-defect magnitudes (translate_range, rotate_z_range, angle_range -- the API has no defaults for these and a catalog prompt never states them), the coverage ratio, how multiple defect types combine, and the solder texture-defect mapping -- is in references/fixed-defaults.md.

Read it before building any script. The values are not obvious and several of them are load-bearing: the coverage ratio applies to structural and solder defects, and the crop class_filter taxonomy is not the same as component_types.

Payload contract

What this skill returns to its caller, what it accepts, and how each value is validated is in references/payload-contract.md. The short version: the output is a CDFJob build plus the compiled JobOrderPlan from job.compile_orders(...), serialized with JobOrderCodec.dumps(plan) (a bare plan.model_dump() is not JSON-serializable), together with a resolved-inputs summary naming every default that applied. The caller supplies the board USD and output root -- both required, with no fallback. This skill supplies everything else from the catalog row and fixed defaults, and marks each variant for an independent process.

Instructions

Four steps, in order. Step 1 decides everything downstream, so do not start writing a script before the row is settled.

  1. Match the prompt to exactly one catalog row or one reference flow. Check the flow markers first (references/reference-flows.md, "Routing"): a named refdes target, a scan grid with "stitched", "component-focus" / "pin-focus" crops. With a marker present the prompt is that flow; without one it is a catalog row. A prompt matching no row and no flow explains the supported request shapes and asks the caller to choose one; it never assembles a best-effort substitute out of the pieces that do exist.
  2. Resolve every input from the precedence order in Inputs. Anything still unset takes its documented default from references/fixed-defaults.md.
  3. Build one cdf.CDFJob script, following the row's shape in Workflow. One job per variant: the executing side must launch each variant as its own process, because sequential job.capture.render(...) calls in one process crash the second Kit subprocess -- so the payload says one variant, never a loop.
  4. Validate, then return -- compile the job with job.compile_orders(...), read the result, and return the build plus the compiled plan to the caller. Do not call render() here. Report what was assumed alongside the payload.

Inputs

Each value is resolved from the first source that supplies it:

state file -> explicit prompt arguments -> agent context -> user prompt text

InputRequiredWhere it comes from if unset
Catalog rowyesMatched from the prompt shape; no default. No match asks the caller to choose a supported shape
Board USD (attachment path)yes, caller-providedNo fallback. Ask for a missing path when interaction is possible; for non-interactive automation, stop with refusal case 3. Never substitute a sample board
Output rootyes, caller-providedNo fallback. Ask for a missing path when interaction is possible; for non-interactive automation, stop with refusal case 3. Never synthesize a directory
Component sidecaroptional legacy inputPrefer embedded USD metadata with source="usd". Attach a matching <stem>.components.json only when a legacy standalone board relies on it or the caller explicitly selects that source; file presence alone does not select it. Instanced panels require embedded metadata
Board root_pathnoRead from the supplied stage, or from the selected legacy sidecar for a sidecar-backed board. For instanced panels follow references/reference-flows.md, "Panels". Opening the attachment is required; an unreadable or unresolved board stops with refusal case 3. Never use another board's root as a fallback
Named componentfrom the promptPassed through as named when present in the selected metadata source (embedded USD by default, or an explicitly selected legacy sidecar -- list types, do not guess); a missing name is refusal case 4, never substituted. State the check in the run summary
Component typesnoThe row's documented set
Seed, scan grid, board side, resolution, pin numbers (flows)noExplicit prompt arguments in the forms listed in references/reference-flows.md ("Seed 7", "a 5x4 scan", "of the bottom side", "at 2000x2000", "(pin SH)"); otherwise that file's per-flow defaults
Panel instancesfrom the attachmentWhen the attachment composes one board as several USD instances (<root>/StepRepeats/SR_*), register all of them with job.scene.instances(...); image budgets multiply by the instance count (references/reference-flows.md, "Panels")
Coverage rationoThe single documented ratio, applied to structural and solder defects; the executing side selects max(1, int(pool * ratio)), so a non-empty selection always yields at least one defect
Defect magnitudesnoThe per-type ranges in references/fixed-defaults.md
class_filternoNone. Never a component-type string -- different taxonomy

State what was resolved and from where in the run summary so the caller can see which defaults applied.

Workflow

1. Match the prompt to a catalog row

Use the sample-prompt phrasing in the table under "Catalog coverage" and in "Examples" below to classify the request into exactly one of rows 1-5.

If a prompt does not clearly match any of the rows or a reference flow, explain the supported request shapes and ask the caller to choose one.

2. Resolve inputs deterministically

Extract from the prompt: attached USD path, output root, named component(s), variation/defect type, "full board coverage" flag. Then open the attachment and read two things from it: the board root and its component types, using embedded metadata by default or the selected legacy sidecar for a sidecar-backed standalone board. A named component that appears in those types is used as named; a name that is absent is refusal case 4 -- never a substitution. Apply the fixed defaults above for optional details the prompt does not specify, and record both reads (root source, component check) in the run summary.

The attachment path and the output root are the two inputs with no default. If either is absent and interaction is possible, ask for it once. For non-interactive automation, stop and report it (refusal case 3). Never substitute a sample board or invent an output directory. Prefer embedded USD metadata. Attach a component sidecar only when a legacy standalone board relies on it or the caller explicitly selects it; do not switch sources merely because a .components.json file is nearby. Keep all metadata-dependent calls on that source. Instanced panels cannot use legacy component sidecars.

3. Build the CDFJob script

import pcb_aoi before constructing the job. The "pcb-aoi" domain registers on import; without that import CDFJob(domain="pcb-aoi", ...) raises unknown domain 'pcb-aoi' (registered: none) on the very first line. Every template below assumes import pcb_aoi and from cdf import CDFJob at the top of the script.

Every row requires job.capture.renderer(mode="pathtracing", resolution=..., spp=..., total_spp=..., max_bounces=...) before capture.camera/scan_grid/outputs -- it is a required field, compile_orders() rejects a plan missing it ("capture render pass 'default' is missing: renderer"). Every template below assumes this call is present even where not shown explicitly.

capture.camera(rotation_range=...) is required, not optional -- only side= has a default. A top-side capture with no rotation asked for still needs rotation_range={"z": 0}; omitting the kwarg is a TypeError before anything is compiled.

Several operations.add_* calls have required magnitude kwargs with no defaults (add_shift needs translate_range and rotate_z_range; add_tombstone and add_sideflip each need angle_range). A catalog prompt never states them, so they come from the fixed table in references/fixed-defaults.md -- do not invent a number and do not ask.

Declaration order matters and is enforced. job.scene.select_components(...) must be declared before job.annotations.label_components(...) -- compile_orders() rejects the reverse order with annotations.components.apply requires component selection to be declared first. Every template below follows select → (operations) → annotate.

scene.select_components(source=..., types=None) without types= needs either USD-embedded component metadata or source="components" pointing at an attached sidecar -- bare source="usd" with no types and no sidecar fails at runtime with component selection needs explicit types or board metadata. Prefer confirmed embedded USD metadata. For a legacy standalone board that requires a sidecar, attach its matching file with job.scene.attach_sidecar(name="components", kind="pcb.components", path=...) and use source="components" consistently. Do not mix that source with embedded metadata or attach a sidecar solely because the file exists.

Generate a standalone script with imports, build_job() -> CDFJob, an argparse CLI accepting --usd-path and --output-dir, and main(), using the per-row template below -- or, for a reference flow, the flow's template and shared conventions in references/reference-flows.md (explicit source="usd", output_start(0), limits(...), realtime_subframes=1, the three-key camera rotation), which are the spellings the YAML interpreter produces. Place generated PCB scripts under pcb_aoi/examples/ only if the run is meant to be durable/reusable; for a one-off request, build and compile the job in-memory, then emit the payload (references/payload-contract.md) without necessarily writing a file to disk. Execution belongs to the caller's chosen executor, never this skill.

Row 1 — Golden board (THT): the template uses embedded USD metadata. For a legacy sidecar-backed standalone board, attach its matching component sidecar and use its job-local source name consistently instead of "usd".

job = CDFJob(domain="pcb-aoi", random_seed=0)
job.scene.configure(usd_path=..., root_path=...)  # root confirmed on the supplied stage
job.scene.select_components(types=[<the attachment's component family>], source="usd")
job.appearance.lighting(mode="white_light", exposure_range=(0.0, 0.0),
                         cone_angle_range=(120.0, 120.0), cone_softness_range=(1.0, 1.0),
                         dome={"intensity": (1000.0, 1000.0), "visible": True})
# The catalog's golden board carries PROCEDURAL solder: joints are generated,
# no defect is applied. `procedural` is valid here precisely because no
# add_* solder-defect call follows (those require surface_evolver).
job.operations.solder_joints(solver="procedural", component_types=[<the same family>], source="usd")  # component_types names the family the joints are generated for. With a sidecar attached, this reads source="components" too -- all three source= arguments in a row must name the same metadata source
job.annotations.label_components(source="usd")  # likewise source="components" when the sidecar is attached
job.capture.renderer(mode="pathtracing", resolution=(1920, 1080), spp=1, total_spp=32, max_bounces=4)
job.capture.camera(side="bottom", rotation_range={"z": -90})
job.capture.scan_grid(x_count=1, y_count=1)
job.capture.outputs(rgb=True, bounding_box_2d_tight=True,
                     semantic_segmentation=True, colorize_semantic_segmentation=True)
# No postprocess.crop() call -- this row has no crop.

camera_path/camera_xform_path/ring_light_root are optional (scene.configure's default is None) -- omit them rather than assuming the /World/camera_light/... Allegro rig exists verbatim on every board; the pipeline falls back to a synthesized camera when unset.

Row 2 — Variation type (THT pin geometry):

job = CDFJob(domain="pcb-aoi", random_seed=0)
job.scene.configure(usd_path=..., root_path=...)  # a board that authors pcba:mesh:role -- see below
job.appearance.lighting(mode="white_light", exposure_range=(0.0, 0.0),
                         cone_angle_range=(120.0, 120.0), cone_softness_range=(1.0, 1.0),
                         dome={"intensity": (1000.0, 1000.0), "visible": True})
job.operations.pin_variation(components=[<THT refdes>], offset_range=(0.1, 0.4))  # or tilt_range/cut_angle/height_variation
job.capture.renderer(mode="pathtracing", resolution=(1920, 1080), spp=1, total_spp=32, max_bounces=4)
job.capture.camera(side="bottom", rotation_range={"z": -90})
job.capture.scan_grid(x_count=1, y_count=1)
job.capture.outputs(rgb=True)

Row 2 needs a board whose through-hole leads are authored with the pcba:mesh:role schema (pkg_lead meshes); a THT board without it cannot run pin_variation at all (see "THT board requirements" in references/fixed-defaults.md). pin_variation(...) targets leads directly by components=/package_types= -- it does not need scene.select_components(...) or annotations.label_components(...) declared first (unlike every other row). Selector: the refdes the prompt names, confirmed on the attachment; with no part named, see the selector rule in references/fixed-defaults.md.

Row 3 — Good images (SMT): board-level ("20 good PCB images") uses capture.scan_grid(x_count=X, y_count=Y) where X * Y is the requested count, not N in each axis -- scan_grid(x_count=20, y_count=20) is 400 renders, not 20. Pick the most square factorisation at or just above the ask (20 -> 5x4; 30 -> 6x5; a prime like 17 -> 5x4 = 20 and say so), no crop, select_components(types=[<every component family the attachment carries>], source="usd") -- the families are read from the attachment (pcba:component:footprintId), so on a one-family board the list has one entry (e.g. types: [C_0805_2012Metric]); a bare select_components(source="usd") with no types= compiles to a different plan (types: null). Component-level ("good images of <component>, max 3") narrows first with select_components(types=[<component_type>], source="usd"), then after the same capture block adds job.postprocess.crop(method="bbox_tight", types=["rgb", "semantic_segmentation", "component_instance"], class_filter=None, offset=10, xform_depth=7, output_subdir="cropped") and caps capture.limits(max_images=3) (or the requested max). class_filter=None, never the component-type string -- see "Pitfall: class_filter is not component_types" below: class_filter=["PASSIVE_SMD_0805"] compiles and executes with "error": "" but silently produces zero crop files, because annotations.label_components assigns the semantic class "capacitor" to that component, not the literal type string. No solder or structural-defect operations for this row -- clean/golden only; output stops at the rendered/cropped RGB.

Board-level Row 3, complete (only the grid and the render size come from the prompt):

job = CDFJob(domain="pcb-aoi", random_seed=0)
job.scene.configure(usd_path=..., root_path="/Board")                       # the attachment's default prim
job.scene.select_components(types=[<all families of the attachment>], source="usd")
job.appearance.lighting(mode="white_light", exposure_range=(0.0, 0.0),
                         cone_angle_range=(120.0, 120.0), cone_softness_range=(1.0, 1.0),
                         dome={"intensity": (1000.0, 1000.0), "visible": True})
job.annotations.label_components(source="usd")                              # always: the good images ship their labels
job.capture.renderer(mode="pathtracing", resolution=(1920, 1080), spp=1, total_spp=32, max_bounces=4)
job.capture.camera(side="top", rotation_range={"z": 0})
job.capture.scan_grid(x_count=X, y_count=Y)                                 # X * Y = the requested count
job.capture.outputs(rgb=True, bounding_box_2d_tight=True,
                     semantic_segmentation=True, colorize_semantic_segmentation=True)
# no operations, no postprocess.crop

Row 4 — Structural defects (SMT): the same SMT scene as Row 3, with pose operations declared after select_components and before label_components, then operation labels and the per-component defect crop. Rows 4 and 5 always emit per-component defect crops -- this is the one output contract for both rows (references/class-filter-taxonomy.md): annotations.enable_operation_labels(namespace="defect") puts the defect class in the segmentation output, and the same postprocess.crop(...) block as Row 3's component-level case follows the capture. A record with no file under cropped/ is a failed record, not a board-level variant. The narrowed select_components(types=[...]) is the scope of every pose operation; whether add_tombstone also takes component_types= depends on the attachment's metadata source -- see "Scoping by metadata source" below.

This legacy standalone-board example uses a component sidecar (the CAD_BOARD board used by pcb_aoi/examples/allegro_defect_job.py); on an embedded-metadata board use source="usd" throughout and the tombstone scoping below.

job = CDFJob(domain="pcb-aoi", random_seed=0)
job.scene.configure(usd_path=..., root_path="/Board_CAD_BOARD")
job.scene.attach_sidecar(name="components", kind="pcb.components", path=...)  # sidecar board
job.scene.select_components(types=["PASSIVE_SMD_0805"], source="components")  # the scope of every pose op
job.appearance.lighting(...)                              # same block as Row 1
job.operations.add_tombstone(ratio=0.2, angle_range=(70.0, 90.0))
# job.operations.add_shift(ratio=0.2, translate_range=0.2, rotate_z_range=15.0)
# job.operations.add_sideflip(ratio=0.2, angle_range=(70.0, 90.0))
job.annotations.label_components(source="components")
job.annotations.enable_operation_labels(namespace="defect")
job.capture.renderer(mode="pathtracing", resolution=(1920, 1080), spp=1, total_spp=32, max_bounces=4)
job.capture.camera(side="top", rotation_range={"z": 0})
job.capture.scan_grid(x_count=1, y_count=1)
job.capture.outputs(rgb=True, bounding_box_2d_tight=True,
                    semantic_segmentation=True, colorize_semantic_segmentation=True)
job.postprocess.crop(method="bbox_tight", types=["rgb", "semantic_segmentation", "component_instance"],
                     class_filter=None, offset=10, xform_depth=7, output_subdir="cropped")

One defect type per script when the prompt wants one image set per type (see "Tell the executing side: one render() per process" below); all three in one script only when the prompt wants a board carrying all three at once.

Scoping by metadata source. add_shift and add_sideflip have no component_types= kwarg, so the narrowed select_components(types=[...]) is always their scope. add_tombstone does have one, and whether to use it is decided by where the attachment's component metadata lives:

  • Embedded USD metadata (pcba:* schema, no sidecar -- every pcb-builder export): narrow with select_components(types=[...], source="usd"), pass eligibility_source="usd", and omit component_types. Supplying it applies the operation to nothing: the list resolves to prim paths the stage does not carry and the run fails with tombstone selected from 1 components but applied none of them.
  • Sidecar board (<stem>.components.json attached): component_types=[...] on add_tombstone works there and may accompany the narrowed selection. It is never a substitute for narrowing the selection, and it is never carried over to an embedded-metadata board.

Row 5 — Texture defects (SMT solder): as Row 4 -- same operation labels, same outputs, same per-component defect crop -- but operations.solder_joints(...) is declared once before any add_* solder call, and the solver must actually be available in the executing environment. The solder add_* calls take ratio only (no count) and their component_types= works on both metadata sources.

The following is a legacy sidecar-backed standalone-board example. Prefer source="usd" for embedded-metadata boards and omit attach_sidecar(...).

job = CDFJob(domain="pcb-aoi", random_seed=0)
job.scene.configure(usd_path=..., root_path="/Board_CAD_BOARD")
job.scene.attach_sidecar(name="components", kind="pcb.components", path=...)  # sidecar board
job.scene.select_components(types=["PASSIVE_SMD_0805"], source="components")   # embedded-metadata board: types=[<family>], source="usd"
job.appearance.lighting(...)                              # same block as Row 1
job.operations.solder_joints(solver="surface_evolver", component_types=["PASSIVE_SMD_0805"], source="components")  # component_types = the selected family
job.operations.add_excess(ratio=0.2, component_types=["PASSIVE_SMD_0805"])
# chain further supported types here, e.g.
# job.operations.add_missing_solder(ratio=0.2, component_types=["PASSIVE_SMD_0805"])
job.annotations.label_components(source="components")
job.annotations.enable_operation_labels(namespace="defect")
job.capture.renderer(mode="pathtracing", resolution=(1920, 1080), spp=1, total_spp=32, max_bounces=4)
job.capture.camera(side="top", rotation_range={"z": 0})
job.capture.scan_grid(x_count=1, y_count=1)
job.capture.outputs(rgb=True, bounding_box_2d_tight=True,
                    semantic_segmentation=True, colorize_semantic_segmentation=True)
job.postprocess.crop(method="bbox_tight", types=["rgb", "semantic_segmentation", "component_instance"],
                     class_filter=None, offset=10, xform_depth=7, output_subdir="cropped")

solder_joints(solver="surface_evolver") resolves the solver inside that call: with manifold3d or the native evolver binary missing it raises there, before compile_orders() is reached. See references/fixed-defaults.md — a Row 5 script cannot even be dry-run validated in an environment that lacks them.

Pitfall: class_filter is not component_types

postprocess.crop(class_filter=...) takes a derived semantic class, not a component-type string. Given the latter it compiles, reports "error": "", and writes zero files. Default to class_filter=None and filter with types=. Worked example and the two taxonomies side by side: references/class-filter-taxonomy.md.

4. Validate, then return -- do not execute

Run job.compile_orders(output_dir=...) to catch a malformed script before anyone spends Isaac boot time. A clean compile is where this skill's job ends: return the CDFJob build, the compiled JobOrderPlan, and the resolved-inputs summary to the caller, in the shape references/payload-contract.md defines. Do not call job.capture.render(...) from here -- this guidance is read, not run, and execution belongs to the caller's chosen executor. Report what was returned; do not claim images were generated, because at this point none have been.

Tell the executing side: one render() per process. Running several variants (for example shift, tombstone and sideflip) sequentially in one Python script crashes the second render(): the Kit subprocess segfaults mid-run (carb.crashreporter-breakpad fatal trace), while each variant as its own process runs cleanly. This matches documented Isaac/replicator fragility around rebuilding the render graph mid-session. So when a prompt implies several output variants ("generate shift, tombstone, and sideflip defects"), emit one payload per variant and mark them as independent launches -- never a loop of render() calls inside one script.

Examples

PromptRowKey resolved values
"Generate a golden board image using the attached USD"1bottom camera, solder_joints(solver="procedural") with no defect calls, rgb+bbox+semantic, no crop
"Using the attached USD, generate images with tilt variation of J13"2tilt_range=(5.0, 15.0), components=["J13"]
"Using the attached USD, generate images with cut variation of J13"2cut_angle=(5.0, 15.0)
"Generate 20 good PCB images using the attached USD"3board-level, scan_grid(x_count=5, y_count=4) = 20 images, no crop
"Generate good images of PASSIVE_SMD_0805, max 3"3select_components(types=["PASSIVE_SMD_0805"]), component-level crop, max_images=3 (a component the attachment does not have is refused, case 4 -- never substituted)
"Using the attached USD, generate tombstone structural defects"4add_tombstone(ratio=0.2, angle_range=(70.0, 90.0)) (no coverage phrase → default ratio, which still yields at least one defect on a non-empty selection; angle_range is required and comes from the fixed table); enable_operation_labels + per-component crop as on every row 4/5 record
"Generate shift structural defects for PASSIVE_SMD_0805, with full board coverage"4select_components(types=["PASSIVE_SMD_0805"]) then add_shift(ratio=1.0, translate_range=0.2, rotate_z_range=15.0); labels + crop
"Using the attached USD, generate excess solder on the passives"5solder_joints(solver="surface_evolver") + add_excess(ratio=0.2, component_types=["PASSIVE_SMD_0805"]); labels + crop
"Generate excess solder and missing solder defects for PASSIVE_SMD_0805"5one solder_joints(...) declaration, then add_excess(ratio=0.2, ...) and add_missing_solder(ratio=0.2, ...) chained (see "Combining multiple supported defect types")
"Using the attached USD, generate bridge defects on the ICs"5Fail loudly — bridge unsupported

When to refuse

Four cases follow. Each states plainly what was not done and why, produces no substitute, and — where part of the request is servable — still delivers that part.

1. bridge mixed with supported solder defects. Partial fulfilment, not refusal: generate exactly the supported types named, drop the bridge clause, report it.

Requested: bridge and excess solder. Generated: excess solder only (add_excess(ratio=0.2, component_types=["PASSIVE_SMD_0805"]), 1 variant, output at <dir>). Not generated: bridge — solder shorting between adjacent pads/leads has no method in the current cdf API. Available texture defects: insufficient, excess, bright, interrupted, missing_solder, dry_contact. I did not add any of those to make up the count, and did not approximate a bridge from the ones that exist.

2. A board whose real metadata is being overridden by the defaults. The CAD_BOARD values belong to the CAD_BOARD example board only.

Not run. The attached USD carries its own metadata (a <name>.components.json sidecar, or embedded pcba:* metadata whose default prim is the board root) naming a different board root, so applying the CAD_BOARD values would silently render the wrong board identity — a mismatch that does not show up in the image. Re-run with that board's own root_path, or confirm the values are genuinely intended for it.

3. No board USD, or no output root. Both are required caller inputs. An attachment that is not a USD stage (for example a photograph) counts as no board USD. Ask the caller to provide the missing value when interaction is possible. In non-interactive automation, stop; do not substitute a sample board for the attachment or synthesize a directory for the output root.

Not built. This request carries no board USD (or: no output root). Both are required caller inputs and have no defaults; images are not accepted as the board input. Provide a USD attachment path and the output root.

4. A named component the attachment does not have. A validation failure, not a substitution. Check component types and refdes in the selected metadata source (embedded USD by default, or the selected legacy sidecar); if the named one is not there, build nothing.

Not built. The prompt names <name>, which the attached board does not have (checked: <sidecar types | embedded component types>: <list>). Rendering another component in its place would deliver a dataset for the wrong part. Re-run naming one of the listed components, or attach the board that carries <name>.

What none of these do: assemble a lookalike out of the capabilities that do exist, or report success for a run that did not happen. This skill returns a payload and never renders, so it never has grounds to say images were generated -- that report comes back from the executor, or not at all.

Guardrails

  • Ask only for a missing board USD or output root when interaction is possible. Apply fixed defaults for optional details and state what was assumed in the run summary.
  • Never invent a component name, prim path, or API method that was not confirmed in this repo's own code (pcb_aoi/sections.py, pcb_aoi/examples/*.py, cdf/API_SPEC.md). If something needed does not exist (for example bridge defects), say so plainly.
  • Never build on a board root that was not read from the attachment. The CAD_BOARD paths belong to the CAD_BOARD example board; an attachment that could not be opened is refusal case 3, not a reason to assume that board. Confirmed metadata includes the embedded USD default prim, not only a sidecar.
  • Never substitute a component for one the prompt names. Check the attachment's component types first: pcb-builder footprint names (C_0805_2012Metric, R_0603_1608Metric, SOT-723) look unfamiliar and are real, and a name the attachment does not have is refusal case 4.
  • Never substitute a sample board for a missing attachment, or a synthesized directory for a missing output root. Both are required caller inputs; ask when interaction is possible or stop non-interactive automation (refusal case 3).
  • Never hand off a defect record whose selection is empty, and never describe a zero-defect outcome as the default doing its job: on a non-empty selection the executing side applies at least one defect (max(1, int(pool * ratio))), and a clean board on a defect request is a failed record.
  • Never claim that a postprocessing step which does not exist in this repo was applied.
  • Never execute from this skill. Compile, then return the build and the JobOrderPlan to the caller. A render() call here is a bug, not a shortcut.
  • Never pass a component-type string to postprocess.crop(class_filter=...) — it is a different taxonomy than component_types/types= and will silently produce zero crop files with no error. Default to class_filter=None.

Limitations

  • bridge solder defects are unsupported; the other texture defects in row 5 are.
  • One variant per process, on the executing side. Sequential job.capture.render(...) calls in a single Python process segfault the second Kit subprocess, so each payload this skill emits is one variant and is marked as an independent launch.
  • Guidance only. This skill compiles and returns a payload; it does not render. The caller's executor owns execution, and this skill has no view of the run's outcome beyond what is reported back.
  • Requires a USD input. Images or photographs are not accepted as the board input.
  • Two required caller inputs. The board USD and output root may be supplied directly; non-interactive automation must inject both. Optional ambiguity resolves to the documented defaults.
  • The defaults are documented, not universal. A different board needs its own confirmed metadata, not the CAD_BOARD values.

Troubleshooting

ErrorCauseSolution
"error": "" but zero crop filesA component-type string was passed to postprocess.crop(class_filter=...), which is a different taxonomy from component_typesUse class_filter=None; filter by types= instead
Second render segfaults (reported back by the executor)Two job.capture.render(...) calls in one Python processEmit one payload per variant, each marked as an independent launch; never a render() loop
This skill was asked to renderA caller treated component guidance as an executorCompile and return the JobOrderPlan; execution belongs to the caller's chosen executor
select_components returns nothingThe sidecar and the board USD disagree, or the source is wrong for that boardConfirm the sidecar belongs to that board; check source= against the row
A defect request rendered a clean board with exit 0The selection was empty (types= matched nothing on that attachment); a non-empty selection always yields at least one defectCheck types= against the attachment's own metadata; do not hand off a plan whose selection is empty
Row 4/5 record with no file under cropped/enable_operation_labels(...) or postprocess.crop(...) was left off the record, or class_filter carried a component-type stringBoth calls are part of the Row 4/5 contract; class_filter=None
Compile error naming an unknown operationAn API method was invented rather than confirmedCheck pcb_aoi/sections.py and cdf/API_SPEC.md; if it is absent, the capability does not exist
Prompt matches nothing in the catalogA request shape this skill does not coverExplain the supported shapes; do not substitute
pin_variation found no through-hole leadsThe board does not author pcba:mesh:role lead meshesReport that the board's THT metadata is insufficient for pin-geometry variation; do not retry with invented parameters

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Move pandas-style table processing to NVIDIA GPUs using cuDF. Choose minimal-change acceleration or explicit GPU code, handle joins and aggregations, compare results with pandas, and use dask-cuDF when data exceeds GPU memory.

  • Accelerate existing pandas processing with minimal changes
  • Move joins and aggregations to GPU code
  • Compare missing values and ordering with pandas
NVIDIA/skills3.7KUpdated Oct 22, 2026

Customize NVIDIA Nemotron Voice Agent’s Generic Pipecat example for appointment scheduling, five-field patient intake, or a custom healthcare conversation. Build prompts and tool handlers without a separate backend, then validate conversation behavior, services, and voice interaction.

  • Build an appointment-scheduling voice agent
  • Collect five patient-intake fields through conversation
  • Design a custom healthcare conversation with tool calls
NVIDIA/skills3.7KUpdated Oct 22, 2026

Calibrate live cameras by recording their RTSP video streams through VIOS and processing the clips with AutoMagicCalib. The workflow imports settings and alignment files, checks readiness, tracks calibration progress, and retrieves results.

  • Calibrate cameras from live RTSP streams
  • Import settings and alignment files for a camera scene
  • Retrieve evaluation statistics using ground truth data
NVIDIA/skills3.7KUpdated Oct 22, 2026

Test a running AMC service with the bundled four-camera warehouse dataset. Run camera calibration from upload to completion, then check distance and image projection errors against ground-truth data to verify the installation.

  • Verify a newly installed AMC service
  • Check the sample's calibration errors against ground truth
  • Walk through the sample workflow in Swagger UI
NVIDIA/skills3.7KUpdated Oct 22, 2026

Calibrate multiple cameras from recorded MP4 files through the AutoMagicCalib REST API. The skill handles project creation, uploads, input verification, progress checks, and evaluation when reference data is supplied, with optional VGGT refinement.

  • Calibrating cameras from synchronized MP4 recordings
  • Uploading local settings and alignment files
  • Evaluating calibration against ground-truth data
NVIDIA/skills3.7KUpdated Oct 22, 2026

Set up AutoMagicCalib from NGC release containers using Docker Compose. The skill handles registry authentication, port and path configuration, optional VGGT model download, service startup, and readiness checks for the backend and web interface.

  • Launching the AutoMagicCalib backend and web interface
  • Configuring service ports and network access
  • Adding the optional VGGT model during setup
NVIDIA/skills3.7KUpdated Oct 22, 2026

See all skills by NVIDIA

Report a problem with this skill