BF deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI…
As a process F 46/100 · Will not run — References files that are not bundled: references/sop_architecture.svg, references/skill_01_fastapi_endpoints.md, references/skill_02_pydantic_schemas.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/sop_architecture.svg - warning
missing-refreference to a missing file: references/skill_01_fastapi_endpoints.md - warning
missing-refreference to a missing file: references/skill_02_pydantic_schemas.md - warning
missing-refreference to a missing file: references/skill_03_deepstream_pipeline.md - warning
missing-refreference to a missing file: references/skill_04_config_templates.md - warning
missing-refreference to a missing file: references/skill_05_triton_ddm_model.md - warning
missing-refreference to a missing file: references/skill_05b_custom_postprocess.md - warning
missing-refreference to a missing file: references/skill_06_sop_process_manager.md - warning
missing-refreference to a missing file: references/skill_06b_sop_checker.md - warning
missing-refreference to a missing file: references/skill_07_sse_streaming.md - warning
missing-refreference to a missing file: references/skill_08_basler_camera.md - warning
missing-refreference to a missing file: references/skill_09_docker_build_deploy.md - warning
missing-refreference to a missing file: references/skill_10_test_suite.md - warning
missing-refreference to a missing file: references/skill_11_env_variables.md - warning
missing-refreference to a missing file: references/skill_12_evaluation_workflow.md - warning
missing-refreference to a missing file: references/skill_13_verification_curl.md - warning
missing-refreference to a missing file: references/skill_14_implementation_checklist.md - warning
missing-refreference to a missing file: references/skill_15_latency_measurement.md - warning
missing-refreference to a missing file: references/skill_16_message_schema.md - warning
missing-refreference to a missing file: references/skill_17_camera_latency_measurement.md - warning
missing-refreference to a missing file: references/skill_18_rtsp_streaming_output.md - note
frontmatter-keyunknown frontmatter key "owner" - note
frontmatter-keyunknown frontmatter key "service" - note
frontmatter-keyunknown frontmatter key "reviewed"
Process rating: all ten parameters 46/100
- 0Tools and files. 21 referenced file(s) missing: references/sop_architecture.svg, references/skill_01_fastapi_endpoints.md, references/skill_02_pydantic_schemas.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4389 tokens
- 85Steps. 4 steps, 2 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 958: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.