菜单
Execute hardware measurements on analog blocks via scope capture + FPGA ADC read. Use when running hardware-in-the-loop verification, "measure analog", "scope capture", "read ADC", or during analog hardware tuning.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | analog-hw-measure |
| description | Execute hardware measurements on analog blocks via scope capture + FPGA ADC read. Use when running hardware-in-the-loop verification, "measure analog", "scope capture", "read ADC", or during analog hardware tuning. |
Drives the measurement instruments (oscilloscope + FPGA ADC) to capture real analog block behavior, then parses the results into a structured measurement report comparable to SPICE simulation output.
analog-hw-testbench-gen has programmed the FPGAanalog-hw-tuning-loop iterationsanalog/<block>/spec.json — specs with min/max limitsanalog/<block>/hw_test/pin_assignments.qsf — which scope channel maps to which signal| Tool | Purpose |
|---|---|
device_scope_capture | Capture transient waveform (CSV: time, voltage) |
device_scope_periodic_pulse_check | Measure frequency, duty cycle, amplitude |
eda_fpga_adc_read | Read MAX10 ADC for DC voltage (when available) |
device_camera_led_diff | Capture LED pass/fail indication |
| Block type | Key measurements | Instrument |
|---|---|---|
| LDO | Vout DC, load regulation, PSRR, transient response | ADC (DC) + Scope (transient) |
| Oscillator | Frequency, duty cycle, jitter, startup time | Scope (periodic) |
| POR | Trip voltage, hysteresis, release delay | Scope (single-shot ramp) |
| Bandgap | Vref DC, temperature coefficient | ADC (DC, sweep temp manually) |
| Comparator | Propagation delay, offset, hysteresis | Scope (transient) |
The DC/rise/settling/overshoot/freq/jitter math below is FIXED and
deterministic — do NOT re-derive it by hand each run. Once you have a
captured scope CSV (time,voltage), invoke the program so the numbers come
out identically every time:
python3 programs/scope_waveform_metrics.py <scope_csv> \
[--spec analog/<block>/spec.json] [--json analog/<block>/hw_measurements.json]
It emits {dc_level, rise_time, settling_time, overshoot, freq, jitter} and,
when a spec JSON with per-metric min/max is given, a per-spec
PASS/FAIL (a metric that cannot be computed grades SKIP, never a false
FAIL). Exit 0 = extracted / all gradeable specs PASS, 1 = a spec FAILed,
2 = IO/parse error. The program degrades gracefully: a capture shorter than
--min-samples (default 8), with no detectable edge, or non-periodic reports
the affected metric as null + a MISSING/SKIP note instead of guessing.
The frozen formulas it implements (kept here for reference / review only):
AI judgment stays with you — choosing the right instrument per block
(scope transient vs ADC DC vs periodic-pulse), setting timebase/trigger,
deciding when a capture is trustworthy, and interpreting a SKIP/MISSING
metric (re-capture vs accept) are NOT delegated to the program. The program
only freezes the arithmetic on a capture you already judged good.
analog/<block>/hw_measurements.json{
"block_name": "ldo_1v8",
"timestamp": "2026-04-29T14:30:00Z",
"measurements": {
"vout_dc": {"value": 1.803, "unit": "V", "spec_min": 1.75, "spec_max": 1.85, "status": "PASS"},
"load_reg": {"value": 0.5, "unit": "%", "spec_max": 2.0, "status": "PASS"},
"settling_time": {"value": 12.3, "unit": "us", "spec_max": 50, "status": "PASS"}
},
"scope_files": ["analog/ldo_1v8/hw_test/scope_transient.csv"],
"all_pass": true
}
hw_measurements.json → analog-hw-tuning-loop for three-way comparisonscope_response_byte_decode_check (if protocol testing)After producing your output, save it to a file and run:
python3 plugins/vibe-ic/_shared/skill_compliance_check.py \
--requirements plugins/vibe-ic/skills/analog-hw-measure/compliance.yaml \
<your_output_file>
Exit 0 = PASS, exit 1 = FAIL with specific missing elements listed.
Your task is not complete until the audit returns PASS.
MANDATORY entry point when `design_one_shot_runner.step_rtl_gen` WAIVES with `fallback_skill='spec-to-rtl'`. This is invoked for every IC class with `rtl_gen=null` in `ic_class_registry.json` (currently: digital_arithmetic_primitive, digital_cmd_driven, bare_fpga, processor_cpu, unknown_protocol_class). The runner has already (1) ingested the prompt into L1-L27, (2) detected the IC class, (3) set the expected RTL path. This skill authors synthesizable RTL into the runner's expected path so the runner's downstream gates (chip_top auto-emit, rtl_hygiene_lint --fix, eda_lint, eda_synth, eco_loop, spec_conformance_check, full_stack_tb_gen) can fire on it. Triggered automatically by the runner's WAIVE message; also fires on phrases like 'AI invokes spec-to-rtl', 'runner WAIVED rtl_gen', 'spec-to-rtl handoff'. THIS IS THE RUNNER'S INTENDED PATH — NOT BYPASS. Bypass means authoring with MCP outside the runner's pipeline (what the 2026-05-28 wrong-shape RTLLM 37/50 did).
Closed-loop core-agent that fixes plugin issues filed by the field-agent. Invoke as a cron prompt; the loop polls the repo for ANY OPEN non-PR issue (new OR reopened — no label gating, no comment classifier), reproduces and fixes the bug chip-AGNOSTIC-ally, SELF-VERIFIES (reproduce + run the cadence-correct plugin test suite the CI way), then SHIPS by DIRECT PUSH (2026-06-26 owner directive — direct commit + `git push origin main`, no PR ceremony) gated by `gatekeeper_review.py --role core-agent` (MERGE_OK) + Step-2.7 + `gatekeeper_assign_version.py --write` (the pusher assigns the monotonic version pre-push) — posts a 繁體中文 fix comment in the canonical 5-section shape (incl 本機驗證 evidence), then `gh issue close` + adds the `core-closed` label. CLOSED is the terminal state; the field-agent audits closed issues on the real benchmark and reopens any it finds inadequate.
MANDATORY before landing any change to the FLOW itself — a gate, a check, a step, a phase runner, a verdict rule, or anything under programs/ that every design passes through. Flow-level changes are foundational: when they are right every cell benefits, and when they are wrong every cell lies at once and nobody notices. This skill is the acceptance standard for that class of change: bidirectional negative control (a test that cannot fail against the pre-fix code proves nothing), corpus sweep with zero false positives, prove-by-run that a gate declared BLOCKING actually stops the flow, no design/PDK/vendor literals, an explicit BLOCKING-vs-ADVISORY declaration, and degrade-loudly-never-silently. Every criterion here was written from a measured failure in this repo, cited inline. Triggers on: authoring or reviewing a gate/check/step, 'add a gate', 'this check should catch', 'why did the flow not catch', 'land a flow fix', 'flow-level change', '流程層改動', '加一個檢查', '這個 gate 為什麼沒擋住'.
When design_one_shot_runner.step_rtl_gen WAIVES rtl_gen and ip_catalog_query has emitted matches, this skill pulls the matched open-source IP RTL into the project's canonical phase2/stage1/rtl/ directory and authors only the integration wrapper / chip-top + OpenLane config glue from L1-L27 spec. Replaces full-from-scratch spec-to-rtl authoring for SoC-class designs where pre-validated open-source IPs exist in the catalog. Triggers automatically when phase2 WAIVES with `fallback_skill=catalog-glue-author`.
Read BEFORE authoring or revising an L-layer emitter, an L-layer schema field, or a layer gate. Answers the three questions no program can decide for you — WHICH of the 27 layers a given fact belongs in (the layer that CONSUMES it, not any layer that mentions it), WHETHER the thing you are specifying is structural (closed, enumerable, correct-by-construction, therefore a program) or behavioural (no unique correct implementation, therefore synthesis and not expansion), and WHETHER a declarative layer should align to IP-XACT / SystemRDL semantics instead of inventing schema. Produces a Layer Contract Decision record. Pairs with l_doc_consumer_contract.py.
Read Static Timing Analysis reports, triage setup/hold/recovery/removal violations, and propose fixes (RTL pipelining, sizing, useful skew, buffer insertion). Use when the user says "STA", "timing report", "timing violation", "setup fail", "hold fail", "close timing", "WNS", "TNS".