Menu
Run circuit simulation (DC, tran, AC) on Virtuoso. Use when executing Spectre simulation, running analysis, or checking simulation results.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | sim-run |
| description | Run circuit simulation (DC, tran, AC) on Virtuoso. Use when executing Spectre simulation, running analysis, or checking simulation results. |
| argument-hint | ["analysis","e.g. \"tran 10us\" or \"ac 1Hz-1GHz\" or \"dc\""] |
| allowed-tools | Bash(virtuoso *) |
Execute Spectre simulation via virtuoso sim run.
Simulation must be set up first (see /sim-setup):
simulator('spectre) configureddesign(lib cell view) setmodelFile(...) configureddesVar(...) set for any parameterized variablesresultsDir(...) set# DC operating point
virtuoso sim run --analysis dc --param saveOppoint=t --timeout 120 --format json
# Transient
virtuoso sim run --analysis tran --stop 10u --timeout 300 --format json
# AC
virtuoso sim run --analysis ac --start 1 --stop 1e9 --dec 10 --timeout 300 --format json
⚠️ The ADE session binds run() to the resultsDir established when the GUI session
was first created. Changing it to any other path silently breaks run() (returns nil).
# ✅ Find the canonical path from the runSimulation script
cat <netlist_dir>/runSimulation | grep "\-raw"
# → -raw ../../../../tmp/opt_5t_ota/psf → canonical = /tmp/opt_5t_ota
# ✅ If resultsDir is nil, restore to canonical path
virtuoso skill exec 'resultsDir("/tmp/opt_5t_ota")'
# ❌ Never do this before a run — it will break run()
virtuoso skill exec 'resultsDir("/tmp/some_new_path")'
sim run now returns a clear error if resultsDir is nil instead of auto-setting it
to a temp path (which would break the ADE session binding).
Also: do not call sim setup again once a working ADE session exists — it resets
the Ocean session state and can cause run() to return nil.
After run(), check spectre.out for errors:
# Check the log
virtuoso skill exec 'resultsDir()' --format json
# Then read the spectre.out file at <resultsDir>/psf/spectre.out
# A successful run has PSF data files (dcOp.dc, tran.tran, etc.)
# A failed run only has artistLogFile, simRunData, variables_file
| run() output | Meaning |
|---|---|
| Returns resultsDir path AND PSF data files exist | Simulation completed ✓ |
| Returns resultsDir path BUT only artistLogFile/simRunData/spectre.out | Spectre failed — run() does NOT check spectre's exit code |
| Returns nil, takes <0.01s | Analysis not configured or session lost |
| Returns nil, takes >0.1s | Netlisting ran but spectre may have failed |
⚠️ run() returning a non-nil path is not sufficient proof of success. Spectre can
terminate with fatal errors (e.g., SFE-868) and run() still returns the resultsDir.
Always verify PSF data files exist:
tail -2 <resultsDir>/psf/spectre.out
# ✓ "spectre completes with 0 errors"
# ✗ "spectre terminated prematurely due to fatal error"
| Error | Fix |
|---|---|
SFE-868: ADE-generated path .../oa/lib/../models/... | Patch input.scs: replace with direct absolute model path + section=tt — see /spectre-netlist-gotchas §8 |
| SFE-868: Cannot open input file (other) | Model path wrong — verify file exists |
| SFE-675: no valid section name | Empty section "" in modelFile for .lib — remove it |
| SFE-1997: parameter not assigned | Set desVar() for the missing parameter |
| OSSHNL-116: Cannot descend into views | Subcell missing spectre view — remove instance or add view |
Import P&R (Genus + Innovus) products into Virtuoso: GDS layout, Verilog schematic/symbol, power labels, and label restyling. Four-step pipeline driven entirely from vcli skill exec — no Python bridge or GUI required. Use when: (1) user wants to pull a routed GDS or post-P&R netlist into Virtuoso, (2) layout labels look giant/unreadable after import, (3) user mentions strmin / ihdl / digital import / P&R-to-schematic flow.
Generate Virtuoso schematics from topology descriptions via vcli schematic commands. Use when: (1) user wants to draw/create a schematic in Virtuoso, (2) user says "draw the OTA" or "create the schematic", (3) after sizing is complete and ready to build the circuit, (4) user provides a topology and wants it instantiated.
Read Maestro/ADE simulation output values directly from PSF binary files — no Virtuoso GUI or bridge required. Parses maestro.sdb + active.state XML to extract output expressions, resolves the PSF directory from history.sdb, evaluates Ocean-style expressions (getData, dB20, phaseDeg, bandwidth, ymax, VF, VT…), and returns structured JSON results. Use this skill whenever: - The user asks "what is the gain / phase margin / bandwidth from the simulation?" - `maeGetOutputValue` returned nil (requires GUI results loaded in memory) - The user wants to check simulation results offline or from a script - The user wants to read PSF files / evaluate output expressions from a Maestro session - Any request involving Maestro output expressions, PSF files, or ADE results without GUI
Maestro (ADE Assembler) session management and simulation. Use when: running simulations via Maestro, configuring tests/analyses/outputs, updating design variables, reading results.
Evolve skills from vcli session history. Use when: (1) user says "根據歷史進化技能" / "evolve skills from history" / "覆盤技能", (2) after a debugging session to capture what went wrong, (3) periodic skill maintenance to close knowledge gaps revealed by real usage. Reads cmd.jsonl + per-session SKILL logs, finds failure/correction/gap signals, maps them to skills in .claude/skills/, and writes concrete improvements.
Execute SKILL code on Virtuoso. Use when running SKILL expressions, querying cellview data, listing libraries/cells, or interacting with Virtuoso programmatically.