메뉴
Analyze simulation failures by cross-referencing workspace artifacts and producing a structured debug report with fix suggestions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | debug |
| description | Analyze simulation failures by cross-referencing workspace artifacts and producing a structured debug report with fix suggestions. |
| disable-model-invocation | true |
| allowed-tools | ["Bash","Read","Write","Grep","Glob"] |
Analyze simulation failures for a hardware module by cross-referencing its workspace artifacts.
/chip-agent:debug <ModuleName>
Extract the module name from $ARGUMENTS. If empty or blank, ask the user: "Which module should I debug? Please provide a PascalCase module name (e.g., ALU, Counter, SimpleRISCV)."
Validate the module name. Must be PascalCase (starts with uppercase letter, contains only alphanumeric characters). If invalid, ask the user to provide a valid PascalCase name.
Determine the project root directory by finding the nearest ancestor directory of this skill file that contains .claude. Store as PROJECT_ROOT.
Check required artifacts exist:
workspace/<ModuleName>/spec.json -- if missing, STOP: "No spec found. Run /chip-agent:requirement-parser first."chisel-project/src/main/scala/chipagent/<ModuleName>.scala -- if missing, STOP: "No Chisel source found for <ModuleName>."workspace/<ModuleName>/sim/logs/sim_result.log -- if missing, STOP: "No simulation results. Run /chip-agent:simulate <ModuleName> first."workspace/<ModuleName>/sim/logs/<ModuleName>.vcd -- if missing, note that VCD is unavailable. Analysis will proceed in log-only mode.Read the debug-analyzer agent definition at agents/debug-analyzer.md (relative to project root).
Follow the agent's analysis instructions to:
scripts/parse_vcd.pyWrite the debug report to workspace/<ModuleName>/debug/debug_report.md following the agent's report structure. Create the directory first with mkdir -p workspace/<ModuleName>/debug.
Display a summary in conversation:
workspace/<ModuleName>/debug/debug_report.md/chip-agent:simulate <ModuleName>."$ARGUMENTS -- PascalCase module name.
workspace/<ModuleName>/debug/debug_report.md -- structured failure analysis with signal traces, root cause analysis, and fix suggestionsRun full Chipyard-to-ORFS PnR flow for large designs (SmallBOOM etc.) using All-Mock memory blackboxing in Docker: generate RTL, preprocess nosram, run multi-round ORFS synth->finish with mock SRAMs to avoid OOM.
Docker Chipyard flow: generate RTL from a Chipyard config via Docker, run SRAM mapping, stage artifacts into MyDesign, and hand off to PnR.
Run full Chipyard-to-ORFS PnR flow with multi-round parameter iteration in Docker: generate RTL from Chipyard Docker, preprocess nosram+SRAM override, run 3 rounds of ORFS synth→finish on sky130hd with progressive clock/utilization/density tuning for optimal PPA.
Run full Chipyard-to-ORFS PnR flow with multi-round parameter iteration: generate RTL from Chipyard with ENABLE_YOSYS_FLOW, preprocess nosram+SRAM override, run 3 rounds of ORFS synth→finish on sky130hd with progressive clock/utilization/density tuning for optimal PPA.
Unified Chipyard PnR flow: automatically routes to local or Docker workflow based on backend_mode setting.
Unified Chipyard flow: automatically routes to local or Docker workflow based on backend_mode setting.