the-openroad-project

@the-openroad-project source repo

15 skills
0 followers
7 hours ago last updated

▌
Release · the-openroad-project bundle
Prepare a new version release for the openroad-mcp project. Automates version bumping, changelog generation, lockfile updates, and release commit creation. Use this skill whenever the user asks to: - Prepare a release, cut a release, or do a release - Bump the version or update the version - Create a release commit - Ship a new version - Update the changelog for a new release Trigger on phrases like "release", "bump version", "prepare release", "cut v0.x", "ship it", "new release", or any mention of version numbers in the context of publishing. Also trigger when the user references the release process we've done before (e.g., "do the release thing", "same as last time").

0
installs
▌
Setup Openroad MCP · the-openroad-project
Install and configure the OpenROAD MCP server so an AI assistant can drive OpenROAD / OpenROAD-flow-scripts (ORFS) for physical design, timing, power, and report analysis. Handles prerequisite checks (Node.js 22+, `openroad` in PATH, optional ORFS), client registration (Claude Code, Claude Desktop, Cursor, VS Code/Copilot, Windsurf, Cline/Roo, Continue, PearAI, Zed, Docker), and a connection smoke test. Use this skill whenever the user asks to: - Set up, install, configure, or connect the OpenROAD MCP server - Add openroad-mcp to Claude Code / Cursor / VS Code / Claude Desktop / etc. - Get their AI assistant talking to OpenROAD or ORFS - Troubleshoot "OpenROAD tools not available" or "openroad not found" in an MCP client Trigger on phrases like "set up openroad-mcp", "install the OpenROAD MCP", "connect Claude to OpenROAD", "add openroad mcp to cursor", "configure ORFS for my assistant", or "the OpenROAD MCP isn't connecting".

0
installs
▌
Fix Bug · the-openroad-project
Fix an OpenROAD bug from a GitHub issue. Analyzes the issue, traces the root cause through the codebase, implements the fix, creates regression tests (registered in both CMake and Bazel), runs clang-format, and prepares a signed-off commit. Use when given a bug report issue number, error code (e.g. GPL-0305, DRT-0001, RSZ-2007), or when asked to fix a bug in any OpenROAD module (ant, cts, dpl, drt, gpl, grt, mpl, odb, pad, pdn, psm, rcx, rsz, sta, stt, tap, upf, utl, etc.). Also triggers on: "fix issue", "debug this error", "resolve crash", "fix segfault", "repair", "patch bug".

0
installs
▌
Add Test · the-openroad-project
Add integration or unit tests to an OpenROAD module. Handles the complete workflow: writing the Tcl/C++ test, generating golden files, and registering the test in BOTH CMake and Bazel build systems (the most common mistake is forgetting Bazel registration). Use when asked to add tests, improve test coverage, create regression tests, or write unit tests for any OpenROAD module (ant, cts, dpl, drt, gpl, grt, mpl, odb, pad, pdn, psm, rcx, rsz, sta, stt, tap, upf, utl, etc.). Also triggers on: "add test", "write test", "test coverage", "missing tests", "create regression test", "add unit test".

0
installs
▌
Review Pr · the-openroad-project
Review an OpenROAD pull request following the project's review priority order: correctness > QoR impact > testing > architecture > style > process. Fetches PR diff, analyzes changes, and prints draft review notes for the human reviewer to inspect and post manually. Use when asked to review a PR, check a pull request, look at changes, or provide code review for any OpenROAD module. Also triggers on: "review PR", "check this PR", "look at pull request", "code review", "review changes", "review #NUMBER".

0
installs
▌
Triage Issue · the-openroad-project
Triage an OpenROAD GitHub issue by reproducing the bug and minimizing the test case with whittle.py. Use when an issue has an attached tarball artifact (.tar.gz) from `make *_issue`.

0
installs
▌
Study Pr · the-openroad-project
Run a measurement study on the flow and publish it as a closed, reference-only bazel-orfs pull request. Covers the two kinds of patch a study carries into OpenROAD, ORFS or yosys (instrumentation that stays on the study branch, candidate fixes carried in patches/ one concern each), the edit/measure loop, the noise discipline that makes a runtime or QoR number trustworthy (byte-identical inputs, fixed and witnessed knobs, repeats with 2σ and a stated resolution, an idle machine asserted not hoped), the harness shape (manual flow targets, unit-tested parsers, a report that discovers results and says "not yet measured"), and the PR shape (study/<slug> branch, the finding as the title, graphs and tables in the body with images committed to the branch, raw data as a CSV comment, a closing comment). Use when asked to "study", "measure", "find out where the time goes", "A/B a knob or patch", or to document design decisions that go into an upstream PR.

0
installs
▌
Odb To Cpp · the-openroad-project
Convert an .odb file into a C++ header that reconstructs the design using odb API calls. Turn a whittled .odb into a self-contained C++ unit test.

0
installs
▌
Byo Openroad · the-openroad-project
Iterate on local OpenROAD source changes against a bazel-orfs flow by building the OpenROAD checkout binary and injecting it via OPENROAD_EXE (a bring-your-own / BYO loop), instead of encoding the diff as a base64 patch swapped into the archive_override. Use when developing or debugging an OpenROAD C++/TCL change that you need to exercise through an ORFS stage (cts, place, grt, route), when a long edit-build-run loop is taxing turnaround, or when a change "isn't taking effect" and you suspect a silently-rejected patch.

0
installs
▌
Debug Rtl Sim · the-openroad-project
Debug an RTL or gate-level simulation that hangs, times out, produces no output, or computes the wrong answer, without dumping logs or waveforms into context. Covers the cheapest-first ladder (which gate failed, how the run stopped, a bounded fetch trace, bounded disassembly, reduce to the smallest failing case, and only then a windowed waveform), the harness properties that make each rung possible (distinct exit codes, a cycle budget, a probe port, the program as a runtime plusarg), and why a plausible-looking number from a broken configuration is the failure mode to fear most. Use when a simulation "just hangs", when a core produces no output, when a workload passes on one configuration and not another, or before reaching for a waveform.

0
installs
▌
Openroad Debug · the-openroad-project
Diagnose and iterate on an OpenROAD/ORFS failure (crash, hang, race, nondeterministic result) and set up a fast edit/measure loop before you package a reproducer.

0
installs
▌
Openroad Issue · the-openroad-project
Create a copy-paste-ready GitHub issue for an OpenROAD bug. File it upstream as a git am patch + failing bazel test.

0
installs
▌
Repair Timing Grt · the-openroad-project
Investigate OpenROAD global-route repair_timing correctly — the grt "grind"/timeout, hold- and setup-buffer insertion. Covers why a skip-repair (fast) grt measures nothing about repair, why repair_timing must run inside global_route.tcl on the pre-GR ODB, how to split the grind into setup vs hold before blaming either, why the win is measured as clk_period-WNS in picoseconds rather than as a percentage of WNS, and why a design that closes measures nothing about a repair knob. Use when a grt stage times out or runs for hours, when a change is meant to affect repair_timing, or when reasoning about hold vs setup buffer insertion at global route.

0
installs
▌
Orfs Deps Preflight · the-openroad-project
Pre-flight an hours-long ORFS _deps / make-extract stage run (grt, place, route, SAIF) by dumping the stage's effective variables and mentally dry-running the flow TCL to confirm the code path you are testing will actually execute. Use before committing to any long OpenROAD flow-stage run, especially when a SKIP_* flag, an *_EFFORT setting, or a setup/hold selector could silently route around what you intend to measure.

0
installs
▌
Untar And Run Report · the-openroad-project
Produce an untar and run reproducer archive for an OpenROAD bug, plus paste-ready text for a GitHub issue comment.

0
installs

15 published skills