gokeshenzhen

9 mods across 3 repositories, 118 stars between them.

gokeshenzhen/TraceWeave

Instructions file CodexOpenCode

Instructions for gokeshenzhen/TraceWeave, covering repository guidance, domain context and authorized scope, installation discipline, traceweave usage and lsf-only npi user setup.

86 2d ago A 8,345 tokens original MIT

gokeshenzhen/TraceWeave

Instructions file

Instructions for gokeshenzhen/TraceWeave, a project described as: 通用的测试平台日志,波形(FSDB/VCD),根因分析MCP Server. A Universal MCP Server to Debug Testbench Simulation Failures Via Log Parsing And Waveform Analysis (FSDB/VCD).

86 2d ago A 3 tokens copy · 100% MIT

traceweave

03

gokeshenzhen/TraceWeave

MCP server Claude CodeCodexCursor +2

Portable MCP runtime for evidence-driven RTL simulation debugging. Runs locally from the traceweave-mcp Python package.

86 2d ago A tokens not measured original MIT

gen-tb

04

gokeshenzhen/gen-tb-skill

Skill Claude CodeCodex

Generate a complete UVM testbench scaffold for a single IP from its spec documents (docx/pdf/md) and register table (xlsx/csv/md/IP-XACT). Use whenever the user asks to "generate a UVM tb", "build a verification environment", "scaffold a testbench", "create a UVC", "set up DV for this IP", or anything equivalent in…

22 1mo ago A 197 tokens original Apache-2.0

analyzer

05

gokeshenzhen/gen-tb-skill

Agent

You run after the blind Comparator has picked a winner. Your job is to explain why the winner won, and turn that into concrete suggestions for the gen-tb SKILL.md and references/.

22 1mo ago A 0 tokens original Apache-2.0

comparator

06

gokeshenzhen/gen-tb-skill

Agent

You are the blind comparator. You will see two staged directories called left/ and right/. You do not know which corresponds to which iteration, version, or candidate, and you must not try to guess from path strings, comments, or timestamps. Compare them on merit only.

22 1mo ago A 0 tokens original Apache-2.0

grader

07

gokeshenzhen/gen-tb-skill

Agent

You are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch.

22 1mo ago A 0 tokens original Apache-2.0

gokeshenzhen/cov-hunter

Instructions file CodexOpenCode

Project instructions for cov-hunter, a tool for analysing gaps in software test coverage. Test coverage measures which parts of a program are exercised by tests.

10 1mo ago A 4 tokens

gokeshenzhen/cov-hunter

Instructions file

Claude Code instructions for gokeshenzhen/cov-hunter, covering claude.md, install / test / run, architecture — what the readme's pipeline hides and conventions.

10 1mo ago A 1,941 tokens