Stats
Actions
Tags
From rtl-agent-team
Provides passive lint tool profiles (verilator, verible, slang, spyglass) with unified report expectations for Verilog/SystemVerilog codebases.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rtl-agent-team:lint-tool-profilesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Prefer wrapper: `lint/scripts/run_lint.sh`
lint/scripts/run_lint.sherrors, warnings, tool, log_path, replay_patherrors == 0verilator:
lint/scripts/run_lint.sh --tool verilator -f rtl/filelist_top.f --outdir lint/lintverible:
lint/scripts/run_lint.sh --tool verible -f rtl/filelist_top.f --outdir lint/lintslang:
lint/scripts/run_lint.sh --tool slang -f rtl/filelist_top.f --outdir lint/lintrtl/): runs with -Weverything for maximum strictness — catches always_ff multi-driver violations (VCS ICPD), uninitialized variables, width mismatches, etc.sim/): runs with --allow-dup-initial-drivers — permits initial + always_ff on same signal (common testbench pattern)spyglass (binary: sg_shell, config key: sg_shell, script flag: --tool spyglass):
lint/scripts/run_lint.sh --tool spyglass --top <top> -f rtl/filelist_top.f --outdir lint/lintrat_config.json uses sg_shell as tool key; runner scripts accept --tool spyglasserror/fatal -> normalized errorwarning -> normalized warningnpx claudepluginhub babyworm/rtl-agent-team --plugin rtl-agent-teamRuns Verilator, Verible, and slang lint checks on RTL files with project coding convention enforcement. Use before commit or phase gate verification.
Lints SystemVerilog files using Verilator or Verible, categorizes errors/warnings, explains common issues with fixes, and returns structured output for /gf orchestration.
Reference for ESLint, Ruff, Pylint, RuboCop, Stylelint, and Clippy rule names, AST selectors, and config details when authoring enforce() rules.