Automated summary
Runs Verilator in lint-only mode on the generated Verilog of a named module inside its workspace directory and reports errors plus any suppressed warnings.
Strengths
- Checks prerequisites first (workspace/<Module>/generated/ exists with at least one .v file) before invoking the linter
- Separates pass from fail outcomes and surfaces suppressed warnings from lint-warnings.log
- On failure it points you to fix the Chisel source rather than hand-editing generated Verilog
- Takes an explicit PascalCase module name and prompts the user when the argument is blank
Limitations
- Relies on an external scripts/lint.sh and on the chip-agent project layout (workspace/, chisel-project/, .claude)
- Does not fix or deeply analyze code itself — it runs the tool and reports output
- Assumes compilation already produced the Verilog; it does not generate it
Use it right after /chip-agent:compile when you want a quick sanity check of a module's generated Verilog before simulation.
Avoid it when the module has not been compiled yet or when you are outside a chip-agent project that provides scripts/lint.sh.
Security analysis
CautionThe skill is a legitimate lint helper and does not intentionally exfiltrate data, disable safeguards, or use obfuscated payloads. However, it invokes Bash to run a project-local script and uses user-supplied module names in paths without sanitization, which warrants caution rather than a safe rating.
- •ModuleName from $ARGUMENTS is interpolated into a filesystem path without validation, so a crafted name such as ../ could potentially escape the intended workspace directory if lint.sh follows it.
- •The skill executes a repository-local script, <project-root>/scripts/lint.sh, whose contents are outside the skill and must be trusted; Bash execution could run arbitrary logic from that script.
Examples
/chip-agent:lint ALU/chip-agent:lint/chip-agent:lint Countername: lint description: Run Verilator lint checks on generated Verilog for a named module in its workspace directory. disable-model-invocation: true allowed-tools:
- Bash
- Read
chip-agent:lint
Run Verilator lint-only checks on the generated Verilog for a named module.
Usage
/chip-agent:lint <ModuleName>
Instructions
-
Extract module name from
$ARGUMENTS. If empty or blank, ask the user: "Which module should I lint? Please provide a PascalCase module name (e.g., ALU, Counter, TrivialModule)." -
Check prerequisites. Verify that
workspace/<ModuleName>/generated/exists and contains at least one.vfile. If not, tell the user: "No generated Verilog found. Please run/chip-agent:compile <ModuleName>first." -
Determine the project root directory by finding the nearest ancestor directory of this skill file that contains
.claude. Use that directory as the base for all paths below. -
Run lint. Execute the lint script with the workspace path:
<project-root>/scripts/lint.sh workspace/<ModuleName> -
On success (exit 0): Report that lint passed. Check if
workspace/<ModuleName>/generated/lint-warnings.logexists and is non-empty. If so, list the suppressed warnings. Mention that the user can now run/chip-agent:simulate <ModuleName>. -
On failure (non-zero exit): Show the Verilator lint errors. Suggest fixing the Chisel source at
chisel-project/src/main/scala/chipagent/<ModuleName>.scala-- do not edit the generated Verilog directly.
Input
$ARGUMENTS -- A PascalCase module name (e.g., ALU, Counter, TrivialModule).
Output
Lint pass/fail report. If warnings were suppressed, they are listed from workspace/<ModuleName>/generated/lint-warnings.log.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/verilator-lint-for-verilog-ms1aw4vm/download' --output '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md.part' && mv '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md.part' '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md' && test -s '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/lint' && cp -R '.skill-downloads/verilator-lint-for-verilog-ms1aw4vm' '.claude/skills/lint'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/verilator-lint-for-verilog-ms1aw4vm'openskills read 'verilator-lint-for-verilog-ms1aw4vm'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/verilator-lint-for-verilog-ms1aw4vm/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.