بنقرة واحدة
بنقرة واحدة
Workflow for evaluating and refining agent debugging capabilities using designated test cases and Swarm principles. Use when evaluating subagent performance or creating benchmarks. Do not use for regular bug fixing.
Workflow for agent self-improvement via isolated execution, evaluation, and process refinement. Use when evaluating historical bugs or self-correcting skills. Do not use for new feature development.
Handles installation and configuration of clangd-mcp for V8. Use when clangd-mcp is missing or needs configuration for the current workspace. Do not use for general C++ editing.
Analyzes recent commits and uses a smart AI subagent to check if they invalidate any documentation in docs/.
Evaluates JavaScript using the official ECMAScript specification
Handles abstraction of environment-specific commands between Jetski and Gemini-CLI. Use when switching execution context between local terminal environments. Do not use for debugging logic issues.
| name | crossbench |
| description | Running benchmarks with Crossbench. |
Crossbench is the central chrome runner harness for press benchmarks like JetStream, Speedometer or Motionmark, as well as for loading live pages.
~/crossbench or in
CHROMIUM_CHECKOUT/src/tools/perf/cb, but could be anywhere.
If not found in standard locations, ask the user for the path.Navigate to the crossbench directory and use ./cb.py directly (or via poetry
if vpython3 is not available).
# Run the latest stable JetStream with a specific d8 binary
./cb.py jetstream --browser=/path/to/d8 --env-validation=warn
And for chrome:
./cb.py jetstream --browser=out/x64.release/chrome --env-validation=warn
--separate for instance to
generate individual profiles for each sub test--story=XXX to only run a specific testUse ./cb.py mcp to launch a local MCP to interact with benchmarks.
./cb.py describe probes to list all probes../cb.py describe probe v8.log to show detailed help for a specific probe.Important probes for v8 investigation:
--probe='v8.log' to generate a v8.log file (see v8-log skill for
more information on how to analyse the log file)--probe='profiling' to generate a Linux perf trace.--probe=perfetto to collected perfetto tracesResults:
cb.results.json file listing all probe results--env-validation=warn to bypass environment input prompts../cb.py describe to understand subcommands and probes.poetry run cb_validate_hjson -- file.hjson.