nodejs/node

trace-processor

Managing and querying Perfetto traces using the trace_processor MCP server.

Langue du texte source : anglais

agent-evaluation-framework

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.

Langue du texte source : anglais

agent-self-improvement

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.

Langue du texte source : anglais

clangd-setup

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.

Langue du texte source : anglais

crossbench

Running benchmarks with Crossbench.

Langue du texte source : anglais

doc-invalidation-checker

Analyzes recent commits and uses a smart AI subagent to check if they invalidate any documentation in docs/.

Langue du texte source : anglais

ecmascript-evaluation

Evaluates JavaScript using the official ECMAScript specification

Langue du texte source : anglais

env-abstraction

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.

Langue du texte source : anglais

header-cycle-breaker

Guide for breaking cyclic dependencies in V8 headers and resolving cascade IWYU failures.

Langue du texte source : anglais

jsvu

How to use jsvu for cross-engine testing.

Langue du texte source : anglais

minimize-reproducer

Use this when you need to minimize a complex or bloated JavaScript test case (e.g., from a fuzzer or external report) into a minimal, readable reproduction for debugging V8 issues.

Langue du texte source : anglais

orchestrator

Core skill for task scheduling and multi-agent coordination in V8 development. Use for any multi-step workflow or complex task. Do not use for simple linear tasks.

Langue du texte source : anglais

subagent-env-passing

Workflow for passing environment variables (like PATH) from the Orchestrator to subagents. Use when spawning subagents that need specific environment variables. Do not use for standard subagent execution.

Langue du texte source : anglais

torque

Provides expert guidance for navigating, implementing, and verifying V8 Torque (.tq) builtins. Use when modifying or debugging Torque files. Do not use for C++ macro builtins.

Langue du texte source : anglais

v8-ciderg-paths

Adjusts instructions for V8 commands when running in a CiderG Chrome workspace environment. Trigger this when invoking any V8 binaries or running tests in a CiderG checkout.

Langue du texte source : anglais

v8-commands

Key commands for building, debugging, and testing in V8. Use when needing command syntax for gm.py, d8 flags, or run-tests.py. Do not use for environment setup.

Langue du texte source : anglais

v8-log

Understanding v8.log files.

Langue du texte source : anglais

v8-poc-classification

Checks if a POC provided by some JS and d8 flags is a vulnerability or just a regular bug.

Langue du texte source : anglais

v8-profile

Profiling V8 execution.

Langue du texte source : anglais

v8-regression-testing

Use this skill when designing, writing, or minimizing regression tests (e.g., mjsunit) for V8 bug fixes

Langue du texte source : anglais

v8-security-triaging

Guides the initial analysis and impact assessment of a V8 security report, strictly excluding implementation or fixing.

Langue du texte source : anglais

v8-setup

Handles missing dependencies and configuration for V8 tools. Use when encountering missing tools, test runners, or workspace symlinks. Do not use for C++ coding issues.

Langue du texte source : anglais

v8-structure

Maps the V8 dir/folder structure, component locations, and local documentation. Use when locating specific subsystems, mapping src/ code to docs/ design files, or understanding repository architecture.

Langue du texte source : anglais

v8-testing

Executes and interprets V8 tests. Use when running unittests, cctest, or mjsunit, or when debugging test failures. Do not use for building.

Langue du texte source : anglais

v8-understanding

Guides the methodology for investigating V8 concepts, codebase structure, performance, memory, and architecture. MANDATORY to use whenever triaging bugs, investigating crashes, reading C++ files, analyzing compiler optimizations (Ignition, Maglev, TurboFan,…

Langue du texte source : anglais

v8-workflow

Manages git task isolation and environment setup in V8. Use at the start of any new task or bug fix. Do not use for general C++ editing.

Langue du texte source : anglais

wasm-d8-perf

Use this skill to reproduce, profile, or analyze WebAssembly (Wasm) execution performance using d8 shell.

Langue du texte source : anglais

workflow-debugging

Workflow for issue-based debugging in V8. Use when tasked with debugging a specific issue, usually associated with a Buganizer ID or a specific reproduction script. Do not use for performance regressions.

Langue du texte source : anglais

workflow-general-debugging

Workflow for general debugging tasks without the overhead of issue tracking. Use when investigating crashes, hangs, or unexpected behavior where no specific issue ID is provided. Do not use when issue ID is provided.

Langue du texte source : anglais

workflow-gerrit-fix

Workflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user.

Langue du texte source : anglais

workflow-perf

Workflow for performance and memory evaluation in V8. Use when tasked with improving the performance or memory usage of a workload in V8. Do not use when debugging a crash or functionality issue.

Langue du texte source : anglais