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.
EnglishHandles 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.
EnglishAnalyzes recent commits and uses a smart AI subagent to check if they invalidate any documentation in docs/.
EnglishHandles 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.
EnglishUse 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.
EnglishProvides 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.
EnglishAdjusts 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.
EnglishKey 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.
EnglishChecks if a POC provided by some JS and d8 flags is a vulnerability or just a regular bug.
EnglishUse when designing, writing, or minimizing regression tests (e.g., mjsunit) for V8 bug…
EnglishHandles missing dependencies and configuration for V8 tools. Use when encountering missing tools, test runners, or workspace symlinks. Do not use for C++ coding issues.
EnglishMaps 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.
EnglishExecutes and interprets V8 tests. Use when running unittests, cctest, or mjsunit, or when debugging test failures. Do not use for building.
EnglishGuides 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, Turboshaft), or doing static research on V8 subsystems. Essential for locating high-level design documents in the local docs/ directory before reading C++ code. Do not use for raw build commands or Git workflows.
EnglishManages 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.
EnglishUse this skill to reproduce, profile, or analyze WebAssembly (Wasm) execution performance using d8 shell.
EnglishWorkflow 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.
EnglishWorkflow 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.
EnglishWorkflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user.
EnglishWorkflow 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.
English
AGENT SKILLS ATLASIncludes Agent Self Improvement, Clangd Setup, Doc Invalidation Checker, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
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.
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.
Doc Invalidation Checker
Analyzes recent commits and uses a smart AI subagent to check if they invalidate any documentation in docs/.
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.
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.
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.
Trace Processor
Managing and querying Perfetto traces using the traceprocessor MCP server.
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.
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.
V8 Poc Classification
Checks if a POC provided by some JS and d8 flags is a vulnerability or just a regular bug.
V8 Regression Testing
Use when designing, writing, or minimizing regression tests (e.g., mjsunit) for V8 bug fixes
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.
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.
V8 Testing
Executes and interprets V8 tests. Use when running unittests, cctest, or mjsunit, or when debugging test failures. Do not use for building.
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, Turboshaft), or doing static research on V8 subsystems. Essential for locating high-level design documents in the local docs/ directory before reading C++ code. Do not use for raw build commands or Git workflows.
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.
Wasm D8 Perf
Use this skill to reproduce, profile, or analyze WebAssembly (Wasm) execution performance using d8 shell.
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.
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.
Workflow Gerrit Fix
Workflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user.
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.
Conditional Testing
Documentation for conditional testing in V8 using gm.py.
Ecmascript Evaluation
Evaluates JavaScript using the official ECMAScript specification
Jsvu
How to use jsvu for cross-engine testing.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agent Self Improvement skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.