Skill Claude CodeCodex
Implement a requested change using the repository's modern C++ agent loop.
162 tagged cpp, measured the same way as everything else here.
Browse within: ai-assisted-development 39code-quality 22code-verification 22defensive-programming 22lua 19Code Generation 18browser-automation 18hpc 18async 17HuggingFace 11PyTorch 11ai-native 11inference 11modern-cpp 11
Skill Claude CodeCodex
Implement a requested change using the repository's modern C++ agent loop.
Skill Claude CodeCodex
Build and test the repository without making unnecessary code changes.
Skill Claude CodeCodex
A development process for changes in the repository, dividing work into bug fixes, optimisations, and new features. New features require prior issue discussion and a written design in .agents/docs, followed by testing, validation, continuous integration, and pull-request checks.
Skill Claude CodeCodex
A guide for finding the cause of failed or crashing mbun runtime tests, including single-file test runs, debugger backtraces, and source-code tracing by API.
Skill Claude CodeCodex
A coding style guide for mcpp that uses modern C++23 conventions, including conventions for C++ modules and source-file organization.
Skill Claude CodeCodex
Review an ArduPilot new-board hwdef PR. Stashes any local changes, checks the PR out as a branch in the current repo, runs DMA / board-ID / file-presence / commit-structure checks, layers the hwdef playbook on top, and (after confirmation) posts a review comment on the PR — then restores the original branch and pops…
Skill Claude CodeCodex
Analyze ArduPilot DataFlash .bin log files or MAVLink .tlog telemetry logs. Use when the user provides a .bin or .tlog log file path or asks to analyze flight log data.
Skill Claude CodeCodex
Review your own ArduPilot PR the way a maintainer will - before you open it, or after review feedback arrives - and then fix what the review finds. Runs the CI gates that bounce PRs mechanically, fans out parallel reviewers over the diff, cross-checks every finding with an independent Codex pass, and iterates fixes…
Skill Claude CodeCodexCursor
Develop or debug the qb-linq header-only C++17 LINQ library (qb::linq): locate declarations and definitions, extend iterators and views, run qblinqtests and optional benchmarks. Use when editing include/qb/linq, adding terminals or lazy views, or writing tests for this repo.
Skill Claude CodeCodex
Analyze an editor, build, or structured trace log (Unreal Engine Saved/Logs, Unity Editor.log, Godot output, MSVC/UBT/MSBuild build output, JSONL / structured .jsonl traces, or any text log) token-efficiently. Use when the user mentions checking, reading, searching, summarizing, or diffing a log; investigating…
Skill Claude CodeCodex
Preview-only dead-code analysis for C/C++, C#/.NET, JS/TS, and Python via vs-token-safer. From one or more seed symbols, walk the official language server's call graph to a fixpoint and report what is provably DEAD (and what transitively becomes dead) — without deleting anything. Use whenever the user asks what code…
Skill Claude CodeCodex
Routing rules for code search in C/C++, C#/.NET, JS/TS, and Python projects via vs-token-safer — use the vs-search MCP tools (clangd/Roslyn/tsserver/pyright language-server index) or the vts CLI instead of Bash grep. Use whenever searching for a symbol, definition, function, variable, type, or finding…
Bastioned-successor320/learn-nanobot
Skill Claude CodeCodex
A code-review procedure for Python, JavaScript, and Go programs. It checks security, performance, maintainability, naming, error handling, and testing.
Bastioned-successor320/learn-nanobot
Skill Claude CodeCodex
A procedure for turning brief work notes into a structured daily report. It records completed work, problems, current progress, and plans for the next day.
NAJEMWEHBE/unreal-ai-connection
Skill Claude CodeCodex
Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot…
Skill Claude CodeCodex
Instructions and architectural standards for Unreal Engine 5 C++ development.
Victory-7291/project-scaffold-setup-skills
Skill Claude CodeCodex
Modern C++ project setup: CMake/CMakePresets, vcpkg, Ninja, VS Code/clangd, GoogleTest, clang-format/tidy, Doxygen, CI, macOS/Linux/Windows. Use for bootstrapping or modernizing host-side C++ apps and libraries; prefer embedded-project-setup for MCU firmware and cross-debug flows.
Victory-7291/project-scaffold-setup-skills
Skill Claude CodeCodex
Embedded firmware setup: STM32, ESP32, AVR, RP2040, Nordic nRF, Zephyr/RTOS, vendor SDKs, CMake/CMakePresets, VS Code/clangd, cross toolchains, flash/debug, Docker/CI. Use for MCU scaffolds, existing firmware modernization, BSPs, linker/startup files, SDK package selection, and embedded CI; prefer cpp-project-setup…
Victory-7291/project-scaffold-setup-skills
Skill Claude CodeCodex
FastAPI service setup: app/main.py, API routers, pydantic-settings, lifespan/app.state services, middleware, health checks, pytest/TestClient, Uvicorn, Gunicorn/uvicorn-worker, Docker/Compose. Use for scaffolding or modernizing Python API services; skip for Flask/Django-only, frontend-only, non-Python APIs, or…
Skill Claude CodeCodex
Demo skill shipped by the exampleresources plugin. Use when the user greets you or asks for a friendly hello.
Skill Claude CodeCodex
Demo skill registered at runtime by the exampleresources plugin entry via the vtable registerskilldir API.
Skill Claude CodeCodex
An isolated review role that checks whether work meets its acceptance criteria and reports its findings without changing the work's status.
Skill Claude CodeCodex
A system for recording runtime failures as structured “noise cards,” which are saved notes about unexpected behavior and its cause. Unresolved cards can later be turned into regression tests, tests that prevent the same failure from returning.
Skill Claude CodeCodex
A noise-card system for recording runtime failures as structured notes that can later become regression tests, which are tests that prevent the same problem from returning.