A collection of AI agent skills for QEMU hardware modeling
This repository also configures its own agents. See what oh-my-qemu tells them →
Skill Codex
Use when a completed QEMU skill session exposed a reusable oh-my-qemu workflow problem and the user wants a sanitized improvement proposal drafted or filed as a GitHub issue.
Skill Codex
Use for QEMU board and SoC topology, memory map, boot policy, FDT/ACPI, and IRQ wiring modeling with proportional qtest verification; peripheral device behavior belongs to qemu-peripheral-modeling.
Skill Codex
Use when the QEMU binary and boot inputs are selected and one reproducible QEMU run must be constructed, logged, timed out, and classified by explicit success or failure markers.
Skill Codex needs its repo
Use for configuring, reusing, building, or diagnosing named QEMU build directories under source-root builds/, including target-specific, debug, sanitizer, and trace configurations. Use for the QEMU source tree only; kernel and U-Boot builds belong to qemu-kernel-build and qemu-uboot-build.
Skill Codex
Use when QEMU crashes, asserts, or hangs, when a guest stalls before a boot marker, or when device, board, TCG, or replay behavior is suspected; debug with host gdb/lldb, the gdbstub, logs, traces, and replay.
Skill Codex
Inspect or package QEMU disk, SD, eMMC, flash, pflash, firmware, raw, and qcow2 images. Use for read-only image format, partition, region, offset, sector-size, and hash analysis, or for explicitly authorized image creation, conversion, partitioning, filesystem population, and fixed-offset writes with readback and…
Skill Codex
Use for building Linux kernels for QEMU boot testing, including defconfig selection, cross compile variables, Docker or host toolchains, Image, DTB, modules, initramfs inputs, output hashes, and provenance records.
Skill Codex
Use for booting Linux in QEMU through either direct kernel loading or firmware and bootloader stages, selecting the path from task inputs while preserving provenance, boot logs, debug handoff, and verification evidence.
Skill Codex
Use when existing qtest, trace, log, replay, boot, or workload evidence must be evaluated against one falsifiable QEMU device, board, TCG, or runtime claim as PASS, FAIL, or INCONCLUSIVE.
Skill Codex
Use for QEMU peripheral, accelerator, MMIO, qdev, or SysBusDevice modeling with register contracts, an explicit register framework decision, and qtest-backed verification.
Skill Codex
Use for QEMU qtest design, registration, execution, debugging, and immediate evidence capture for device, board, QMP, timer, IRQ, DMA, and memory behavior.
Skill Codex
Use to extract a source-cited QEMU register and behavior contract from drivers, datasheets, firmware, device trees, runtime traces, and SVD, IP-XACT, SystemRDL, or vendor regfiles before modeling a hardware block.
Skill Codex
Use for writing or updating QEMU reStructuredText documentation, including board and machine docs, system docs, device docs, developer docs, boot command examples, feature status tables, Sphinx index/toctree updates, and docs build validation.
Skill Codex
Use for adapting a QEMU TCG host backend, including optional op support, constraints, register allocation, host code emission, qemuld/st, atomics, vectors, and native-versus-fallback verification.
Skill Codex
Use for adding, reviewing, or debugging guest ISA decode and translation in a QEMU TCG frontend, including feature gates, exceptions, PC/TB behavior, and focused instruction tests.
Skill Codex
Use for building U-Boot artifacts for QEMU firmware boot testing, including defconfig selection, cross compile variables, SPL/TPL, U-Boot proper, FIT or ITB files, BL31 or TF-A dependencies, logs, hashes, and provenance.
Skill Codex
Use for non-trivial multi-step QEMU research, debugging, local-only implementation, modeling, boot, build, and verification tasks that benefit from auditable planning, source and artifact provenance, small reviewed rounds, evidence-backed verification, and a clear handoff; skip it for trivial read-only questions or a…
Skill Codex
Use to independently review one QEMU modeling round or patch: verify the plan and acceptance criteria, RS-IR and translation consistency, error/trace/log coverage, qtest/boot evidence, and audit gates, then report BLOCKER/MAJOR/MINOR/NOTE findings and a PASS/FAIL/INCONCLUSIVE verdict.
Skill Codex
Use when starting or resuming an end-to-end QEMU device, board, SoC, or firmware modeling task; it decomposes the real goal into milestones and evidence-backed acceptance criteria, orchestrates evidence extraction, RS-IR translation, domain-skill execution, debugging, independent review, feedback capture, and the goal…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: