amd-agi/aklr · harness/automations/shepherd/skills/optimize-and-deliver-kernels/SKILL.md · Optimize kernel-less AKLR schemas with KernelForge and deliver them as draft PRs, one round per run (observe, chain…
amd-agi/aklr · harness/automations/shepherd/skills/setup-shepherd/SKILL.md · Configure shepherd and prepare its Cursor automation. Use when installing shepherd or changing its repository…
amd-agi/aklr · harness/skills/bad-cases/SKILL.md · A list of mistakes agents have made in AKLR, with what to do instead and how to spot each one in a code change. Use…
amd-agi/aklr · harness/skills/build-runtime-image/SKILL.md · Build and validate a reproducible runtime image for an exact AKLR revision and declared ROCm stack. Use when kernel…
amd-agi/aklr · harness/skills/forge-loop-campaign/SKILL.md · Run an autonomous optimization campaign on a kernel-less AKLR schema with KernelForge on an MI355X (gfx950) machine and…
amd-agi/aklr · harness/skills/geak-campaign/SKILL.md · Optimize a kernel-less AKLR schema with GEAK (AMD-AGI/GEAK) instead of KernelForge, and deliver the kernel back into…
amd-agi/aklr · harness/skills/kb/SKILL.md · What makes a kernel fast on gfx950 (MI350/MI355X) inside AKLR, and how to write it in FlyDSL, Triton/Gluon or HIP (the…
amd-agi/aklr · harness/skills/kb/flydsl/SKILL.md · Writing FlyDSL kernels for AKLR on gfx950 (MI350/MI355X): FlyDSL v0.3.2 limits, compile errors and version differences…
amd-agi/aklr · harness/skills/kb/hip/SKILL.md · Making HIP kernels fast and AITER-exact on gfx950 (MI355X) inside AKLR. Covers memory-bound kernels (normalization…
amd-agi/aklr · harness/skills/monitor-upstreams/SKILL.md · Monitor configured upstream repositories for new kernels and optimizations, deduplicate candidates, and route them to…
amd-agi/aklr · harness/skills/open-pr/SKILL.md · Open a AKLR pull request whose body carries the evidence each kind of change needs (contracts, kernels, code, withdrawn…
amd-agi/aklr · harness/skills/port-generated-kernels/SKILL.md · Port agent-generated GPU kernels into AKLR with their provenance, dispatch, fallbacks, and review evidence. Use for…
amd-agi/aklr · harness/skills/qualify-downstream/SKILL.md · Qualify an exact AKLR build with supported SGLang, vLLM, and ATOM revisions for API compatibility, correctness, and…
amd-agi/aklr · harness/skills/read-validation/SKILL.md · Read a AKLR validation result, local or from CI, and decide what it means for a kernel - which Points pass, which fail…
amd-agi/aklr · harness/skills/remote-gpu-setup/SKILL.md · Add, re-probe, update or remove the clusters remote-gpu allocates on (~/.remote-gpu/clusters/), and verify them. Use…
amd-agi/aklr · harness/skills/remote-gpu/SKILL.md · Allocate whole remote GPU nodes on the Slurm-family clusters under ~/.remote-gpu/clusters/ and use them through one…
amd-agi/aklr · harness/skills/report-progress/SKILL.md · Write a short progress report on long-running AKLR work (what changed, key numbers against their baseline, what is…
amd-agi/aklr · harness/skills/tdd/SKILL.md · Test-driven development, red before green. Use when writing or changing a test, fixing a bug, or changing what code in…