beaver-engine
Beaver Engine
Internal skill. Do not invoke directly. Other beaver skills reference these rules and command templates.
Single source of truth for an Issue's lifecycle metadata is GitHub Projects V2 #14 custom fields and the native GitHub Issue Type — not labels. All read/write operations on lifecycle metadata go through plugins/beaver/scripts/beaver-lib.sh (see §4 Field Operations). Native GitHub Issues APIs that fall outside the lifecycle-metadata surface (e.g., the sub-issues API used by G009, the labels API used for beaver/* flag labels in §4) are called directly with gh api since they do not correspond to Project V2 fields or Issue Type.
废弃说明 (Deprecation Notice)
Earlier revisions of this engine modeled lifecycle metadata as status/*, type/*, and size/* repository labels. Those label families are deprecated and replaced by Project V2 fields and native Issue Types per RFC-0013. The old labels are kept on primatrix/projects for historical Issues but are no longer read or written by any Beaver command. New code MUST go through beaver-lib.sh.
Mapping for reference (legacy label → new field semantics):
More from primatrix/skills
linear
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
13exec-remote
Executes Python scripts, tests, or benchmarks on a provisioned remote cluster (GPU or TPU) using SkyPilot. Use this skill when the user asks to run code on GPU, TPU, or any "remote" cluster.
12session-recorder
Records the complete session content and logs it to a daily work directory with a dynamic filename based on the active CLI agent. Use this for automated progress tracking and documentation.
10lint-fix
Check and fix lint issues for changed Python files. Supports single commit, commit range, and unstaged/staged working tree changes. Use when the user wants to verify or fix lint compliance.
2gke-tpu
Manage GKE-based TPU workloads — create pods/jobs via kubectl, sync code, and run multi-process benchmarks. Use when the user wants to create/manage/run TPU workloads on GKE. Reads config from gke.toml in the current working directory.
1tpu-perf-model
Use when analyzing theoretical TPU v7x performance for a mathematical formula or comparing kernel performance against theoretical bounds. Trigger when the user asks about TPU performance modeling, roofline analysis, data flow optimization, or tiling strategy.
1