plugins/beaver/skills/beaver-focus/SKILL.md
Show your personal Beaver work status: today's tasks, pending reviews, blockers, and DDL warnings with priority recommendations. Trigger when the user asks about their tasks, what to work on, or personal status.
npx skillsauth add primatrix/skills beaver-focusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Show the current developer's personal work dashboard: active tasks, pending reviews, blockers, DDL warnings, and LLM-powered priority recommendations.
References beaver-engine for: label taxonomy (Section 1), label ops (Section 4), config reading (Section 5).
gh auth status must succeedCURRENT_USER=$(gh api user --jq '.login')
Read beaver-config per engine Section 5.
gh api "repos/{org}/{issueRepo}/issues?labels=Control-By-Beaver&assignee=$CURRENT_USER&state=open&per_page=100" \
--jq '.[] | {number, title, labels: [.labels[].name], milestone: {title: (.milestone.title // null), due_on: (.milestone.due_on // null)}, updated_at}'
Parse labels per engine Section 4. Group by status.
gh api "search/issues?q=is:pr+is:open+review-requested:$CURRENT_USER" \
--jq '.items[] | {number, title, repository_url, created_at, user: .user.login}'
For issues with milestones, check if due_on is within 48 hours. Flag accordingly.
# Beaver Focus: @{username}
**Date:** {today}
## In Progress ({count})
| # | Title | Priority | Updated |
|---|-------|----------|---------|
## Ready to Develop ({count})
| # | Title | Priority |
|---|-------|----------|
## Awaiting My Review ({count})
| # | Title | Repo | Waiting Since |
|---|-------|------|--------------|
## My Blockers ({count})
| # | Title | Blocked Since |
|---|-------|--------------|
## DDL Warnings ({count})
| # | Title | Due | Days Left |
|---|-------|-----|-----------|
## Today's Top 3 Priorities
{LLM recommendation based on:
1. p0/blocker and p1/urgent issues first
2. DDL < 48h issues next
3. Longest-waiting review requests
Explain WHY each is prioritized.}
gh authenticated userdevelopment
Use when analyzing TPU pretraining HBM occupancy from a profile directory — locates the static HBM peak (the same number TensorBoard's Memory Viewer shows), enumerates every buffer alive at the peak schedule moment with size / HLO instruction / opcode / op_name, and rolls the alive set up by opcode and op_name. Reads compile-time `*.hlo_proto.pb` (BufferAssignmentProto) as the primary source; runtime `*.xplane.pb` allocator events are a secondary, often-truncated signal.
testing
Use when analyzing TPU pretraining compute efficiency from xplane.pb — produces source-line-aggregated HLO duration tables, layer-scoped breakdowns, non-compute (padding/cast/copy) audits, and v7x roofline shortfall vs theoretical peak. Reads schema documented by profile-anatomy.
tools
--- name: comm-analysis description: Use when analyzing communication on a TPU pretraining profile — extracts every comm primitive (async + sync, TC + SparseCore), attributes axes via HLO replica_groups, computes per-row NCCL bus BW vs per-axis peak ICI BW (peak_link × k_torus_dims × directions_per_dim; TPUv7x: 200 GB/s bidir per link on a 3D torus; util% requires `--mesh-spec` with topology), and reports per-step compute/comm overlap. Builds on profile-anatomy. --- # Communication Analysis **
documentation
Use when reading TPU pretraining profiles (xplane.pb, trace.json.gz) — describes the on-disk layout, the XSpace/XPlane/XLine/XEvent/XStat hierarchy, and provides reference scripts that future tpu-perf skills can read as schema documentation.