// Audit TSZ repo iteration speed and quality. Use when asked to deep-dive repo health, identify avoidable delays, improve agent workflows, reduce CI/PR churn, add guardrails, choose skills to install or create, or turn recurring TSZ process failures into focused tooling/docs PRs.
| name | tsz-iteration-audit |
| description | Audit TSZ repo iteration speed and quality. Use when asked to deep-dive repo health, identify avoidable delays, improve agent workflows, reduce CI/PR churn, add guardrails, choose skills to install or create, or turn recurring TSZ process failures into focused tooling/docs PRs. |
Use this skill to turn repo-health observations into small, useful changes. The output should be evidence-backed and PR-sized, not a new roadmap unless the durable project direction truly changes.
Read the current direction and coordination state:
sed -n '1,320p' docs/plan/ROADMAP.md
gh pr list --state open --limit 100 --json number,title,isDraft,headRefName,baseRefName,labels,updatedAt,url
gh pr list --state merged --limit 30 --json number,title,headRefName,mergedAt,url
gh issue list --state open --limit 100 --json number,title,labels,updatedAt,url
Inventory existing guardrails before proposing new ones:
find .agents/skills .claude/skills scripts/agents scripts/ci scripts/arch scripts/bench scripts/conformance scripts/emit -maxdepth 3 -type f | sort
Look for recurring iteration costs:
find crates scripts .agents .claude .codex docs -type f \
\( -name '*.rs' -o -name '*.py' -o -name '*.mjs' -o -name '*.js' -o -name '*.sh' -o -name '*.md' \) \
-not -path '*/target/*' -not -path '*/.target/*' -print0 | xargs -0 wc -l | sort -nr | sed -n '1,60p'
rg -n "source_text\\.contains|rewrite_.*fingerprints|format_type_diagnostic|TypeData|CompatChecker|is_assignable_to" crates scripts
rg -n "WIP|stale|drift|queue|worktree|disk|allowlist|fingerprint" docs scripts .agents .claude .codex
Classify each finding:
workflow: agents repeatedly start from stale state or lose coordination.guardrail: architecture, file-size, WIP, PR-body, or CI checks miss a
preventable class.visibility: useful data exists but is hard to find at decision time.duplication: the same policy lives in multiple scripts/docs/skills.behavior debt: compiler code violates an architecture rule and needs a
focused owner, not process cleanup.Choose the smallest aligned change:
Use references/2026-05-26-findings.md as a starting evidence map. Replace it
with fresher evidence when the repo state changes.
docs/plan/ROADMAP.md for ordinary cleanup or PR bookkeeping.For iteration-audit PRs, write:
AgentName.The best audit PRs make the next agent faster within the first five minutes of their task.
Drive TSZ GitHub PRs through review, CI, and the merge queue. Use when checking PR status, debugging failing GitHub Actions, deciding whether a PR is WIP, marking draft PRs ready, enqueueing or verifying the queue, landing a PR, or interpreting TSZ CI gates.
Create, refresh, and publish TSZ pull requests with correct coordination state. Use when opening a draft PR, updating a PR body, applying canonical agent labels, changing WIP/draft/ready state, acknowledging review, handing off readiness to a manager agent, or making sure a TSZ PR satisfies AgentName, Project Corpus Impact, verification, and overlap rules.
Prevent TSZ machines and worktrees from running out of disk while preserving useful build caches. Use before creating worktrees, running large builds/tests, diagnosing low disk, cleaning artifacts, deciding whether to delete caches, or recovering space without slowing future Rust/TypeScript builds.
Use when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot investigations, OOM/timeout/stack-overflow blockers, or optimization PR evidence.
Start TSZ work safely in a crowded multi-agent checkout. Use when beginning a TSZ task, resuming a goal, switching or creating branches/worktrees, recovering from a merged or stale branch, checking disk/cache state, reading lane goals, or deciding whether local dirty files belong to the requested work.
Preserve TSZ architecture boundaries while changing checker, solver, binder, emitter, LSP, WASM, or CLI code. Use when planning semantic fixes, moving logic across query boundaries, handling architecture guard failures, ratcheting boundary debt, or reviewing changes for solver-first and no hardcoding rules.