Prove whether a skill-pack change made agents better at writing code. Use when a single passing eval doesn't prove anything and you need multi-run pass@k evidence, when grading coding tasks with hidden tests the agent cannot see, or when comparing outcomes across skill-set versions.
Create design documents (WHICH/WHERE) for approved specs. A design is a max-200-line architectural sketch — components, interfaces, data flow, and key decisions with trade-offs — that gives reviewers a high-leverage point to redirect architecture before the full plan is written. Design is approved when `wiki/STATUS.md` shows the spec row at `design approved` — written there by a human signal that `kata-dispatch` or the active agent propagates.
Write implementation plans (HOW/WHEN) for approved designs. Translate an approved design into concrete steps, file changes, sequencing, and risks for a trusted agent to execute. Plan is approved when `wiki/STATUS.md` shows the spec row at `plan approved` — `staff-engineer` writes this row after a clean panel review (plans may be approved by agents).
Grade a single artifact (spec, design, plan, or implementation diff) against quality criteria and return findings by severity. Use when another skill spawns a fresh sub-agent for an independent review of its work. This skill never spawns sub-agents — it produces findings only — which structurally prevents the spec/design/plan/implement review loop from recursing.
Write specifications (WHAT/WHY) for features, changes, and improvements. Spec is approved when `wiki/STATUS.md` shows the spec row at `spec approved` — written there by a human signal (label, comment, APPROVED review, or in-session message) that `kata-dispatch` or the active agent propagates. Use when proposing changes, capturing findings as actionable specs, or evaluating spec quality. Pair with the `kata-plan` skill for the HOW side.
Merge gate for open pull requests. Verify contributor trust, classify PR type, rebase on main, fix mechanical CI failures, gate on `wiki/STATUS.md` approval state, and merge passing PRs. Sole external merge point.
Detect time-bounded artifacts whose retention window has passed, confirm each one's durable signal is preserved elsewhere, then retire them — past-period wiki files directly and terminal spec directories through a retention PR. Use on a scheduled archivist shift, or when the specs tree and weekly logs grow faster than they retire and repository search signal drops.
Perform a deep-dive codebase-health review — dead code, duplication, inconsistency, and accumulating debt — one area per run against a coverage map. Use on a scheduled developer-experience shift, when reviewing a change for maintainability, or when debt in one area has started slowing every agent invocation.