Optional focused post-implementation review routing. Use only when the user requests review or the changed surface has a clear specialist evidence need that direct diff inspection and the smallest relevant check cannot cover. Never creates an automatic review swarm.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Obtain the minimum additional review evidence needed for a specific risk.
Use only when:
Direct ROSE diff inspection and the smallest relevant check are the default. Multi-file work alone does not trigger this skill.
Near misses: implementation completion, SHIP wording, a pending merge, test failures, or broad quality concerns without one review question do not trigger routing. code-review-and-quality may be the primary loop for an explicit direct review; use this pipeline only when the current intent is specifically specialist review routing.
ROSE/aili-delivery-flow owns lifecycle state, approvals, repairs, verification, and final judgment. This skill runs one bounded routing pass and does not invoke another process skill; it returns any missing capability or material delta to ROSE. Canonical approval and claim-matched verification rules win.
WT-001 context, keep artifacts in the owning repository, disclose the shared-trust soft boundary, and do not scan the host broadly.subagent-task-packet.md and require the canonical result/finding envelope in subagent-result.md.Do not automatically fan out code, test, security, coverage, AI, silent-failure, convergence, browser, or E2E lanes. Do not create a fixed multi-cycle repair loop.
Report the reviewed scope, evidence, blocking findings, skipped specialist checks, freshness, and remaining Unverified risks. ROSE owns the final judgment. A33 results reference rather than duplicate or rebind WT identity, keys, approvals, Git state, rules, or command/cwd.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Review a single academic paper, preprint, DOI, arXiv link, or user-provided PDF/text with source-grounded critique. Use for paper summaries, methodology review, novelty checks, reproducibility concerns, or "review this paper" requests; do not use for multi-paper surveys, systematic literature reviews, citation management, or implementation from a paper.
The English summary is being prepared. Showing the original description.
AI regression scouting routing. Use when agents, prompts, skills, model/tool routing, harness fixtures, or generated-output expectations change and need regression scenarios; do not use for ordinary product-code regressions.
The English summary is being prepared. Showing the original description.
Run the AILI delivery lifecycle from natural-language IDEATE, DEFINE, BUILD, and SHIP intent or the equivalent slash shortcuts; use for idea shaping, spec/test definition, bounded BUILD package queues, review-repair closeout, or adapter routing without exposing internal stage commands.
The English summary is being prepared. Showing the original description.
Android native Kotlin/Compose app development, Material 3 UI, accessibility, and Gradle builds.
The English summary is being prepared. Showing the original description.
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
The English summary is being prepared. Showing the original description.
Route an explicitly requested independent/delegated browser QA assignment or durable E2E evidence need; do not trigger for direct Playwright/DOM/console/network inspection, ordinary UI implementation, backend-only work, or production-mutating flows.
The English summary is being prepared. Showing the original description.