yeaight7

Check version bump, changelog, compare range, package metadata, validation commands, publish steps, and rollback plan before cutting a release.

Self-referential loop until task completion with configurable verification reviewer

Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.

Use when code needs restructuring without changing observable behavior.

Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.

Verify that API endpoints match their OpenAPI/Swagger specifications.

Run a review and CI loop around a pull request with explicit approval gates for code changes, remote writes, and follow-up actions.

Evaluate metric and semantic model changes for BI/reporting breakage and business meaning drift.

any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when the user wants to build, inspect, or query a cross-file knowledge graph from code, docs, papers, images, or videos with upstream graphify.

Use when code needs restructuring without changing observable behavior.

Usar ao projetar ou usar busca de código estruturada com suporte MCP, incluindo fluxos de trabalho de busca, consulta AST, inventário de símbolos e extração limitada.

Inspect and test web UIs using screenshots, browser automation, accessibility snapshots, and console/network signals with structured visual evidence collection.