r3nd

Execute live manual QA from written cases or an inline repro case, capture verifiable artifacts, and write a structured result report.

Convert a manual QA Markdown result into a standalone HTML evidence report with clickable proof links for JSON, images, and code snippets.

Reproduce a bug locally, trace intent and history, propose the smallest safe fix, then implement and verify the repair.

Turn a technical spec or concrete problem statement into a concrete implementation and test plan formed of small, traceable tasks.

Review PR discussions to identify improvements to agents, templates, or instructions; write a retro report to rnd/retros.

Convert product specs into a repo-grounded technical specification / high-level design.

Produce E2E sanity test cases (English) for features and save them under rnd/test_cases/.

Implement features and tests based on a build plan; follow repository standards and keep diffs small and test-driven.

Coordinate feature delivery with dependency-aware implementation, task-level QA, and final live QA.

Investigate, gate, plan, implement, and QA a very small feature with explicit approval and tight scope.

Generate, run, and diagnose E2E tests from test cases; output structured results to rnd/e2e-results.

Create clear, concise product specifications from short feature descriptions or issue text.

Analyze an app root and generate detailed app-level AGENTS.md / CLAUDE.md files.

Analyze a module path and generate detailed module-level AGENTS.md / CLAUDE.md files.

Analyze a repository root and generate high-signal repository AGENTS.md / CLAUDE.md files with machine-readable app metadata.