Case Executor
Execute OpenCase test cases (agent manual testing): fetch the execution prompt with run, operate the application under test for real with browser/computer-use tools, judge pass/fail against Expected line by line, and record a dated, attributed execution record; when the failure is a product bug, draft an issue with gh. Also used for drift-hunting on scripted cases. Use when the user asks to "exec…
Case Reviewer
Run a grill-style review session for OpenCase: present cases one at a time with full content and context for the user to decide (approve / edit / skip), self-approve only obviously correct cases with a reason recorded in the session summary. Use when the user says "review the cases / walk me through review / approve cases". One case at a time — never bulk-dump.
Case Writer
Write test cases for OpenCase: decompose multi-source requirements (Feishu PRD, spec docs, grill/to-prd artifacts, pasted documents) into user journeys, happy paths, edge cases and failure flows, writing one file per case into cases/ per the OpenCase format contract, then run validate. Use when the user asks to "write test cases / break down requirements into cases / produce cases from a PRD". Ne…
Opencase Release
Prepare and publish a new OpenCase release: bump Cargo.toml version, update CHANGELOG.md, PR-first into protected main, then tag v<version> — the release workflow verifies, publishes to crates.io, and builds the platform binaries. Use when asked to cut a release, bump the version, publish to crates.io, or update the changelog.