test-gate-bivio
Manages test gate interaction respecting the required depth
Installation
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
View source ↗GuidesSkill instructions
Operational Instructions
Trigger
- Within
tech_rag(Step 5 Test Gate). - Whenever interactive validation is needed before proceeding.
Inputs
-
User Config:
<SmokeTestCmd>in.agent/project/PROJECT_AGENT_CONFIG.md. - User Choice: Direct interaction (Easy/Deep/Debug).
Steps
- Interrupt: ASK the user for the desired test level.
-
Easy/Smoke:
- Execute
<SmokeTestCmd>command.
- Execute
-
Deep:
- Execute complete regression tests (
pytest,npm test, etc). - Execute
<DeepTestCmd>(e.g.,uv run pytest -q). - If
<NegativeTestMarkers>are present, also run negative tests (e.g.,uv run pytest -m "negative or fuzz").
- Execute complete regression tests (
-
Debug:
- Activate
sequential-thinkingto isolate the case. - Execute
<DebugTestCmd>(e.g.,uv run pytest -q -vv --maxfail=1 --pdb).
- Activate
Outputs
-
Result:
PASS(proceed) orFAIL(fix required).
Configuration
Check .agent/project/PROJECT_AGENT_CONFIG.md for the default Smoke command.
Examples
Read the usage examples in the source repository.
View source ↗Source history
- Indexed on
- 2026-01-20
- Index updated
- 2026-03-03
- Branch
- main
Index and sync dates describe this directory. View the source repository for code history.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!