fix-next-test
SkillDev toolsFix one relevant failing test with bounded investigation and isolated CI verification.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the fix-next-test skill
What this skill tells your AI
The instructions your AI receives, as published by glowingkitty/openmates in .agents/skills/fix-next-test/SKILL.md and read by ahel’s review.
Identify the requested failing spec and its first useful error. Reuse existing CI results; load only the relevant test, implementation and contract. Obtain the bound workspace before editing. Record the expected behavior, then fix the cause and maintain relevant E2E assertions. Do not weaken coverage to get a pass.
Run focused local checks and the relevant isolated CI selection with
ci_coordinator.py submit and wait <id>. Do not create a separate debug campaign
or require coordinator approval for already-authorized work. Reassess after two
unsuccessful attempts with the same approach. Ask before unrelated infrastructure
repair, uncertain behavior changes, or expanding the original task. Preserve
useful evidence and keep the OpenMates Task status accurate. Shared policy:
.claude/rules/testing.md and AGENTS.md.
Signals
- GitHub stars
- 46
- Forks
- 3
- Last commit
- Sep 2026
Others that do the same job
Advanced
- Catalog kind
- skill
- Gateway key
fix-next-test- Source
- github.com/glowingkitty/openmates