Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD
Passed 16 of 18 test cases with the skill, and 2 of 18 without it.
and 17 more in the full report
16 fixed3 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
A bug in an object-oriented Java service causes NullPointerException on checkout. CLAUDE.md lists Object-Oriented as the paradigm. Which crafter agent carries out Phase 3 TDD execution?
| Checked | Without skill | With skill |
|---|---|---|
| Selects @nw-software-crafter as the crafter agent. | Missed | Passed |
The instructions your model reads when the skill loads.
Wave: CROSS_WAVE Agents: Rex (nw-troubleshooter) → selected crafter (OOP or FP per project paradigm)
End-to-end bug fix pipeline: diagnose root cause, review findings with user, then deliver regression tests that fail with the bug and pass with the fix. Ensures every defect produces a test that prevents recurrence.
INPUT: "{bug-description}"
│
├─ Phase 1: Root Cause Analysis (@nw-troubleshooter)
│ └─ /nw-root-why "{bug-description}"
│ └─ Output: RCA document with root cause chain + fix proposal
│
├─ Phase 2: User Review (INTERACTIVE — STOP here)
│ └─ Present RCA findings to user
│ └─ User confirms root cause + approves fix direction
│ └─ If user rejects → refine RCA or stop
│
└─ Phase 3: Regression Test + Fix
└─ /nw-deliver "fix-{bug-id}" — roadmap-based bugfix flow
└─ Paradigm detection determines crafter (OOP or FP)
└─ Regression test (RED) → fix (GREEN) → verify (COMMIT)
Skill loading: The troubleshooter loads its skills from ~/.claude/skills/nw-{skill}/SKILL.md:
nw-five-whys-methodology — core investigation methodologynw-investigation-techniques — systematic debugging patternsnw-post-mortem-framework — structured incident analysisInvoke @nw-troubleshooter via Agent tool:
test cases passed, vs 2 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.