Nw Bugfix logo

Nw Bugfix

Organization
nWave-ai
nw-bugfix

Bug fix workflow: root cause analysis → user review → regression test + fix via TDD

Overview

PublishernWave-ai
RepositorynWave
Skill namenw-bugfix
Stars
616
Forks
65
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by nWave-ai on GitHub. Read the source before you install it.

Installation

Install the Nw Bugfix AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-bugfix
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nWave-ai/nWave.git /tmp/nWave
mkdir -p .claude/skills
cp -r /tmp/nWave/nWave/skills/nw-bugfix .claude/skills/nw-bugfix
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nw Bugfix in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nw Bugfix on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nw Bugfix is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

NW-BUGFIX: Defect Resolution Workflow

Wave: CROSS_WAVE Agents: Rex (nw-troubleshooter) → selected crafter (OOP or FP per project paradigm)

Overview

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.

Flow

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)

Execution Steps

Phase 1: Root Cause Analysis

Skill loading: The troubleshooter loads its skills from ~/.claude/skills/nw-{skill}/SKILL.md:

  • nw-five-whys-methodology — core investigation methodology
  • nw-investigation-techniques — systematic debugging patterns
  • nw-post-mortem-framework — structured incident analysis

Invoke @nw-troubleshooter via Agent tool:

Execute *investigate-root-cause for the following defect:

{bug-description}

Configuration:
- investigation_depth: 5
- multi_causal: true
- evidence_required: true

Produce:
1. Root cause chain (5 Whys with evidence at each level)
2. Contributing factors
3. Proposed fix with specific code changes
4. Files affected
5. Risk assessment of the fix

After the troubleshooter returns, present findings to the user. Include:

  • Root cause summary (1-2 sentences)
  • Evidence chain
  • Proposed fix
  • Files to modify
  • Risk level

STOP and wait for user confirmation before proceeding to Phase 3.

Phase 2: User Review

Present the RCA findings and ask:

  1. "Does this root cause match your understanding?"
  2. "Do you approve the proposed fix direction?"
  3. "Any additional constraints or context?"

If user rejects:

  • Refine the RCA with additional context
  • Or stop the workflow entirely

If user approves → proceed to Phase 3.

Phase 3: Regression Test + Fix

Phase 3 dispatches the fix through the roadmap-based bugfix flow. It does paradigm detection (reads project CLAUDE.md for ## Development Paradigm), crafter selection (@nw-software-crafter for OOP, @nw-functional-software-crafter for FP), DES enforcement, and reads the rigor profile from .nwave/des-config.json.

Preparation:

  1. Derive feature-id: fix-{kebab-case-bug-summary} (max 5 words)
  2. Create docs/feature/{feature-id}/deliver/ directory
  3. Prepare RCA context from Phase 1 output (root cause, files affected, proposed fix)

Delegate to /nw-deliver:

/nw-deliver "fix-{bug-summary}"

The deliver orchestrator builds a minimal two-step roadmap:

Step 01-01: Regression test (RED)

  • Write a test that reproduces the exact defect
  • Test MUST fail against current code (proves the bug exists)
  • Test location: tests/regression/{component}/ or tests/bugs/
  • Test name: test_bug_{description}.py

Step 01-02: Fix implementation (GREEN)

  • Implement the minimal fix identified in RCA
  • Run ALL tests — regression test must now PASS
  • Existing tests must not regress

The crafter handles the TDD cycle (3-phase canon RED → GREEN → COMMIT per ADR-025) with DES monitoring.

Success Criteria

  • Root cause identified with evidence at each causal level
  • User reviewed and approved fix direction
  • Regression test written that fails with the bug
  • Fix implemented that makes the regression test pass
  • All existing tests still pass (no regressions)
  • Commit with conventional message: fix(scope): description

Examples

Example 1: Runtime crash

/nw-bugfix "DES hook crashes with FileNotFoundError when template schema is missing"

Phase 1: Rex traces to missing step-tdd-cycle-schema.json in plugin cache. Phase 2: User confirms. Phase 3: /nw-deliver "fix-missing-template-schema" → crafter writes test_bug_missing_template_schema.py (RED), adds fallback path resolution (GREEN), commits.

Example 2: Silent failure

/nw-bugfix "Skills plugin reports success but installs zero files when source has nw-prefixed layout"

Phase 1: Rex traces to is_public_skill() returning False for all nw-prefixed names due to ownership map key mismatch. Phase 2: User confirms. Phase 3: /nw-deliver "fix-ownership-map-keys" → crafter writes regression test with nw-prefixed fixture (RED), fixes ownership map keys (GREEN), commits.

Example 3: Functional project bug

/nw-bugfix "Pipeline composition breaks when filter predicate returns None"

Phase 1: Rex traces to missing None guard in compose() function. Phase 2: User confirms. Phase 3: /nw-deliver "fix-compose-none-guard" → paradigm detected as FP → @nw-functional-software-crafter writes property-based test (RED), adds None guard (GREEN), commits.

Notes

  • This command is for known defects (something is broken). For new features, use /nw-deliver.
  • The regression test is the primary deliverable — it prevents the bug from recurring.
  • Keep the fix minimal. Refactoring belongs in /nw-refactor, not here.
  • If the RCA reveals a design flaw (not just a code bug), escalate to /nw-design before fixing.
  • Phase 3 delegates to /nw-deliver, which handles paradigm detection, DES enforcement, and rigor profile automatically.

Frequently asked questions

What does the Nw Bugfix AI skill do?

Bug fix workflow: root cause analysis → user review → regression test + fix via TDD

Why use Nw Bugfix on TypingMind?

Because you install it once and use it with any model. Nw Bugfix is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nw Bugfix in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-bugfix. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Nw Bugfix?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nw Bugfix?

As many as you like. As long as a model supports skills, you can use Nw Bugfix with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nw Bugfix AI skill free?

Yes. It is published on GitHub by nWave-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇