From devflow
Use when triaging bugs, investigating unexpected behavior, or performing root cause analysis before fixing
npx claudepluginhub nexuz-sys/devflow --plugin devflowThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Structured bug triage and investigation process. Bridges superpowers' systematic-debugging with dotcontext's bug-fixer agent.
Announce at start: "I'm using the devflow:bug-investigation skill to investigate this bug."
git log for recent changes)Ask "why?" 5 times (5-Whys technique):
Bug: User sees blank page
Why? → Component throws during render
Why? → API returns null for required field
Why? → Database migration didn't run
Why? → Deploy script skips migrations in staging
Why? → Migration step was added after deploy script was written
Root cause: Deploy script doesn't run new migrations
Before fixing, record:
For complex bugs, invoke superpowers:systematic-debugging which provides:
agent({ action: "orchestrate", agents: ["bug-fixer"], task: "<bug-description>" })
Read .context/agents/bug-fixer.md for project-specific investigation procedures.
| Pattern | Problem |
|---|---|
| Fix without reproducing | You might fix a different bug |
| Fix the symptom, not the cause | Bug will resurface differently |
| Change multiple things at once | Can't tell what actually fixed it |
| Skip documentation | Next person hits the same bug with no context |
| Blame the framework/library | 95% of the time it's your code |