fastapi-debug

Solid

Use when the user reports an error, bug, or unexpected behavior in this repo and wants help diagnosing it. Five phases — reproduce, diagnose root cause (read-only), write a failing test, fix, verify against the full suite.

Code & Development 11 stars 0 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 79/100

Stars 20%
36
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

Debug the error or issue the user described. Do NOT jump to a fix. Follow these phases in order. --- ## Phase 1: Reproduce and Understand 1. **Read CLAUDE.md** for project structure, test commands, and known pitfalls. 2. **Read any `.claude/rules/*.md`** whose `paths:` glob matches the file(s) where the bug surfaces. Path-scoped rules often encode the conventions a fix needs to respect. 3. **Understand the failure.** What exactly is going wrong? Read the error message, stack trace, or described behavior carefully. Identify: - What is the expected behavior? - What is the actual behavior? - When did it start? Run `git log --oneline -10` to check for recent changes that could be the cause. 4. **Reproduce it.** If there's a test command or way to trigger the bug, run it now. If you can't reproduce it, say so before proceeding — a fix you can't verify is a guess. --- ## Phase 2: Diagnose Do NOT write any fix yet. Investigate read-only until you understand the root cause. 1. **Find the code path.** Starting from the error location or the described behavior, trace the execution. The three operations below are independent — issue them as a single batch of parallel tool calls, not sequentially: - Grep for the error message, function name, or component. - Read the file where the failure occurs — the full file, not just the function. - Trace backwards: what calls this code? What data does it receive? 2. **Find the actual data source.** If the bug involves wrong ...

Details

Author
steph-dove
Repository
steph-dove/klaussy-agents
Created
4 months ago
Last Updated
yesterday
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category