skill debug

AI Community

Skill notes

Purpose

This document defines a self-directed debugging workflow for a Large Language Model (LLM) operating inside or alongside Visual Studio Code: (VS Code:). The goal is for the LLM to: Inspect a codebase without human intervention Identify likely failure points Insert breakpoints programmatically Generate a valid VS Code: launch.json debugging configuration

High-Level Debugging Strategy

The LLM must operate as a deterministic debugger, not a conversational assistant. Core principles: Prefer evidence over speculation Favor runtime inspection over static guesses Never suppress errors at source

Step 1: Workspace Reconnaissance

Enumerate the workspace root Identify: Primary language(s) Entry points (e.g. main.py, index.js, app.ts, Program.cs) Existing test suites

Step 2: Static Code Analysis

For each execution path: Parse the AST (or equivalent) Identify: Unhandled exceptions Unsafe casts

Step 3: Breakpoint Placement Heuristics

Automatically insert breakpoints at: Program entry point All caught and uncaught exception blocks Function boundaries with: Complex conditionals

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
AI
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@Noizefield · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Linux · Windows
Runtime requirements
Node.js · Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 1: Workspace Reconnaissance

Enumerate the workspace root Identify: Primary language(s) Entry points (e.g. `main.py`, `index.js`, `app.ts`, `Program.cs`) Existing test suites

02
Step 2: Static Code Analysis

For each execution path: Parse the AST (or equivalent) Identify: Unhandled exceptions Unsafe casts

03
Step 3: Breakpoint Placement Heuristics

Automatically insert breakpoints at: Program entry point All caught and uncaught exception blocks Function boundaries with: Complex conditionals

04
Step 4: Generate VS Code: Debug Configuration

Create or update:

05
Step 5: Enter Debug Mode

Invoke VS Code: command: `Debug: Start Debugging` Confirm debugger attachment Verify all breakpoints are registered If debugger fails to attach, halt and report configuration errors.

06
Step 6: Runtime Observation

While execution is paused or running: Capture: Call stacks Variable states Heap/closure values (where available)

07
Step 7: Error Telemetry Handling

Step 7: Error Telemetry Handling

08
Step 8: Transmission Back to the LLM

Transmit a structured payload containing: Workspace map Breakpoint list `launch.json` Execution timeline

09
Step 9: Iterative Debugging Loop

If the root cause is not definitive: Adjust breakpoints Restart debug session Narrow scope Repeat until failure is explained by evidence

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.