jtag-swd-debug

Deep integration with JTAG/SWD debug probes for hardware-level debugging and flash programming

509 stars

Best use case

jtag-swd-debug is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Deep integration with JTAG/SWD debug probes for hardware-level debugging and flash programming

Teams using jtag-swd-debug should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/jtag-swd-debug/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/embedded-systems/skills/jtag-swd-debug/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/jtag-swd-debug/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How jtag-swd-debug Compares

Feature / Agentjtag-swd-debugStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Deep integration with JTAG/SWD debug probes for hardware-level debugging and flash programming

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# JTAG/SWD Debug Skill

## Overview

This skill provides deep integration with JTAG/SWD debug probes for hardware-level debugging, flash programming, and real-time firmware analysis. It enables direct hardware interaction through industry-standard debug interfaces.

## Capabilities

### Debug Probe Operations
- Execute OpenOCD, J-Link, and ST-LINK commands
- Configure debug probe connections and interfaces
- Manage multiple debug probe types and adapters
- Handle transport protocols (JTAG, SWD, cJTAG)

### Memory Operations
- Read/write memory-mapped registers
- Direct memory inspection and modification
- Real-time memory watch and modification
- Flash programming and verification
- Memory dump and analysis

### Debugging Features
- Set hardware breakpoints and watchpoints
- Core state inspection (registers, stack, PC)
- Single-step execution control
- Fault handler analysis and debugging
- Call stack unwinding

### Trace and Output
- Semihosting input/output support
- SWO trace output configuration
- ITM stimulus port configuration
- Real-time trace buffer analysis

## Target Processes

- `hardware-bring-up.js` - Initial board validation and debug setup
- `bootloader-implementation.js` - Bootloader debugging and flash operations
- `device-driver-development.js` - Driver debugging with hardware access
- `field-diagnostics.js` - Field debugging and analysis

## Dependencies

- OpenOCD (Open On-Chip Debugger)
- J-Link software (Segger)
- ST-LINK utilities (STMicroelectronics)
- Debug probe hardware (J-Link, ST-LINK, CMSIS-DAP)

## Usage Context

This skill is invoked when tasks require:
- Direct hardware debugging through JTAG/SWD
- Flash memory programming operations
- Low-level register and memory inspection
- Fault analysis and crash debugging
- Hardware breakpoint management

## Configuration

```yaml
debug_probe:
  type: jlink | stlink | openocd | cmsis-dap
  interface: swd | jtag
  speed: 4000  # kHz
  target: cortex-m4 | cortex-m7 | etc.
```

## Example Operations

### Flash Programming
```bash
openocd -f interface/stlink.cfg -f target/stm32f4x.cfg \
  -c "program firmware.elf verify reset exit"
```

### Memory Read
```bash
JLinkExe -device STM32F407VG -if SWD -speed 4000 \
  -CommanderScript read_memory.jlink
```

### Register Inspection
```bash
openocd -f board/stm32f4discovery.cfg \
  -c "init; halt; reg; resume; exit"
```

Related Skills

Debugger Integration Skill

509
from a5c-ai/babysitter

Advanced debugging integration for vulnerability research

request-debugger

509
from a5c-ai/babysitter

HTTP request/response debugging and inspection tools

Debug Adapter Protocol

509
from a5c-ai/babysitter

Expert skill for implementing Debug Adapter Protocol for debugger integration

cuda-debugging

509
from a5c-ai/babysitter

Expert skill for GPU debugging using CUDA-GDB and NVIDIA Compute Sanitizer. Detect memory errors, race conditions, uninitialized memory access, validate atomic operations, analyze kernel synchronization issues, and generate debugging reports with recommendations.

fpga-debugging

509
from a5c-ai/babysitter

On-chip debugging skill with ILA, VIO, and related FPGA debug tools

systematic-debugging

509
from a5c-ai/babysitter

Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.

debugging-patterns

509
from a5c-ai/babysitter

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.