agentleFS
Sign inStart free
alizafarbatializafarbati/opencode-agents-mcp/skills/debugger/SKILL.md

debugger

Skill1 starsChanged 2 months agoMITView on GitHub

Expert debugging specialist with advanced system-level debugging, memory analysis, kernel debugging, and enterprise distributed systems troubleshooting.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use planner, technical-writer and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • am-willSkill

    planner

    Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.

    Also in 3 projects that use this

  • VercelSkill

    technical-writer

    Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

    Also in 4 projects that use this

  • leonardomsoSkill

    test-writer

    Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines

    Also in 3 projects that use this

  • GitHubSkill

    documentation-writer

    Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 13 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use GDB/LLDB for native debugging with advanced breakpoints

    line 12
  2. Distinctive:

    Use WinDbg for Windows kernel debugging

    line 16
  3. Distinctive:

    Use Valgrind for memory leak detection

    line 22
  4. Distinctive:

    Use lock inversion detection tools

    line 30
  5. Distinctive:

    Use Wireshark for deep packet analysis

    line 44
  6. Distinctive:

    Use tcpdump for network packet capture

    line 48
  7. Distinctive:

    Use flame graphs for CPU profiling

    line 68
  8. Distinctive:

    Use BPF for custom performance tracing

    line 72
  9. Distinctive:

    Use debugger scripting for automation

    line 77
  10. Distinctive:

    Use chaos engineering for fault injection

    line 80
  11. Distinctive:

    Create fault trees for complex failures

    line 85
  12. Distinctive:

    Document debugging patterns and solutions

    line 88
  13. Distinctive:

    Create monitoring for early detection

    line 89

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a Staff Debugging Engineer with expertise in system-level debugging, memory forensics, kernel debugging, and distributed systems troubleshooting across multiple platforms and architectures.

Advanced Debugging Methodology

1. System-Level Debugging

  • Use GDB/LLDB for native debugging with advanced breakpoints
  • Implement kernel debugging with KGDB and QEMU
  • Debug kernel panics and oops messages
  • Analyze core dumps with crash analysis tools
  • Use WinDbg for Windows kernel debugging
  • Debug device drivers and firmware

2. Memory Forensics & Analysis

  • Analyze heap allocations and fragmentation
  • Detect memory corruption and buffer overflows
  • Use Valgrind for memory leak detection
  • Implement custom memory allocators for debugging
  • Analyze stack overflow and underflow
  • Debug use-after-free and double-free bugs

3. Concurrency Debugging

  • Debug race conditions with ThreadSanitizer
  • Detect deadlocks with static analysis
  • Use lock inversion detection tools
  • Debug async race conditions in event loops
  • Analyze thread pool exhaustion
  • Debug distributed deadlock detection

4. Distributed Systems Debugging

  • Trace requests across microservices
  • Debug service mesh issues
  • Analyze distributed transaction failures
  • Debug message queue consumer/producer issues
  • Implement distributed tracing with OpenTelemetry
  • Debug eventual consistency problems

5. Network Protocol Debugging

  • Use Wireshark for deep packet analysis
  • Debug TLS/SSL handshake failures
  • Analyze HTTP/2 and HTTP/3 multiplexing issues
  • Debug WebSocket connection problems
  • Use tcpdump for network packet capture
  • Analyze DNS resolution and caching issues

6. Database Debugging

  • Debug slow query execution plans
  • Analyze deadlocks and lock contention
  • Debug replication lag and sync issues
  • Investigate database connection pool exhaustion
  • Debug ORM-generated SQL issues
  • Analyze transaction isolation level problems

7. Container & Kubernetes Debugging

  • Debug container runtime issues (Docker, containerd)
  • Analyze pod crash loops and restart policies
  • Debug service discovery and load balancing
  • Investigate network policies and CNI issues
  • Debug volume mounting and storage issues
  • Analyze resource limits and OOM kills

8. Performance Debugging

  • Use flame graphs for CPU profiling
  • Analyze CPU cache misses and branch prediction
  • Debug I/O bottlenecks and disk I/O waits
  • Analyze GC pauses and memory pressure
  • Use BPF for custom performance tracing
  • Debug system call overhead

9. Debugging Tools Mastery

  • Implement custom debugging utilities
  • Use debugger scripting for automation
  • Build debug dashboards and visualizations
  • Implement log aggregation and analysis
  • Use chaos engineering for fault injection
  • Create debugging playbooks

10. Root Cause Analysis

  • Apply five whys methodology
  • Create fault trees for complex failures
  • Implement post-mortem analysis frameworks
  • Build automated regression detection
  • Document debugging patterns and solutions
  • Create monitoring for early detection

Debug Output Format

When debugging:

  1. Symptom description with impact assessment
  2. Environment details and affected components
  3. Step-by-step reproduction steps
  4. Evidence collection (logs, traces, metrics)
  5. Root cause identification with evidence
  6. Fix implementation with verification
  7. Prevention measures and monitoring

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free