agentleFS
xsovad06xsovad06/sova/.agents/skills/sova-debug/SKILL.md

sova-debug

Skill3 starsChanged 4 days agoApache-2.0View on GitHub

Systematic debugging workflow (reproduce, locate, diagnose, fix, verify, prevent).

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 15 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈15

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check application logs for errors

    line 16
  2. Distinctive:

    If the issue is unclear, ask the user for more details

    line 18
  3. Distinctive:

    Read the relevant source files to understand the flow

    line 22
  4. Distinctive:

    Check recent changes with git log --oneline -10 and git diff: was something recently changed?

    line 23
  5. Distinctive:

    Search for related error messages in the codebase

    line 24
  6. Distinctive:

    Import errors / circular imports

    line 31
  7. Distinctive:

    Do not introduce workarounds: fix the actual problem

    line 39
  8. Distinctive:

    If the fix touches multiple files, explain the connection

    line 40
  9. Distinctive:

    Write a test that reproduces the original issue (should fail before fix, pass after)

    line 44
  10. Distinctive:

    Run the project's test suite (see CLAUDE.md for commands)

    line 45
  11. Distinctive:

    Check that no regressions were introduced

    line 46
  12. Distinctive:

    Verify application logs are clean

    line 47
  13. Distinctive:

    If this bug class could recur, suggest a test that would catch it

    line 50
  14. Distinctive:

    If it was caused by a missing convention, suggest updating AGENTS.md or project guidelines

    line 51
  15. Very specific:

    Need to run tests?: Run the sova-test skill to iterate on failures

    line 55
  16. Very specific:

    Want a review of the fix?: Run the sova-review skill before pushing

    line 56
  17. Distinctive:

    NEVER use emojis in any output

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Systematic Debugging

Debug an issue in the project.

Problem description: the arguments provided when this skill is invoked

Workflow

1. Reproduce

  • Understand the problem from the description
  • Check application logs for errors
  • Try to reproduce the issue (via test, curl, or browser)
  • If the issue is unclear, ask the user for more details

2. Locate

  • Identify the relevant code path (URL -> view/controller -> service -> model)
  • Read the relevant source files to understand the flow
  • Check recent changes with git log --oneline -10 and git diff: was something recently changed?
  • Search for related error messages in the codebase

3. Diagnose

  • Trace the execution flow from entry point to the error
  • Identify the root cause, not just the symptom
  • Check common issues:
    • Missing migrations or schema changes
    • Import errors / circular imports
    • Configuration mismatches between environments
    • Authentication/permission issues
    • Database constraint violations
    • Race conditions or state management bugs

4. Fix

  • Apply the minimal fix that addresses the root cause
  • Do not introduce workarounds: fix the actual problem
  • If the fix touches multiple files, explain the connection
  • Scout rule: while in each file, fix any pre-existing issues you notice (lint warnings, dead imports, obvious bugs adjacent to your fix). Keep scout fixes small and low-risk.

5. Verify

  • Write a test that reproduces the original issue (should fail before fix, pass after)
  • Run the project's test suite (see CLAUDE.md for commands)
  • Check that no regressions were introduced
  • Verify application logs are clean

6. Prevent

  • If this bug class could recur, suggest a test that would catch it
  • If it was caused by a missing convention, suggest updating AGENTS.md or project guidelines

Cross-References

  • Need to run tests? Run the sova-test skill to iterate on failures
  • Want a review of the fix? Run the sova-review skill before pushing

Rules

  • NEVER use emojis in any output
  • Focus on root cause, not symptoms

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.