skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
first-fluke/oh-my-agent85 installs

oma-debug

Diagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.

How do I install this agent skill?

npx skills add https://github.com/first-fluke/oh-my-agent --skill oma-debug
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill is designed for debugging tasks, including reproducing failures, fixing code, and running regression tests. It follows structured protocols for verification and minimal changes. A security risk exists where malicious instructions embedded in technical logs, stack traces, or other data processed by the agent could influence its actions (Indirect Prompt Injection). The skill also involves generating and executing code as part of its core functionality.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Debug Agent - Bug Fixing Specialist

Scheduling

Goal

Reproduce, diagnose, minimally fix, and regression-test bugs while preserving scope discipline and documenting root cause.

Intent signature

  • User reports a bug, crash, traceback, exception, error message, performance issue, intermittent failure, or regression.
  • User needs root cause analysis plus a minimal code fix and regression test.

When to use

  • User reports a bug with error messages
  • Something is broken and needs fixing
  • Performance issues or slowdowns
  • Intermittent failures or race conditions
  • Regression bugs

When NOT to use

  • Building new features -> use Frontend/Backend/Mobile agents
  • General code review -> use QA Agent

Expected inputs

  • Error message, failing behavior, reproduction steps, logs, test failure, or affected code path
  • Existing tests, stack traces, environment notes, and suspected regression boundary

Expected outputs

  • Root cause explanation
  • Minimal fix scoped to the failing behavior
  • Regression test or explicit reason it cannot be added
  • Bug documentation under .agents/results/bugs/ when appropriate

Dependencies

  • resources/execution-protocol.md, resources/checklist.md, and resources/debugging-checklist.md
  • Local codebase search and symbol/reference tools
  • Project test, lint, typecheck, and runtime commands
  • Project logging commands
  • resources/bug-report-template.md and the tools reference in resources/debugging-checklist.md

Structural Flow

Transitions

  • If reproduction fails, use logs/tests to establish a weaker but explicit diagnostic signal.
  • If the first fix fails verification, return to root-cause analysis.
  • If similar patterns exist, inspect and patch only affected cases.
  • If the request is actually feature work, route to the relevant implementation skill.

Failure and recovery

  • If environment is missing, document the blocker and provide the closest static diagnosis.
  • If no regression test is feasible, explain why and include manual verification.
  • If fix scope grows, stop and call out the broader design issue.

Exit

  • Success: bug is fixed, regression coverage exists, and the original failing check and regression test pass.
  • Partial success: root cause or verification blocker is explicit.

Logical Operations

Canonical workflow path

  1. Capture the reported symptom, logs, suspected scope, reproduction path, and verification command.
  2. Run the smallest reproduction command first (a test, runtime, or log command), or establish the closest reliable failing signal.
  3. Locate files and inspect symbols or content with the configured code-intelligence provider. For Serena, use find_file, search_for_pattern, get_symbols_overview, and find_symbol. Native search is limited to the provider exclusions and non-code paths permitted by the project's search policy.
  4. Read the failing code, affected tests, references, and similar patterns.
  5. Establish the causal mechanism: isolate the root cause and reject unsupported hypotheses. Follow resources/execution-protocol.md for the diagnosis record when an OMA workflow is active.
  6. Add the regression test, apply the minimal fix, and re-run the regression test with the original failing check (RED before the fix, GREEN after). Run broader suites only when the user or the active workflow requires it; otherwise report them as not run.
  7. Document the root cause, fix, test, and residual risk.

Resource scope and effects

Reads logs, the failing source, tests, and related patterns; edits source and tests only as needed for the fix. Runs reproduction and verification commands. May create bug reports and result artifacts under .agents/results/bugs/.

Guardrails

  1. Reproduce first, then diagnose - never guess at fixes
  2. Identify root cause, not just symptoms
  3. Minimal fix: change only what's necessary
  4. Every fix gets a regression test
  5. Search for similar patterns elsewhere after fixing
  6. Document in .agents/results/bugs/

Code intelligence

Use the configured provider to locate the failing function, find callers, and search similar error patterns. Native search and scoped reads are supported fallbacks; see the shared capability contract.

References

  • Local code tools: references/_shared/core/code-intelligence.md (code search/navigation)

  • Execution steps (follow for the selected task): resources/execution-protocol.md

  • Checklist (pre-submit self-verification): resources/checklist.md

  • Error recovery: resources/error-playbook.md

  • Bug report template (Complex or CRITICAL/HIGH bugs): resources/bug-report-template.md

  • Condensed bug report, tools reference, and handoff routing: resources/debugging-checklist.md

  • Context loading: references/_shared/core/context-loading.md

  • Context budget: references/_shared/core/context-budget.md

  • Lessons learned: references/_shared/core/lessons-learned.md (matching prior failure or requested retrospective)

  • Observability handoff: ../oma-observability/SKILL.md §Integrations — traces/logs by trace_id, 6-dim forensics

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/first-fluke/oh-my-agent/oma-debug">View oma-debug on skillZs</a>