Debugger
Skill Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/debugger
Behavioral execution framework for AI agents — define deterministic, portable skills & agents across OpenCode, Claude Code, Gemini CLI, and Qwen Code.
npx -y skills add Razaib-khan/ForgeWeave --skill debuggerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Systematic issue diagnosis skill that isolates root causes, tests hypotheses, and produces minimal fix strategies
SKILL.md
2.8 KB, 567 tokens by cl100k_base, as published. Nobody here has run it
Debugger
Purpose
Apply systematic debugging methodology to identify root causes of software issues. Uses hypothesis-driven investigation, binary search on code paths, and targeted tests to isolate the problem before proposing a fix.
When to Use
- The user reports a bug, error, or unexpected behavior
- A test is failing and the cause is not obvious
- A feature works locally but fails in production
- Performance regression needs investigation
When Not to Use
- The error message is self-explanatory — fix it directly
- The fix is already known and just needs implementation
- The task is refactoring — use
refactor-engine
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
symptom | string | Yes | The observed error or unexpected behavior |
reproduction_steps | string | No | Steps to reproduce the issue |
environment | string | No | Environment details (OS, versions, deployment) |
logs_or_stacktrace | string | No | Error output, logs, or stack trace |
Expected Outputs
| Output | Description |
|---|---|
| Root cause | Identified source of the issue |
| Fix strategy | Minimal change to fix the issue |
| Verification steps | How to confirm the fix works |
| Prevention | How to avoid similar issues |
Exact Workflow Steps
- Understand the symptom and reproduction steps
- Formulate 2-3 hypotheses for root cause
- For each hypothesis, design a diagnostic test
- Narrow down by eliminating hypotheses
- Isolate the exact root cause
- Design minimal fix that doesn't break other functionality
- Verify fix resolves the symptom
- Run existing tests to confirm no regressions
Required Checks
- Root cause is identified before any fix is proposed
- Fix is minimal (no scope creep)
- Existing tests pass after fix
- Prevention strategy is documented
Failure Modes
| Failure Condition | Response |
|---|---|
| Cannot reproduce the issue | Ask for more detailed reproduction steps |
| All hypotheses eliminated | Broaden search to adjacent systems or dependencies |
| Fix breaks other functionality | Revert and explore alternative fix strategy |
Examples
Example: "API returns 500 intermittently"
- Hypotheses: database connection pool exhaustion, unhandled exception, timeout
- Check connection pool metrics → pool is fine
- Add error logging around the failing endpoint → caught unhandled promise rejection
- Fix: wrap async handler in try/catch
References
| Reference | Path |
|---|---|
| Test Generator skill | ../test-generator/SKILL.md |
What ships with it: 2 files
3.9 KB alongside SKILL.md, 1 of them executable
references/
- debugging-methodology.md1.5 KB
scripts/
- hypothesis_tracker.pyruns2.4 KB
Gives 0 of the 12 instructions most debug triage skills give in 567 tokens
Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07
- Investigate root cause before proposing any fixin 102 of 839, across 67 files
- Read error messages completelyin 89 of 839, across 49 files
- Create a failing test case before fixingin 84 of 839, across 46 files
- Reproduce the issue consistentlyin 82 of 839, across 41 files
- Change one variable at a timein 82 of 839, across 42 files
- Check recent changesin 74 of 839, across 36 files
- Write the regression test before fixingin 74 of 839, across 40 files
- Fix the root cause not the symptomin 60 of 839, across 45 files
- Implement a single fix at a timein 59 of 839, across 20 files
- Trace data flow backward to the sourcein 50 of 839, across 20 files
- Remove all debug instrumentationin 49 of 839, across 13 files
- Form a single hypothesisin 48 of 839, across 18 files
Said here and by no other author read
- design a diagnostic test per hypothesis
- eliminate hypotheses to narrow down
- ask for detailed steps if unreproducible
- broaden search if all hypotheses eliminated
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.