Systematically debugs and resolves software regressions.
Install
mkdir -p .claude/skills/diagnose-tr3kkr && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16512" && unzip -o skill.zip -d .claude/skills/diagnose-tr3kkr && rm skill.zipInstalls to .claude/skills/diagnose-tr3kkr
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Diagnose Yuzu bugs and performance regressions with a disciplined reproduce-minimize-hypothesize-instrument-fix-regression-test loop. Use when the user says `/diagnose`, "debug this", reports a failure, flake, broken behavior, or performance regression.Key capabilities
- →Reproduce Yuzu bugs and performance regressions
- →Minimize test cases to sharpen failure signals
- →Formulate falsifiable hypotheses for debugging
How it works
The skill follows a disciplined loop: reproduce the failure, minimize the test case, hypothesize potential causes, instrument the code to test hypotheses, fix the issue, and verify with regression tests. It emphasizes creating a fast, deterministic signal for reproduction.
Inputs & outputs
When to use diagnose
- →Debug a production regression
- →Reproduce a flaky test
- →Fix a reported bug
About this skill
Diagnose
Build a feedback loop before guessing. Read CONTEXT.md and relevant ADRs so hypotheses use Yuzu's domain vocabulary.
Loop First
Create the fastest deterministic signal that reproduces the user-visible failure:
- focused unit or integration test
scripts/start-UAT.shplus REST/gRPC/CLI probe- gateway EUnit/CT/Dialyzer command
- replayed log, request, proto payload, or DB fixture
- reduced harness around a store, handler, plugin, or gateway module
- repeated stress loop for flakes
- perf measurement before changing code
If no loop is possible, stop and ask for the missing artifact or environment. Do not proceed on vibes.
Phases
- Reproduce: confirm the loop shows the same symptom the user reported.
- Minimize: reduce the input, fixture, test, or command until the signal is sharp.
- Hypothesize: list 3-5 ranked falsifiable hypotheses and the prediction each makes.
- Instrument: probe one hypothesis at a time. Use debugger/REPL first, targeted logs second.
- Fix: add the regression test at the correct seam before the fix when possible.
- Verify: run the original loop, the regression test, and the relevant targeted suite.
- Cleanup: remove temporary probes and
[DEBUG-...]logs; delete throwaway harnesses unless intentionally kept under a debug path.
Yuzu Checks
- For Erlang failures, source
scripts/ensure-erlang.sh; rememberrebar3 eunit --moduleis not isolation. - For build/test selection, invoke
$yuzu-build. - For Meson/proto/plugin/Windows boundaries, invoke the matching Yuzu skill.
- For performance, use measurement scripts such as
scripts/test/perf-gate.shor a narrow harness before and after. Perf gates are measure-only unless the specific test enforces a threshold.
Final Report
State the reproduced symptom, the hypothesis that won, the fix, the regression test, exact validation commands, and any architectural gap that prevented a clean regression test.
When not to use it
- →When no deterministic signal can be created to reproduce the failure
- →When the task is outside the Yuzu domain
- →When the user wants to proceed on 'vibes' without a reproducible loop
Limitations
- →Requires a reproducible loop for diagnosis
- →Specific to Yuzu bugs and performance regressions
- →Does not proceed without a reproducible loop or missing artifacts
How it compares
This skill applies a rigorous, structured debugging process with a strong emphasis on reproducible loops and falsifiable hypotheses, providing a systematic approach to fixing Yuzu bugs and regressions unlike ad-hoc debugging.
Compared to similar skills
diagnose side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| diagnose (this skill) | 0 | 2mo | No flags | Advanced |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| chrome-devtools | 41 | 7mo | Review | Intermediate |
| bats | 9 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by Tr3kkR
View all by Tr3kkR →You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
chrome-devtools
mrgoonie
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
bats
OleksandrKucherenko
Bash Automated Testing System (BATS) for TDD-style testing of shell scripts. Use when: (1) Writing unit or integration tests for Bash scripts, (2) Testing CLI tools or shell functions, (3) Setting up test infrastructure with setup/teardown hooks, (4) Mocking external commands (curl, git, docker), (5) Generating JUnit reports for CI/CD, (6) Debugging test failures or flaky tests, (7) Implementing test-driven development for shell scripts.
browser-daemon
noiv
Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.
performance-profiling
davila7
Performance profiling principles. Measurement, analysis, and optimization techniques.
obsidian-local-dev-loop
jeremylongshore
Configure Obsidian plugin development with hot-reload and fast iteration. Use when setting up development workflow, configuring test vaults, or establishing a rapid development cycle. Trigger with phrases like "obsidian dev loop", "obsidian hot reload", "obsidian development workflow", "develop obsidian plugin".