agentsclimarketplace

Systematic debugging

Skill Tsurai7/agentic-playbook/skills/systematic-debugging

Portable playbook for coding agents: always-on principles, user rules, and triggered skills.

Install
npx -y skills add Tsurai7/agentic-playbook --skill systematic-debugging

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 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 root-cause debugging: investigate before fixing, log hypotheses, trace data flow, and stop to reassess after 3 failed fix attempts. Use when debugging a non-obvious failure, when a fix attempt did not work, or when asked to find a root cause. Skip for trivial errors whose cause is stated in the error message.

SKILL.md

2.1 KB, as published. Nobody here has run it

Systematic debugging

The Iron Law

No fixes without investigation. Reproduce the failure first, read the actual error (not what you assume it says), and locate the failing layer before editing anything. A fix that skips investigation is a guess.

Hypothesis loop

Before each probe, write one line: HYPOTHESIS: <what you believe is wrong and why> → TEST: <cheapest observation that can falsify it>. Run the test — a log line, an assertion, a targeted read — and record what it ruled out. If the hypothesis is wrong, don't guess again blind — return to gathering evidence.

Trace the data, not the blame

Follow the value through the layers it passes through (input → transform → output) until you find the first place reality diverges from expectation. Fix at the divergence point, not at the symptom. A fix proposed before tracing the data flow is a guess, not a diagnosis.

The 3-strikes stop rule

After 3 failed fix attempts — three HYPOTHESIS lines whose fixes did not survive their test — STOP. Do not try variant #4 of the same idea. Re-read the evidence, list what every failed attempt assumed in common, and question that shared assumption — it is usually a wrong architectural belief, not a string of bad luck. Escalate or ask the user rather than continuing to guess.

Exit criteria

A fix ships only with the reproducing check that now passes — see verification-before-completion for the evidence bar before claiming done.

Provenance

Distilled from the gstack /investigate skill by Garry Tan (garrytan/gstack, MIT) — method only, none of the gstack runtime (no telemetry, gbrain, or scope-freeze tooling carried over).

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.