Systematic debugging
skillet — a package manager for AI agent skills (SKILL.md). Find, install, version & share skills from a Git-backed registry. Zero infra, MCP-native, reproducible.
npx -y skills add jnMetaCode/skillet --skill systematic-debuggingAssembled 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
Root-cause a bug with a hypothesis-driven loop instead of shotgun edits. Use when a bug isn't obvious after the first look, or when asked to "find out why" something fails.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.2 KB, as published. Nobody here has run it
systematic-debugging
Never fix what you can't reproduce; never explain what you haven't observed. The loop is: reproduce → observe → hypothesize → test the hypothesis → narrow. One variable at a time.
Procedure
- Reproduce first. Find the smallest, fastest command that shows the
failure deterministically. If it's flaky, make the loop tight
(
while ./repro; do :; done) and treat flakiness itself as a clue (timing, ordering, shared state). - Read the actual error. The full message, the first stack frame in your own code, and the line right before things went wrong. Resist pattern-matching to a familiar failure — verify this one.
- State a falsifiable hypothesis ("the cache returns stale entries after a restart") and pick the cheapest observation that could kill it: a log line, an assertion, a debugger breakpoint, one curl.
- Bisect the space, whichever axis is cheapest:
- history:
git bisect run ./repro - data: half the failing input, recurse
- stack: confirm the bad value at the boundary between two layers, then descend into the guilty one only
- history:
- The fix must explain the symptom. Before writing it, say why this cause produces exactly this behavior. If the explanation is fuzzy, you've found a bug, maybe not the bug.
- Prove it: the repro from step 1 now passes, AND a new regression test
fails without the fix. Then look for siblings — the same mistake usually
exists elsewhere (
grepfor the pattern you just fixed).
Anti-patterns
- Changing two things between observations — you learn nothing from the result.
- "It works now" without knowing why it failed — it will be back.
- Adding sleeps to fix timing issues — that's hiding the race, not fixing it.
- Debugging through the framework before confirming your own code's inputs and outputs at the boundary.