Systematic debugging
Skill kimtth/agent-skill-100-lines-or-less/skills/systematic-debugging
🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
npx -y skills add kimtth/agent-skill-100-lines-or-less --skill systematic-debuggingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 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
Use when: a bug is unclear and you need a hypothesis-driven loop instead of random edits.
SKILL.md
1.1 KB, 214 tokens by cl100k_base, as published. Nobody here has run it
Goal: find the true cause with evidence before changing code.
Use for:
- intermittent, surprising, or hard-to-reproduce failures
- bugs that resisted a first guess fix
- behavior that contradicts your mental model
Workflow:
- Reproduce reliably; capture the smallest failing case.
- Observe exact symptoms, errors, and recent changes.
- Form one falsifiable hypothesis about the cause.
- Design the cheapest test that would prove it wrong.
- Run it, read the evidence, keep or discard the hypothesis.
- Once confirmed, fix the cause and verify the original case.
Tactics:
- bisect inputs, commits, or code paths to localize
- add temporary logging at the boundary, not everywhere
- check assumptions about data, types, and timing first
Rules:
- one hypothesis at a time; do not change several things at once
- never claim a fix without reproducing then re-verifying
- treat a passing run after a guess as luck until explained
- remove temporary instrumentation when done
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most debug triage skills give in 214 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 the cheapest disproof test
- run the test and read the evidence
- fix the confirmed cause
- verify the original case
- add temporary logging at boundaries
- check data, type, and timing assumptions
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.