Debugging
Global Kiro steering + skills — portable AI engineering layer. Pairs with template-generic-project (spec → handoff → code).
npx -y skills add LaProgrammerie/ai-engineering-core --skill 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
- 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Systematic debugging with drift checks: spec vs code, outdated handoff, reproduce, narrow, minimal fix.
SKILL.md
1.5 KB, as published. Nobody here has run it
Debugging (global)
Objective
Find root cause with a reproducible method, then propose a minimal verifiable fix.
When to use
- Failing tests, runtime errors, flaky behaviour
- Incident analysis (read-only mode if required)
Expected inputs
- Exact symptom (message, stack, screenshot)
- Environment, version, reproduction steps
- Suspected recent changes (if known)
- Logs or traces available
Steps
- Reproduce with a minimal scenario; if impossible, list what is missing.
- Narrow: bisect in time (commits) or space (modules).
- Hypotheses: rank by likelihood; disprove with evidence (logs, tests, experiments).
- Fix: target root cause; avoid expensive band-aids when a cleaner fix is reasonable.
- Harden: suggest a small test, assertion, or log to prevent recurrence.
Drift checks (behaviour mismatch)
When behaviour does not match expectations:
- Check for spec vs implementation drift (
.kiro/specs/or equivalent vs code). - Check whether
docs/ai/active/handoff.md(or equivalent) is stale relative to what was actually built. - If docs are wrong, recommend updating spec / handoff / projections — not only patching code to match outdated text.
Output format
- Current theory + evidence for / against
- Proposed fix (or options if uncertain)
- Verification steps (commands or scenarios)
Gives 0 of the 12 instructions most debug triage skills give
Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-06
- investigate root cause before proposing any fixin 102 of 839, across 65 files
- read error messages completelyin 90 of 839, across 48 files
- create a failing test case before fixingin 84 of 839, across 44 files
- reproduce the issue consistentlyin 82 of 839, across 40 files
- change one variable at a timein 82 of 839, across 42 files
- check recent changesin 74 of 839, across 35 files
- write the regression test before fixingin 74 of 839, across 36 files
- fix the root cause not the symptomin 60 of 839, across 43 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
- narrow the cause using commit bisects
- disprove hypotheses using evidence
- avoid expensive band-aid fixes
- check for spec vs implementation drift
- check if handoff docs are stale
- recommend updating incorrect docs
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.