Loading...
Loading...
Found 16 Skills
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.
Systematic debugging with hypothesis-driven investigation. Use when diagnosing bugs, errors, or unexpected behavior. Phases: Reproduce, Hypothesize, Investigate, Fix, Verify, Regression.
Debug problems by investigating multiple hypotheses in parallel. Use when you have a bug, unexpected behaviour, or mystery where the root cause is unclear. Spawns parallel investigator agents each pursuing a different theory, then compares evidence to identify the most likely cause and fix.
Find the cause of a failure and prove it before any fix. No hypothesis before a command that already reproduces the symptom. Covers building a signal that reproduces, ranking rival explanations with what would falsify each, probing without fixing, putting the regression test where the bug actually occurs, and reporting the causal chain at file:line. Use when the user says "this is broken", "why is this failing", "tests fail after my change", "it only breaks sometimes", or reports something throwing, hanging, or newly slow. Not for judging a change that already exists, or for an error whose message already names the file, line, and cause.
Diagnose reproducible bugs using temporary runtime probes and captured evidence.
Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs with human-in-the-loop verification. Only for hard-to-diagnose bugs; in those cases, remind the user that debug-mode is available, and never proactively activate this skill.
Investigate a bug observed in the running application by reading the generated code in plain_modules/, tracing the issue back to the specs, and fixing only the .plain files. Generated code is never modified. Use when the user reports unexpected behavior, visual glitches, crashes, or incorrect logic in the app.
Diagnose and fix bugs using runtime execution traces. Use when debugging errors, analyzing failures, or finding root causes in Python, Node.js, or Java applications.
Investigate unclear, intermittent, unexpected, or performance-related behavior and report an evidence-backed cause and next action. Use for requests asking why something happens. Do not implement a fix unless the user also requests correction or safe diagnostic instrumentation requires a change.
Triage a bug report. Reproduces the bug, diagnoses the root cause, verifies whether the behavior is intentional, and attempts a fix. Use when asked to "triage issue
Diagnose unexpected Three.js WebGPU/TSL runtime, rendering, API, asset, or version behavior. Use for a concrete failure, a suspected upstream regression or known issue, or a choice among an application fix, released upgrade, bounded workaround, upstream report, and blocker.