185 skills · sorted by relevance
Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
The English summary is being prepared. Showing the original description.
Trace bugs backward through call stacks and execution flows to identify the original source of errors, invalid data, or incorrect behavior. Use when debugging complex issues, tracing error origins, investigating data corruption, following execution paths, identifying where invalid data enters the system, or finding root causes of cascading failures.
The English summary is being prepared. Showing the original description.
Fix broken or failing functionality through structured reproduction, root-cause analysis, minimal fix, and verification. Load when the user asks to fix a bug, debug an error, resolve an issue, or work on a Linear ticket. Also triggers on "this is broken", "fix this bug", "why is this failing", "debug this", "resolve this error", "what went wrong", or any request to diagnose and fix a problem.
The English summary is being prepared. Showing the original description.
Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.
The English summary is being prepared. Showing the original description.
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
The English summary is being prepared. Showing the original description.
Designs or reviews provenance-bound DAG attempt traces, coverage gaps, cancellation, and unknown-effect reconciliation. NOT for claiming execution completeness, deployment monitoring, or root-cause proof.
The English summary is being prepared. Showing the original description.
Investigates DAG incidents with a precise top event, timeline, competing hypotheses, barriers, propagation, and bounded recovery. NOT for automated root-cause classification, trace collection, or performance profiling.
The English summary is being prepared. Showing the original description.
Naturalistic causal reasoning for failures and disputed attribution. Use when postmortems or root-cause debates need reframing. NOT for causal inference, fault trees, or fully observed failures.
The English summary is being prepared. Showing the original description.
Naturalistic causal reasoning for failures and disputed attribution. Use when postmortems or root-cause debates need reframing. NOT for causal inference, fault trees, or fully observed failures.
The English summary is being prepared. Showing the original description.
Diagnostic method for any bug, failure, regression, flake, or slowdown. Use before proposing a fix: something is broken, throwing, not saving, not showing, or 'worked yesterday'; on 'debug this' or 'find the root cause'; and immediately after a fix attempt did not work.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "このエラーを直して", "help me debug this", "fix this stack trace", "なぜこのエラーが出るの", "CI が落ちた", or pastes an error message or stack trace and wants help diagnosing it. Classifies the error type, identifies related files, and proposes up to three root-cause hypotheses with concrete fix plans.
The English summary is being prepared. Showing the original description.
Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.
The English summary is being prepared. Showing the original description.
Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.
The English summary is being prepared. Showing the original description.
[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes. Use when the task requires investigation, root-cause analysis, or mapping unknown areas. Always maintain a research log file that captures findings, hypotheses, and next branches; use web.run when external verification is needed.
The English summary is being prepared. Showing the original description.
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
The English summary is being prepared. Showing the original description.
4-phase root cause debugging: understand bugs before fixing.
The English summary is being prepared. Showing the original description.
Repair one concrete reproducible build, typecheck, lint, test, packaging, or CI failure with a bounded root-cause-first loop; do not trigger for runtime bugs without a failing gate, broad test strategy, dependency/toolchain migration, or generic implementation.
The English summary is being prepared. Showing the original description.