error-recovery
Error Recovery
Overview
AI agents get stuck. They try the same approach repeatedly, add complexity to fix complexity, and rationalize "one more attempt" long past the point of diminishing returns. This skill detects stuck patterns proactively and forces recovery before wasted effort compounds.
Core principle: Track every failed attempt. Escalate at defined thresholds. Never allow unbounded retries.
The Prime Directive
NO CONTINUED ATTEMPTS WITHOUT ACKNOWLEDGING FAILURE COUNT
Before EVERY fix attempt, state: "This is attempt N of the current issue." If N >= 3, you are not authorized to continue without user direction.
When to Use
This skill activates automatically when any of these patterns appear:
More from noobygains/godmode
fault-diagnosis
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
15task-planning
Use when you have a spec or requirements for a multi-step task, before touching code
15agent-messaging
Use when dispatching subagents, composing prompts for teammates, structuring handoff reports, or managing context boundaries between agents. Covers both subagent prompts and team-level messaging.
15intent-discovery
Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.
15quality-enforcement
Use when preparing code for commit, PR, or merge - covers linting, type safety, bundle budgets, coverage thresholds, complexity limits, dependency audit, and dead code detection
14pattern-matching
Use when contributing code to an existing project - guarantees that every new line mirrors the established conventions, naming schemes, architectural layering, directory layout, and stylistic choices already present in the codebase rather than drifting toward generic AI defaults
14