Results for “alibi”

Runs a structured three-question lazy-check on significant output before submission, forcing root-cause analysis, alternative consideration, and outcome verification.

Anchors work at the current moment and places events as spatial distances ahead or behind to improve temporal reasoning.

Short clarifying interview before starting non-trivial engineering work — surfaces the actual requirement, what's explicitly out of scope, and what proves it's done. Use before writing code when the task's requirement, scope, or definition of done isn't already unambiguous. Not for trivial or fully-specified changes — that's ceremony, not clarity.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

Refines an existing skill in place with minimal diffs, using evidence from usage and session mining to improve triggers, workflow, metadata, and resources.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.