Results for “trajectory-inference”

Resolves legacy references to the tdd-guide capability by routing to the current runtime's equivalent agent, plugin, or skill.

Resolves legacy references to the remotion-engineer skill by routing to the modern runtime capability.

Analyzing session replays, extracting persona-based behavioral patterns, and storytelling UX issues. Reads the 'why' from real user operation logs. Works with Field/Echo for persona validation.

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.

Influence Functions in Deep Learning

Resolves legacy references to the devops-engineer capability by routing to the current runtime agent or plugin skill.

Resolves legacy references to the cyber-intel capability by routing to the current runtime agent or skill.

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Imported skill analyze from langchain

Bundles a prompt with selected files into a one-shot request for another model, supporting API and browser engines with session reattachment.