Loading...
Loading...
Found 5 Skills
When user asks about "confidence", "accuracy", "how sure", "uncertain", "reliable", "track record", or when Claude should express calibrated uncertainty. Enables domain-aware self-assessment.
You must use this when merging findings from multiple studies into a coherent narrative with grounded evidence.
This skill should be used when analyzing codebases, understanding architecture, or when "analyze", "investigate", "explore code", or "understand architecture" are mentioned.
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
Use this skill when you are not sure about a fact, have outdated knowledge, or the question is contested. Explicitly communicate the level of confidence instead of asserting uncertain things as fact.