forked from obra/superpowers
-
Notifications
You must be signed in to change notification settings - Fork 0
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Eval suite: mechanical assertions for well-defined operational skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#6 In mthalman/superpowers;Eval suite: simulated-user dialogue evaluation for conversational skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#5 In mthalman/superpowers;Eval suite: lift-vs-baseline LLM-judge for creative skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#4 In mthalman/superpowers;Eval suite: tool-trace / behavioral checks for agent-disciplining skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#3 In mthalman/superpowers;Eval suite: structured-output assertions for artifact-generating skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#2 In mthalman/superpowers;Eval suite: detection-harness pattern for analytical skills
evaluationSkill evaluation / test-suite workSkill evaluation / test-suite workskillsWork related to a skillWork related to a skillStatus: Open.#1 In mthalman/superpowers;