Repository navigation
feat(ab): paired with/without-skill lift and trigger rate - #1
Merged
Merged
Conversation
Add compare_skill and run_ab so authors can measure causal lift of a SkillSpec against a withheld baseline, plus trigger rate. Stdlib only.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
SkillSpec,compare_skill, andrun_abfor paired with vs without skill evaluationexamples/skill_ab.py+ tests; existingscore()API unchangedMotivation
Community wishlist: static suites inflate gains when the agent never loads the skill. Authors need causal with/without lift and an explicit trigger-rate signal — still zero-deps / no framework.
Verification
pytest -q— 6 passedpython -m compileall -q src testspython examples/quickstart.pypython examples/skill_ab.pyRisk
Opt-in module. Pure functions; no I/O. No new dependencies.