Skip to content

startupbros-com/skill-tuner

v0.10.0MIT

Tells you whether a change to an agent-consumed document actually worked: paired comparison with a confidence interval and a non-inferiority margin, content-hashed provenance with drift detection, and an adversarial defect probe. Reads Anthropic's skill-creator benchmark output and supplies the verdict it stops short of.

scripts

  • skill-tuner
  • scripts/compare.py
  • scripts/doctor.sh
  • scripts/endtask.py
  • scripts/gate.py
  • scripts/plugineval.py
  • scripts/portfolio.py
  • scripts/probe.py
  • scripts/provenance.py
  • scripts/routing_parity.py
  • 19 more
    • scripts/skillcreator.py
    • scripts/tests/__init__.py
    • scripts/tests/test_cli_wiring.py
    • scripts/tests/test_compare.py
    • scripts/tests/test_doctor.py
    • scripts/tests/test_endtask.py
    • scripts/tests/test_envelope.py
    • scripts/tests/test_gate.py
    • scripts/tests/test_manifests.py
    • scripts/tests/test_paired_json.py
    • scripts/tests/test_plugineval.py
    • scripts/tests/test_portfolio.py
    • scripts/tests/test_probe.py
    • scripts/tests/test_provenance.py
    • scripts/tests/test_release_train.py
    • scripts/tests/test_routing_parity.py
    • scripts/tests/test_runner_core.py
    • scripts/tests/test_skillcreator.py
    • scripts/tune.py
plugin.json
name
skill-tuner
version
0.10.0
description
Tells you whether a change to an agent-consumed document actually worked: paired comparison with a confidence interval and a non-inferiority margin, content-hashed provenance with drift detection, and an adversarial defect probe. Reads Anthropic's skill-creator benchmark output and supplies the verdict it stops short of.
author
StartupBros / House of Vibehttps://houseofvibe.ai
license
MIT

What else this package ships

These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.

  • 27Python files
  • doctor.sh
  • 2YAML files
  • plugin-eval-aggregate-result.json
  • LICENSE
View on GitHub