YAO
31ce04c655
Merge the beta-ready Yao Meta Skill architecture, report, evidence gate, and release-boundary updates.\n\nRelease boundary: beta/public testing is allowed; formal world-class, fully reviewed, or superiority claims remain blocked until the pending evidence gates are accepted.
Examples
This directory shows complete examples from raw workflow input to final skill package shape.
It is organized in three tiers:
simple-note-cleanup: a small personal workflowteam-frontend-review: a team-level reusable workflowcomplex-release-orchestrator: a multi-step, higher-complexity workflowgoverned-incident-command: a governed operational asset with lifecycle metadata, review cadence, and evidence reports
Each example contains:
raw-workflow.md: what the user originally givesdesign-summary.md: how the meta-skill scopes and structures the resultgenerated-skill/: the resulting skill package shape
Some examples also include:
optimization/: example-specific baseline descriptions, semantic configs, dev/holdout suites, and route-optimization reportsoptimization/blind_holdout/: acceptance prompts used only after the winner is chosen on devoptimization/adversarial/: harder route-collision prompts used to measure noisy positives, deceptive negatives, and family-level calibration
The complex example is intentionally thicker than the others and includes:
manifest.jsoninput/andoutputs/sample artifactsevals/trigger_cases.json- richer references and a deterministic script
The governed example adds:
- explicit lifecycle and maturity metadata
- review policy and governed ownership
- reports for maturity and revision history
- context budget evidence
- a stronger example of how reusable skills become maintained assets
Additional evolution example:
evolution-frontend-review/: shows raw workflow, v0, v1, final, and eval delta