Read-only Hugging Face mirror

Turn repeated experience into one reviewable Skill change.

A WikiSkill-inspired workflow that separates raw Runs, reusable patterns, evidence gates, human review, and one bounded Skill edit.

What the project owns

The workflow converts experience only when evidence, scope, safety, and human authority align.

Runs and corrections remain evidence rather than immediately becoming instructions.

Support, counterexamples, recurrence, and scope are retained together.

One exact change is scored, reviewed, accepted, held, or rejected.

The sequence is explanatory. Install and execute the actual project locally from its canonical repository.

Select bounded Runs, failures, corrections, and protection cases.

Propose reusable patterns while retaining counterexamples.

Check scope, structure, security, evaluator integrity, and evidence quality.

A human accepts, holds, or rejects the exact proposed change.

Only one bounded Skill file changes, followed by fresh validation.

This page preserves the project's published limits instead of turning engineering checks into outcome claims.

The workflow cannot approve or publish its own Skill change.

Rejected and harmful changes remain visible rather than being erased.

A clean scorecard does not prove downstream task improvement.

Local files below are curated public mirrors. GitHub remains authoritative for development, releases, and issue history.