Milestones

List view

• Evaluation & effectiveness

  Improve the evals/ harness and how skill quality is measured: ground-truth generation, per-runtime measurement, review-quality scoring, model benchmarking, triggering-eval coverage, and F1/recall tracking behind the repo's effectiveness claims. Anchor doc: evals/EVALUATION_IMPROVEMENT_PLAN.md

  No due date

  •1/1 issues closed
  100% complete0 open1 closed

• New skills

  New wa-review skill variants/companions. Issues: #106, #89

  No due date

  •5/5 issues closed
  100% complete0 open5 closed

• Install & packaging parity

  Cross-platform install parity and devops-agent packaging. Issues: #102, #53

  No due date

  •4/4 issues closed
  100% complete0 open4 closed

• Continuous WA / CI

  Machine-readable wa-review output + CI gate + drift guard. Issues: #90, #118 (PR #119)

  No due date

  •8/9 issues closed
  88% complete1 open8 closed

• Crawler reliability

  Fix crawler content drops and normalize lens references; unblocks new lenses. Issues: #80 (blocker), #99, #75, #76

  No due date

  •4/6 issues closed
  66% complete2 open4 closed