MaintainAll / Evaluation
Legacy DSH skill report

DSH plugin validation

controls only. Large plugin audit cases are useful controls; no stable correctness separation from the without arm.

8/8 bothplugin audit
7/7 bothsupplychain
7/7 bothroute-authz
8/8 bothmultifinding
Disabled: Legacy cases are controls only; hidden from default skill discovery until a discriminating case is frozen. The skill is kept in the repository as SKILL.md.disabled.
No replicated correctness signal. Treat as controls until a new discriminating case is frozen.

Documented comparisons

legacy evidence, not sealed records
0255075100plugin audit: 100plugin audit: 100plugin auditsupplychain: 100supplychain: 100supplychainroute authz: 100route authz: 100route authzmultifinding: 100multifinding: 100multifindingwith skillwithout skill
Case / batchWith skillWithout skillReading
large-plugin-audit (204 files)8/88/8large control, not discriminator
large-plugin-supplychain (205 files)7/77/7efficiency hint only
large-route-authz at 807/76/7 then 7/7training case candidate; holdout only budget difference
large-plugin-multifinding at 1508/88/8large efficiency control

Source and limitations

These numbers come from benchmarks/evaluation/TASK_LEVEL.md and benchmarks/evaluation/FINAL_REPORT.md. Raw trial records were not retained as sealed records in this rebuild; counts here are documented legacy results.

No cross-skill or cross-model aggregate is computed. The attribution report is the only page in this site backed by the current sealed evidence set.