  
|
92299e1238
|
feat(skill): beef up ml-engineering with scripts/templates/evals (#257)
Add a schema-valid eval manifest (6 cases: fine-tuning plan review, eval-set
design, quantization decision, deployment plan, regression triage, training-run
reproducibility), three fillable templates (training-run record, eval regression
table, quantization decision record), a stdlib eval-set overlap/leakage checker
with a unittest suite, routing to the llama-cpp tool skill, and a README Quick
Start documenting the script. Closes #240.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
|
2026-08-03 15:25:06 -04:00 |
|
|
Magnus HedemarkandGitHub
|
c7c4d3b74f
|
Port 11 methodology skills from hermes-profiles (#69)
Engineering: backend-engineering, frontend-engineering, data-engineering,
ml-engineering, platform-engineering, qa-methodology
Executive: go-to-market, legal-strategy, operational-design, org-design,
product-strategy
ml-engineering: added missing training-infrastructure.md reference
qa-methodology: added test-data-management, performance-testing,
security-testing references
All frontmatter converted to agent-skills convention.
Source: https://github.com/magnus919/hermes-profiles
|
2026-07-21 00:58:26 -04:00 |
|