Skip to content

Sync analysis-orchestrator evals with amd/skills#193 #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danielholanda merged 1 commit into from
Aug 29, 2026
Merged

Sync analysis-orchestrator evals with amd/skills#193 #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions TraceLens/Agent/Analysis/skills/analysis-orchestrator/evals/evals.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,17 @@
{
"id": "gemm-01-repeatability",
"skill_should_trigger": true,
"prompt": "Run the full standalone TraceLens analysis workflow locally with analysis mode default.\n- trace_path: {trace_path}\n- platform: {platform}\n- output_dir: {output_dir}\n- venv_path: {venv_path}\n- tracelens_dir: {tracelens_dir}\n",
"prompt": "Run the full standalone TraceLens analysis workflow on locally with the default analysis mode, and write everything to analysis_output/ in the current directory. The trace ships inside https://github.com/AMD-AGI/TraceLens/raw/main/agent_evals/Analysis/analysis_tests/unit_tests_standalone.tar.gz. Unpack that and analyze agent_evals/Analysis/analysis_tests/unit_tests_standalone/gemm/gemm_01_compute_few_tiles_analysis_output/gemm_01_compute_few_tiles.json.",
"files_exist": [
"analysis_output/analysis.md"
"analysis_output/analysis.md",
"analysis_output/perf_report.xlsx",
"analysis_output/category_data/category_manifest.json",
"analysis_output/priority_data.json",
"analysis_output/metadata/model_info.json",
"analysis_output/perf_improvement.png"
],
"expected_behavior": [
"Filled the Executive Summary of analysis.md with measured numbers, leaving no template placeholders such as 'X ms', 'Y%' or '<Brief Title>' behind"
]
},
{
Expand Down
178 changes: 0 additions & 178 deletions TraceLens/Agent/Analysis/skills/analysis-orchestrator/evals/hooks.py
View file
Open in desktop

This file was deleted.

Loading