chore: remove committed test-run artifact (#602)
This commit is contained in:
@@ -25,7 +25,6 @@ assets/ export-ignore
|
||||
# Historical + repo-only manifests
|
||||
SPEC.md export-ignore
|
||||
TASKS.md export-ignore
|
||||
test-run.log export-ignore
|
||||
CONTRIBUTORS.md export-ignore
|
||||
HERMES_SETUP.md export-ignore
|
||||
CHANGELOG.md export-ignore
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
# Private benchmark / evaluation artifacts — never push to upstream
|
||||
docs/comparison-results/
|
||||
test-run.log
|
||||
scripts/evaluate-synthesis.py
|
||||
scripts/generate-synthesis-inputs.py
|
||||
fixtures/polymarket_sample.json
|
||||
|
||||
@@ -1,11 +0,0 @@
|
||||
📁 Output directory: /Users/mvanhorn/last30days-skill-private/docs/test-results/v1-vs-v2-20260206-231338
|
||||
|
||||
📦 Backing up current V2 SKILL.md...
|
||||
📥 Installing V1 SKILL.md from upstream...
|
||||
✅ V1 installed (stripped: context:fork, agent:Explore, disable-model-invocation)
|
||||
|
||||
==========================================
|
||||
Running V1 — 17 queries
|
||||
==========================================
|
||||
|
||||
[V1] (1/17) prompting techniques for chatgpt for legal questions [PROMPTING+TOOL]
|
||||
Reference in New Issue
Block a user