Lift drill into evals/ at 013fcb8b7dbefd6d3fa4653493e5d2ec8e7f985b

rsync of obra/drill@013fcb8b7d into superpowers/evals/, excluding
.git/, .venv/, results/, .env/, __pycache__/, *.egg-info/,
.private-journal/.

The drill repo is unaffected by this commit; archival is a separate
manual step after this PR merges.

Source SHA recorded at evals/.drill-source-sha for divergence
detection.
This commit is contained in:
Jesse Vincent
2026-05-06 12:15:46 -07:00
parent 895bb732d5
commit 3c046f579e
124 changed files with 13806 additions and 0 deletions

32
evals/bin/skill-called Executable file
View File

@@ -0,0 +1,32 @@
#!/usr/bin/env bash
# Verify a specific superpowers Skill was invoked at least once.
#
# Usage: skill-called <skill-name>
# Example: skill-called superpowers:systematic-debugging
#
# Wraps the common case of `tool-arg-match Skill '.skill == "<name>"'` so
# scenario YAML doesn't have to embed jq quoting.
set -euo pipefail
command -v jq >/dev/null || { echo "jq required"; exit 127; }
SKILL_NAME="$1"
FILE="tool_calls.jsonl"
if [ ! -s "$FILE" ]; then
echo "FAIL: tool_calls.jsonl missing or empty"
exit 1
fi
COUNT=$(
jq -s --arg name "$SKILL_NAME" \
'[.[] | select(.tool == "Skill" and (.args.skill // "") == $name)] | length' \
"$FILE"
)
if [ "$COUNT" -gt 0 ]; then
echo "PASS: Skill($SKILL_NAME) called $COUNT time(s)"
exit 0
else
echo "FAIL: Skill($SKILL_NAME) never called"
exit 1
fi