Carlo1911
18df2fe7b4
Standalone Python stdlib pipeline that reads an agent's past sessions, compares them against installed skills, and generates structured improvement proposals gated by an evaluation framework before anything mutates. Host-agnostic via HostAdapter (Hermes, Claude Code). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
20 lines
821 B
Bash
Executable File
20 lines
821 B
Bash
Executable File
#!/bin/bash
|
|
# Cron wrapper for skill quality tracking
|
|
# Resolves skill_quality.py relative to this script's location, following symlinks
|
|
|
|
# Resolve the directory this script is in, following symlinks
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
|
|
# Report output directory. Default is `<repo>/reports/`; deployments can override
|
|
# via SKILL_EVOLUTION_QUALITY_REPORT_DIR when they want reports stored elsewhere
|
|
# (e.g. inside a user-owned data dir that the host agent also reads).
|
|
OUTPUT_DIR="${SKILL_EVOLUTION_QUALITY_REPORT_DIR:-$SCRIPT_DIR/../reports}"
|
|
mkdir -p "$OUTPUT_DIR"
|
|
OUTPUT_FILE="${OUTPUT_DIR}/skill-quality-$(date +%Y-%m-%d).md"
|
|
|
|
# Run the quality tracker
|
|
python3 "$SCRIPT_DIR/skill_quality.py" --output "$OUTPUT_FILE"
|
|
|
|
# Report completion
|
|
echo "Skill quality report generated: $OUTPUT_FILE" >&2
|