evo-defect-pipeline
SkillFiles & storageEnd-to-end pipeline that reads test center log CSVs and product codebook files, orchestrates text normalization and fuzzy matching, and produces structured solution.json output.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-defect-pipeline skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-defect-pipeline/SKILL.md and read by ahel’s review.
Orchestration pipeline for defect text normalization.
Key Functions
safe_read_csv(file_path)- Read CSV with encoding fallbacks (utf-8, gbk, replace)discover_codebooks(directory)- Find codebook CSVs, map product_id to filepathbuild_codebook_mapping(codebook_df)- Build preprocessed label -> code dictprocess_record(row, codebook_dict, standard_texts, threshold)- Process single recordexport_results_to_json(records, output_path)- Write JSON with numpy-safe encodingrun_pipeline(data_dir, output_path, threshold)- Full end-to-end pipeline
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-defect-pipeline/scripts')
from utils import run_pipeline
run_pipeline('/app/data', '/app/output/solution.json')
Signals
- GitHub stars
- 91
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-defect-pipeline- Source
- github.com/openlair/openskill