An AI-driven normalization engine that transforms messy, manual engineering failure logs into standardized, codebook-compliant data for manufacturing quality control.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install manufacturing-codebook-normalization-manufacturing-failure-reason-codebook-normalization
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install manufacturing-codebook-normalization-manufacturing-failure-reason-codebook-normalization using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Manufacturing Failure Reason Codebook Normalization?
Manufacturing Failure Reason Codebook Normalization is a sophisticated utility designed for the industrial sector to bridge the gap between raw engineering feedback and structured data analysis. In high-pressure testing environments, engineers often record defect reasons using inconsistent abbreviations, mixed languages, or ambiguous descriptions. This skill leverages Openclaw Skills to parse these logs, correct linguistic errors, and map them to official product codebooks with high precision.
The system goes beyond simple text matching by implementing station validation and semantic calibration. It ensures that the assigned codes are physically possible at the specific testing station where the defect was recorded, significantly reducing false positives in manufacturing analytics and improving the reliability of root cause investigations.
Manufacturing Failure Reason Codebook Normalization Use Cases
Primary Applications
- Automated Defect Logging: Converting handwritten or shorthand engineering notes into standardized database entries.
- Quality Assurance Auditing: Validating that recorded failure codes align with the specific constraints of the testing station.
- Multilingual Log Processing: Cleaning up mixed Chinese-English text and resolving misused technical abbreviations.
- Confidence-Based Data Filtering: Flagging weak matches as UNKNOWN to prompt manual engineering review for ambiguous defects.
How Manufacturing Failure Reason Codebook Normalization Works
- Data Ingestion: The skill loads test center logs and corresponding product codebooks to establish a ground truth for valid codes and station scopes.
- Text Segmentation: The raw reason text is split into distinct segments, ensuring each span of text is analyzed for individual defect components.
- Candidate Filtering: Potential codes are filtered based on station compatibility to ensure physical and logical alignment.
- Semantic Scoring: A match score (0.0 to 1.0) is calculated using fuzzy similarity, keyword examples, and context alignment (test items and fail codes).
- Tie-Breaking & Selection: The engine ranks candidates and uses a deterministic tie-break for near-matches to ensure reproducible results.
- Confidence Calibration: The final output includes a calibrated confidence score and a rationale cue to provide engineering teams with transparent evidence.
Manufacturing Failure Reason Codebook Normalization Setup
Installation and Integration
To integrate this normalization engine within your Openclaw Skills workflow, follow these steps:
# Initialize the manufacturing skill environment
openclaw install manufacturing-normalization
# Configure your product codebook paths
openclaw config set codebook_path "./data/codebooks/"
# Run the normalization pipeline on your test logs
openclaw run manufacturing-normalization --input test_center_logs.csv
Manufacturing Failure Reason Codebook Normalization Data Schema & Taxonomy
Normalization Data Model
The skill structures output based on the following taxonomy:
| Field | Description | Format |
|---|---|---|
segment_id |
Unique identifier linking the segment to the record | <record_id>-S<i> |
span_text |
The exact substring from the raw log being analyzed | String |
pred_code |
The mapped code from the product codebook | String / UNKNOWN |
confidence |
Calibrated engineering confidence level | Float (4 decimals) |
rationale |
Evidence cue (station, test_item, or token overlap) | String |
Metadata Objects
- CodebookEntry: Contains valid_code_set and station_scope_map.
- RecordContext: Includes record_id, station, fail_code, and test_item for deterministic processing.
Manufacturing Failure Reason Codebook Normalization Advanced Features
- Context-Dependent Tie-Breaking: Prevents stochastic errors in near-tie scenarios by using record metadata for reproducible selection.
- Station Validation Hooks: Automatically rejects codes that are incompatible with the physical limitations of the reported testing station.
- UNKNOWN Handling Protocol: Intelligent alerting system that triggers when evidence strength falls below calibrated thresholds.
- Cross-Project Normalization: Handles nuances in codebooks across different product lines and manufacturing projects.
SKILL.md
Loading
Related Openclaw Skills
Book Author Skill
A comprehensive end-to-end publishing engine for creating, humanizing, and launching professional-grade books on Amazon KDP and IngramSpark.
Einstein Perspective
A sophisticated cognitive framework based on Albert Einstein's mental models for scientific research, theoretical construction, and creative problem-solving.
LeBron James & Lionel Messi Career Analytics
A comprehensive data module for comparing the legendary careers, stats, and achievements of LeBron James and Lionel Messi.
Gemini TTS
A powerful text-to-speech skill leveraging Google Gemini models to generate expressive, multi-speaker audio with natural language style control.
deaiify
A powerful plugin that intercepts AI responses to replace em-dashes and en-dashes with natural, dash-free language through embedded LLM rewrites.
Acca Tracker
A sophisticated sports monitoring skill that parses betting slips and provides automated 15-minute live score updates for multi-sport accumulators.
Featured*
