$ show jherrodthomas/automotive-skills-suite
This repository is a curated suite of 152 Claude AI skills (76 builder + 76 paired checklist reviewer archives) for generating structured Excel workbooks across the automotive engineering lifecycle. Domains include ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, ASPICE, AUTOSAR, SysML/MBSE, diagnostics (UDS, DBC, ODX), calibration (A2L), quality tools (APQP, PPAP, FMEA), and program management. Each `.skill` file is a ZIP archive containing SKILL.md, Python generators/reviewers, references, and shared utilities. Builders produce multi-tab xlsx workbooks from JSON input; reviewers validate existing workbooks and emit compliance checklists with dashboards. The suite is maintained via an autonomous weekly cycle (plan, polish, docs, release), with status tracking, chain-contract audits, and known issue catalogs. While the concept is robust, many shipped skills suffer from documentation/code drift (advertised check counts mismatch actuals), silent failures (empty workbooks certified as compliant), and duplicated shared scripts across 152 archives.
The LLM identified 4 files worth highlighting for reuse:
Provides a LD_PRELOAD shim for LibreOffice socket communication in sandboxed environments. Compiles a C shim at runtime to fake AF_UNIX sockets. Self-contained and reusable for any project requiring headless LibreOffice in restricted deployments.
A utility to recalculate all formulas in an Excel workbook via a LibreOffice Basic macro, then scan for `#VALUE!` errors. Kept byte-identical across all 152 skills as a canonical hash. Portable and extractable.
A reusable dashboard builder for any checklist reviewer skill. Consumes a standard data structure of `{tab_code: [(check_def, check_result)]}` with FC/LC/PC/NO/NA/PENDING ratings and generates KPI tiles, pie/bar/stacked charts, findings table, and an overall status verdict. Designed to be shared across all 76 reviewer skills.
A static analysis script that audits builder-to-builder sheet name expectations across skill chains. Uses alias resolution from `docs/PAIRING_ALIASES.md` rather than hard-coded names, preventing pairing regressions. Demonstrates cross-artifact consistency enforcement.