# Monthly KPI — May 2026

_Generated 2026-06-01 by automotive-skills-monthly-kpi._

## Velocity
- Commits: 23
- Distinct skills touched (skill files, polish-log, examples): 24
- Releases: v2026.05.W20 (2026-05-16), v2026.05.W21 (2026-05-23), v2026.05.W22 (2026-05-30)

## Quality
- Open issues at month start: unknown (no prior snapshot — first monthly run)
- Closed this month: 0
- Currently open: 12 (mean age: 12.1 days)

## Coverage
- Builders with paired reviewer: 76 / 76 (100.0%) — counts alias-pairs `item-definition ↔ item-def` and `ppap-package ↔ ppap` per STATUS classifier
- Builders with examples/: 6 / 76 (7.9%) — `8d-problem-solving`, `autosar-swc`, `dbc`, `dfmea`, `hara`, `uds-services`

## Domain mix (commits this month)

```
quality        ████ 4
diagnostics    ███ 3
safety         ███ 3
autosar        ███ 3
comms          ███ 3
aspice         █ 1
cyber          █ 1
calibration    █ 1
mbse           █ 1
program-mgmt   █ 1
v&v            █ 1
sysml          █ 1
sotif          · 0
```

`sotif` received zero commits in May 2026. No prior month report exists, so the two-month-running flag cannot yet trigger — watch in June.

## Top 5 most-changed skills
1. `hara-builder` — 3 commits (W20 polish, W22 polish, examples stub)
2. `uds-services-builder` — 3 commits (W21 polish, examples stub, W23 carryover)
3. `dbc-builder` — 3 commits (W21 polish, examples stub, classifier pairing)
4. `autosar-swc-builder` — 3 commits (W21 polish + description fix, examples stub)
5. `dfmea-builder` — 2 commits (W22 polish, examples stub)

## Stale watchlist (not touched 60+ days)
None. Oldest commit in the repository is 2026-05-01, so no skill is yet 60+ days stale. Re-check in July 2026 once the bulk-add bootstrap (2026-05-02) crosses the threshold.

## Recommendations for next month
- Drive `sotif` domain off zero — schedule `sotif-analysis-builder` or `triggering-conditions-builder` into the W24/W25 polish queue to avoid a two-month-streak flag.
- Close the examples coverage gap (currently 7.9%). At ~1 stub per week, full coverage takes >1 year; consider a batched examples sprint or relaxing the per-skill bar to a single representative example per cluster.
- Sustain the zero-orphan paired-reviewer rate as new skills enter the suite — fold the alias-aware pairing check into the W23 classifier-freeze ticket so the 100% number cannot regress silently.