Agent skill · vasilyu1983
dev-contribution-quality-analysis
Analyzes commit and PR history to score contribution quality objectively. Use when building engineering scorecards, calibrating promotions, or measuring AI-assist impact.
What it needs
About 8k tokens when loaded.
What this skill does
Developer Contribution Quality Analysis Objective, multi-dimensional analysis of code contribution quality from git data. Produces individual deep-dive reports and team calibration comparisons. Modern Best Practices Measure contribution quality through outcomes (churn, duplication, test coverage), not presence metrics AI-assisted code is normal; score the output, not the authorship GitClear Diff Delta and CodeScene Code Health are the established commit-level quality benchmarks Stanford ghost engineering research claims commit content analysis predicts expert quality judgments (r=0.82); study is not peer-reviewed — apply with caution Agent Trace (Cursor RFC) is an emerging vendor-neutral standard for AI attribution DX Core 4 framework consolidates DORA/SPACE into a unified set of four oppositional dimensions DORA 2025 itself reports AI adoption now correlates with higher throughput and a "mirror and multiplier" pattern (seven team archetypes replace prior elite/high/medium/low clusters); do not confuse it with vendor telemetry reports Faros AI's 2026 "Acceleration Whiplash" telemetry report (4,000+ teams, distinct from DORA) found bugs per developer up 54% and incidents per PR up 242.7% where AI adoption outran test/review discipline — cite it as Faros, not DORA GitClear Jan 2026 (2,172 developer-weeks): power AI users produced 4.2x more durable code than non-users but also showed 9x more churn — AI widened an existing performance gap and its downside, not evidence of uniform uplift GitClear "The Maintainability Gap" 2026 (623M code changes) extends this: refactor/moved-code share collapsed to 3.8% YTD 2026 (13% in 2023), copy/paste 15.7% in H1 2026, error-masking constructs +47%, cross-file reuse -35% — use these as the current structural-quality benchmarks Treat commits and PRs authored end-to-end by an autonomous coding agent (not just AI-assisted) as a distinct evidence class — see Known Traps Quick Reference Task Tool / Reference Command / Path When ------ ---- …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills vasilyu1983/dev-contribution-quality-analysis