Human-centered frontend quality gate and theory-based UX audit skill with measurable fast-gate checks, weighted scoring, and CI strict mode.
-
Updated
May 12, 2026 - Python
Human-centered frontend quality gate and theory-based UX audit skill with measurable fast-gate checks, weighted scoring, and CI strict mode.
A model-agnostic record/replay reliability gate for tool-using agents — scores Determinism and Faithfulness as two independent, CI-gateable axes.
Merge-blocking evaluation gates for generative AI features: YAML suites run against any HTTP endpoint or Python callable, fail the build on a miss, and emit both a diffable JSON pack and a reviewer document cross-referenced to California's published GenAI risk framework. Aligned to, never approved by.
Fail-closed evaluation harness for government-facing chat systems: reproducible, provenance-stamped audit verdicts, byte-identical across Python 3.11 to 3.14, with no third-party dependencies. A silent or unreadable target scores zero rather than passing by absence. Two public projects pin it by exact commit.
Complete security framework for AI Agents, MCP Servers, and RAG pipelines. Features automated MCP fuzzing, cross-agent poisoning detection, persistent memory audits, unified risk scoring, and CI/CD security gates.
Self-hosted accuracy evals + correction loop for document extraction. Bring your own model.
SiteOne Crawler: Crawler/analyzer для SEO, OpenGraph, headings, redirects, 404, performance, accessibility, security.
GitHub Action that gates a workflow on Slack approval - threaded or standalone, with multi-approver, self-approval guard, and timeout.
Field-level evaluation and release gate for LLM document extraction: exact golden set, per-field precision/recall, CI gate that blocks regressions
LLM evaluation harness that gates quality in CI: golden datasets, regression detection, grounding and faithfulness checks.
強型別 AI 多代理人 SOP 治理 CLI — 將 Markdown 交接編譯為機器可校驗的契約,內建確定性語意防偽 Oracle,在 CI 閘口硬性阻斷偽造的 Vitest 測試 log(exit 1,不寫合規戳記)。終結 AI 代理人偷懶合謀。
Agent and LLM evaluation harness: golden datasets, multi-scorer execution, regression detection across model versions, cost-quality leaderboards, and CI gates for model promotion.
Bootstrap and enforce enterprise repo hygiene in any codebase, from one command.
A FORCE row-level-security coverage gate for multitenant Postgres: surface tenant-scoped tables that lack FORCE RLS, minus a documented allow-list.
Add a description, image, and links to the ci-gate topic page so that developers can more easily learn about it.
To associate your repository with the ci-gate topic, visit your repo's landing page and select "manage topics."