The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

Verification-gated skill routing and self-improvement harness for Hermes-style agent skills

AI-powered release gate for SAP Transport Requests. CLI collects evidence from ADT; SKILL guides LLMs to review code, config, interfaces, and release risk — online or offline.

Black-box-first skill suite for manual test design, risk-based prioritization, minimal test case synthesis, and release gate decisions. / ブラックボックス前提で、手動テストの観点出し・リスク優先度付け・最小ケース化・リリースゲート判定まで行う skills

Risk-based release gate for CRA (Article 14), NIS2 and DORA compliance with SBOM, KEV correlation, and auditable evidence.

QA Architecture Blueprint — Python/Playwright/Pytest, Docker-first CI Gate Chain, Release-Readiness Governance, Agentic QA Workflow Foundation

ML release-gate checks for drift, performance regression, latency, and JSON/Markdown deployment reports.

[DO NOT DELETE] Load-bearing CI fixture for AgentV's release contract eval — gate pins a commit before npm latest publish. Do not delete/archive/make private/rewrite history.

Trace-first release gate for coding-agent skills. Scores baseline vs. candidate traces across a 7-dimension rubric and emits a PASS / HOLD / INVESTIGATE Skill Delta Report.

Paired performance release gate for llama.cpp on Apple Silicon. Runs base/head benchmarks on your Mac, reports PASS/FAIL/INCONCLUSIVE with statistical intervals.

PreFlight — Agent Service Release Gate

ResilOps CICD action for quality gate

Portfolio-grade AI evaluation framework for KYC/AML entity screening — Promptfoo matrix, release gate, red-team, offline CI. Synthetic data only.

Release gate for vertical drama script readability, opening conflict, mobile framing, payoff clarity, and episode handoff.

Release gate for AI short drama character state continuity, scene dependencies, blocker severity, and handoff decisions.

Release gate for AI storyboard continuity QA, approved frames, scene coverage, prompt changes, and production review.

A closed-loop safety harness for agentic LLMs: stress-test → regression → release-gate → incident-replay.

Evidence-based quality gate for LLM deployments: evaluates telemetry against latency, cost, and error policies to produce auditable go/no-go release decisions for CI/CD.

Local-first CLI that turns TODO comments into a ranked maintenance queue.

Evaluation-first CI/CD for RAG, agents, chatbots & search. Significance-aware release gate (bootstrap CI + Mann-Whitney U), 13 evaluators (G-Eval, citation, trajectory, ECE), reproducibility manifest, OpenRouter routing for 10× cheaper OSS judges. FastAPI + Celery + Next.js.