release-readiness

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.

Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

Evidence-based review skill for diff, project, and artifact review across code, readiness, architecture, requirements, and risk.

Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.

Local-first repository health and OSS readiness reports for open-source maintainers

Human-governed readiness system for UAT evidence, launch readiness, blocker escalation, signoff ownership, and release decision support.

A Codex skill for turning small apps and games into a defensible v1.0.

Honest QA gap analysis for deployed web apps. Auth-aware scanning, real accessibility checks, and an MCP server for AI agents.

Final-gate review skill for AI agents - structured release-readiness reports with PASS / PASS WITH RISKS / FAIL verdicts. Claude Code and Agent Skills compatible.

A local-first React Native & Expo project auditor for release readiness, dependency health, and risk reports.

Release workflow repo for requirements, feature flags, readiness reviews, and risk tracking.

A starter repository for documenting, reviewing, and releasing regulated AI systems.

Browser-based product delivery dashboard for tracking TaskFlow mobile app scope, Agile execution, release readiness, and stakeholder visibility.

Agentic QA quality-intelligence for Qase, as an installable plugin: coverage gaps, failure triage, flakiness, and release readiness — evidence-backed, read-only by default, deletions blocked in code.

Structured QA pipeline for pre-release risk analysis: test coverage, flaky tests, and high-risk components detection

Experimental framework for analyzing AI output behavior, hallucination risk and uncertainty before release

Reusable Factor Skills for Agent-native product optimization

Aptoria is a self-hosted Laravel application for API QA, endpoint visibility, regression monitoring, release evidence and lightweight security review.

LLM eval regression gateway with provenance, independent approvals, deterministic release artifacts, FastAPI, metrics, Kubernetes, and Terraform.

Portable AI agent skills and specialist subagents for prompt enhancement, workspace resume, source-grounded research, and release readiness.