#sdlc

Skill repository to enforce Engineering disclipline in coding assistants

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Spec-first, cross-harness SDLC skills framework — one director, AI agents, a living spec spine

Brain-grounded SDLC pipeline for Claude Code — story → arch → slice → fleet → PR, with gates held in code

Eleven free, vendor-neutral AI engineering skills for common SDLC workflows.

Engineering craft for Claude Code — TDD, verification, code quality, and SDLC discipline.

Battle-tested multi-agent dev team for Claude Code — 9 specialized sub-agent templates + a 6-stage pipeline with agent memory, verdict protocols, commit checkpoints & standing review prompts. CLAUDE.md constitution, bug-pattern library, full Laravel + React example. Bilingual EN/AR. Extracted from a production app with 200+ releases.

AISEF — AI Software Engineering Framework: one requirements file in, a gated and evidence-backed application out. Agents do the judgement; code enforces the guarantees.

Universal security audit skill for Claude Code — OWASP Top 10 (2021) + Russian security standards (ГОСТ Р 56939, ФСТЭК, ФЗ-152) + STRIDE threat modeling. Multi-stack: Node/Python/Go/Rust.

🚀 MergeCrew 2026: Autonomous AI Dev Team - Daily PRs with Human Approval Gate

CLI for Skaftor — drive AI-native software delivery work orders from your terminal over MCP.

Claude Code plugin: one engineering process, skills that take turns, and agents that keep discovery off the main context.

研发全生命周期技能库：23 个技能 / 4 个 plugin / 单一编排器 dev-master 管 13 阶段流程（SRS 真源 → 设计 → 实现 → 测试 → 上线审计 → 发版）。Claude Code / Codex / Cursor 三端可装。

Agent-agnostic merge bar and spec-driven Claude Code plugins for governed software delivery.

Agents write code. aisdlc runs the process. Harness-agnostic Agent Skills + a zero-dependency CLI for EARS specs, evidence gates G1-G6 and hash-bound approvals.

Claude Code plugin for vibe coding on the AI-native SDLC playbook: intent → design → spec → plan → verify → review → ship. Runs on a Claude subscription, with opinionated stacks (Nuxt/Next + Cloudflare, Go + Postgres, Flutter, Tauri) and deterministic guardrails.

Small set of Claude Code agent roles (orchestrator, engineering manager, .NET/frontend engineers, QA, security, architect) with hard release gates. MIT.

HashForge — AI-native software engineering platform: multi-agent SDLC pipeline for Claude Code (idea → verified, release-ready software)

Fail-closed control plane for agentic SDLC. Portable skills, evidence ladder, SPIFFE/WIMSE identity. Intent is not a grant.

Agent skills and a Rust CLI that take an issue to a reviewed, verified PR overnight. Works with any harness (Claude Code, Codex, Cursor) and any stack.

Copyable Claude Code + GitHub Copilot configuration: AGENTS.md operating manual, CLAUDE.md, copilot-instructions, rules, skills, subagents, hooks, and a gated 7-stage SDLC (spec review, self code review, PR-bot triage). Token-efficient agentic coding you vendor into your repo and adapt with /adopt.