Development-Workflows plugins

Autonomous development methodology for Claude Code

11 commands · 22 agents

Disciplined Agentic Engineering (DAE) — methodology kit for Claude Code. Skills that implement the DAE pipeline: feature intake, AC discovery, spec writing, planning, implementation, verification, hardening.

25 skills · 6 agents

Acceptance Test Driven Development for Claude Code. Enforces the ATDD methodology: write Given/When/Then specs first, generate a project-specific test pipeline, maintain two test streams (acceptance + unit). Inspired by Robert C. Martin's acceptance test approach from empire-2025.

3 skills · 4 commands · 2 agents · hooks

The most comprehensive Claude Code extension for PHP developers. 26 commands, 68 agents, 283 skills.

200 skills · 26 commands · 68 agents · hooks

Native Meta-Harness — run a harness-optimization loop natively: propose scaffolding variants around a fixed model, score each with a $0 deterministic test, keep the Pareto-best, loop.

1 skill

pair-review app integration — Open PRs and local changes in the pair-review web UI, run server-side AI analysis, and address review feedback. Includes MCP server.

6 skills · 1 MCP server

Agent-orchestrated review loop — implement, review with pair-review multi-model councils via the headless CLI, triage, fix, and repeat until a final review returns no blockers. Writes triage back to a running pair-review server so the web UI stays current. No MCP required.

1 skill

AI-powered code review analysis — Run three-level AI analysis directly in your coding agent. Works standalone, no server required.

1 skill

Skills and agents to automate repository maintenance, releases, and CI/CD workflows

18 skills · 3 agents

Spec-driven development workflow with /specops command (includes init, view, list, interview, update subcommands).

3 skills

AI team orchestration. CTO, Engineer, QA, Designer work together while you watch in real-time.

1 skill · 13 commands · hooks

Generate structured Markdown reports with YAML frontmatter for repository health monitoring. Includes metrics, tables, and status tracking.

1 skill

Full SDLC developer profile — 36 skills for Go API services: onboarding, task solving, code review, monitoring, incident investigation

36 skills

An opinionated governance layer for Claude Code, built for solo developers. Autonomous sprint execution, worktree-isolated items, quality gates, TDD workflow, scope control, architecture fitness, and pre-PR code review — workflow enforced by hooks, not just rules. Installs via /plugin marketplace add lwalden/AIAgentMinder.

15 skills · 16 agents · hooks

AI orchestration tool — GSD management shell + Superpowers quality core. 6 commands, 4 agents, 6 workflows, MCP server, context monitoring.

6 commands · 4 agents · 1 MCP server · hooks

Scan a project and create a Stitch-style design.md file.

1 skill

MCP server for querying a local library of versioned Markdown documents. Point to a folder of Markdown files and give AI agents read-only access to versioned documents, metadata, and diffs.

1 MCP server

Metodologia de desenvolvimento agnóstica de projeto: brainstorm→spec, casos de teste derivados da spec e executados no fim, TDD forçado (RED-GREEN-REFACTOR), code review com gate de severidade, execução paralela de tarefas independentes, commits em Conventional Commits, scaffolding de Clean Architecture/DDD e documentação final da implementação.

12 skills · 9 agents · hooks

A multi-agent team for writing and reviewing federal government procurement proposals. Includes specialized agents for compliance review, solution architecture, past performance, growth strategy, and subject matter expertise.

6 skills · 5 agents

Teaches Claude Code how to install and manage skills from plugin marketplaces using the local-skills CLI

1 skill

Walk through shipping your code to production with simple yes/no questions. Handles intent classification, blocker detection, PR creation, pipeline setup, and deployment — no DevOps knowledge required.

1 skill

developer, debugger, tracker, auditor personas for Clean Architecture projects

48 skills · 38 agents

Engineering Delivery Framework — structured software delivery harness with skills, agents, and hooks for TDD, design, and process automation

24 skills · 14 agents · hooks

Base commands and skills for development workflows (commit, plan, review, init, etc.)

24 skills · 11 agents · hooks

Specialized research + execute agent team. /kirei auto-detects task type (security, UI, refactor, performance, architecture, test, migrate, review, debug, data, deps, observability, bundle, license, resilience, eval, or general via kirei-research) and complexity, spawns the right specialist to investigate, then an execute agent — kirei-stitch (focused) or kirei-loom (multi-file) — to implement. Also: /kirei-prism (parallel multi-lens research), /kirei-audit (depth-tunable code-quality audits with ordered fixes), /kirei-deps (Dependabot-aware dependency-safety audits), /kirei-sentry (production Sentry setup), /kirei-showcase (a showcase README with reproducible screenshots via @noctcore/showcase-kit), /kirei-templatize (repo to starter template), /kirei-discuss (pre-code idea audit), and /kirei-wave (worktree-parallel multi-slice execute: fan-out builders, run the gate battery, open PRs, gate each with the read-only adversarial kirei-gate reviewer, then merge in dependency order). kirei-resilience audits error handling.

9 skills · 22 agents

Jeeves, by Draft0 — session memory and living docs for brainstorming, code documentation, quality hardening, and drift detection. Your AI doesn't remember. Jeeves does.

13 skills · 1 MCP server · hooks

Auto-activates REVIEWER (Senior Engineer) and DEVELOPER (Mid-level Engineer) agents on every Claude Code session. Runs an automated review loop with configurable max iterations. Includes security, architectural, system-design, clean-code, and senior-architect skills.

7 skills · 2 agents · hooks

Procedural engineering knowledge (deep-research, draw-diagrams, write-prd, etc.)

7 skills · 1 agent

Claude Code plugin that gates ambiguous coding tasks with lateral hypotheses, probes, and validation.

3 skills · 2 agents · hooks

千岛小程序开发助手，支持前后端开发、调试、部署、运维，并内置产品底线与 Taro 设计规范。

4 skills