By abimedapp
Git/PR workflow plugin. Orchestrator coordinates diff analysis and commit writing.
Draft a Conventional Commits message OR a PR description from analyzed diff context. Loads the conventional-commits and pr-description skills. Returns text only.
Read-only analysis of a Git diff against a base branch. Returns scope, file groups, and risk flags. Use when another agent needs structured diff understanding.
Use when preparing a PR end-to-end. Coordinates diff analysis and commit/PR description writing. Does NOT read files or write text itself — delegates to subagents.
Trigger when drafting a pull request body. Provides the Summary / Changes / Test plan / Risks structure used by /pr-prepare.
Trigger when writing a Git commit message. Enforces Conventional Commits 1.0 format. Apply when drafting commits via /commit-smart or any agent that produces commit text.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Example Claude Code marketplace with two plugins demonstrating commands, orchestrator agents, and skills.
ai-plugins-test-2/
├── .claude-plugin/
│ └── marketplace.json # Marketplace manifest (lists plugins)
├── dev-workflow/ # Plugin A
│ ├── .claude-plugin/plugin.json
│ ├── commands/ # /branch-create, /commit-smart, /pr-prepare
│ ├── agents/ # workflow-orchestrator + 2 subagents
│ └── skills/ # conventional-commits, pr-description
└── code-quality/ # Plugin B
├── .claude-plugin/plugin.json
├── commands/ # /review-diff, /refactor-suggest, /test-gaps
├── agents/ # quality-orchestrator + 2 subagents
└── skills/ # code-review-checklist, test-design
Each plugin follows a coordinator/executor pattern:
slash command → orchestrator agent → delegates to specialized subagents
↓
loads skills for domain knowledge
The orchestrator coordinates and synthesizes — it does not perform the work itself. Specialized subagents read files, run analysis, and return findings. Skills hold the durable conventions (commit format, review checklist, etc.) so the agents stay focused on coordination logic.
# From this repo
claude plugin marketplace add ./
claude plugin install dev-workflow@ai-plugins-test-2
claude plugin install code-quality@ai-plugins-test-2
Or from a Git remote:
claude plugin marketplace add <git-url>
dev-workflow| Command | What it does |
|---|---|
/branch-create | Create a branch from an issue or feature description |
/commit-smart | Analyze staged diff and produce a conventional commit msg |
/pr-prepare | Orchestrate diff analysis + PR description |
code-quality| Command | What it does |
|---|---|
/review-diff | Review the current diff via reviewer + test auditor |
/refactor-suggest | Suggest refactorings with tradeoffs |
/test-gaps | Find uncovered branches and weak assertions |
MIT
npx claudepluginhub abimedapp/ai-plugins-2 --plugin dev-workflowCode review and test quality plugin. Orchestrator coordinates review and test auditing.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.