Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By zzaia
Multi-agent orchestration system for software engineering workflows across analytics, development, management, and workspace operations
npx claudepluginhub zzaia/zzaia-agentic-workspace --plugin zzaia-workspaceIntelligent answering, query and clarification system with read-only access
Multi-framework build with error reporting across repositories
Full task development workflow with multi-agent orchestration
Execute comprehensive Git version control operations with standardized branch management
Entity Framework Core migrations management across repositories
Transform basic problem statements into comprehensive technical research reports with multiple analytical approaches
Delegate web search tasks here. Use for keyword queries, deep research, URL extraction, site crawling, and site mapping via Tavily MCP tools.
Comprehensive code quality review and static analysis
Multi-language development specialist with mandatory language rule compliance.
DevOps platform specialist handling all operations across Azure DevOps and GitHub — work items, pipelines, repositories, builds, pull requests, wikis, and test plans.
External network access
Connects to servers outside your machine
Requires secrets
Needs API keys or credentials to function
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
agent-flow — Claude Code plugin for automated bug-fix, feature, and scaffold workflows. Issue tracker to merged PR via a pipeline of specialized AI agents.
Long-running agent harness with 5-layer memory architecture, GitHub integration, autonomous batch processing, Agent Teams with ATDD, 9 hooks (safety, quality gates, team coordination), and 6 Agent Skills
Unified spec-to-execution workflow system. Combines spec rigor, autonomous execution, and native task orchestration with parallel agent dispatch. Swarms-ready architecture.
Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 13 skills, 15 commands, quality gates, TDD enforcement
HarnessFlow — From idea to shipped product: high-quality engineering workflows for AI agents. Spec-anchored SDD, gated TDD, evidence-based routing, independent reviews, and formal closeout.
Self-orchestrating multi-agent development system powered by Claude Fable 5 — 15 agents (8 core + 1 security gate + 6 department), Smart Routing default, token-efficient subagents, risk-based quality gates. You say WHAT, the AI decides HOW.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Has parse errors
Some configuration could not be fully parsed
Share bugs, ideas, or general feedback.
Multi-agent orchestration system for software engineering workflows across analytics, development, documentation, and management.
For full onboarding instructions see QUICKSTART.md.
/plugin marketplace add zzaia/zzaia-agentic-workspace
/plugin install zzaia-workspace@zzaia
Commands are organized in a five-layer hierarchy. Each layer calls into the next, enabling complex automation through composition:
sequenceDiagram
participant O as /orchestrator:*
participant W as /workflow:*
participant B as /behavior:*
participant S as /capability:*
participant T as templates/
O->>W: dispatch workflows (parallel or sequential)
W->>B: sequence domain operations
B->>S: invoke reusable capabilities
S->>T: populate markdown blueprints
T-->>S: structured content
S-->>B: capability result
B-->>W: operation complete
W-->>O: workflow result
| Layer | Prefix | Responsibility |
|---|---|---|
| Orchestrator | /orchestrator:* | Multi-item coordination — dispatches workflows in parallel or sequentially based on dependency analysis |
| Workflow | /workflow:* | Sequence of behaviors for a complete task (e.g. implement a work item end-to-end) |
| Behavior | /behavior:* | Single domain operation with agent delegation (e.g. run a pipeline, create a PR) |
| Capability | /capability:* | Self-contained capability with SKILL.md, template.md, examples/, scripts/ |
| Template | templates/ | Markdown blueprints filled in by capabilities with real conversation context |
From a product specification document to production-ready - human super-visioned automated flow.
sequenceDiagram
actor U as Product Spec
participant A as workflow:remote:architect
actor T as Tech Team
participant I as orchestrator:implement
participant D as dev/stg
participant H as workflow:remote:homologate
U->>A: PDF / Word / MD / POC
A-->>T: BDD + Epic + Work Items + SDDs
T-->>A: Review and update SDDs
A->>I: Approved work items
I-->>T: All PRs created
T-->>I: Review and complete PRs
I->>D: Deploy
loop Until no bugs
D->>H: E2E BDD
H-->>I: Bug work items
I-->>T: Bug fix PRs
T-->>I: Review and complete PRs
I->>D: Deploy fix
end
D-->>U: Ready for Production
# 1. Generate BDD, Epic, Work Items and SDDs from a product spec document
/workflow:remote:architect --selected-work-item 2001 --project MyProject --description "Feature description" --doc ./spec.pdf
# 2. Implement all approved work items in parallel — all PRs created via agent teams
/orchestrator:implement --work-items 2002,2003,2004 --portal azure --project MyProject --target-branch develop --description "Feature description"
# 3. Run E2E BDD against staging — creates test case, runs scenarios, files bugs
/workflow:remote:homologate --work-item 2001 --project MyProject --url https://staging.myapp.com --application MyApp --type e2e
# 4. If bugs found — implement all bug fix work items and create PRs
/orchestrator:implement --work-items 2010,2011 --portal azure --project MyProject --target-branch develop --description "Bug fixes"
# 5. Re-run until no bugs found
/workflow:remote:homologate --work-item 2001 --project MyProject --url https://staging.myapp.com --application MyApp --type e2e
This layering keeps each command focused on one responsibility and makes the system extensible without coupling between layers.
All individual commands can be called by users for standalone operations; workflows combine multiple commands.
Machine learning dataset discovery and analysis workflows.
/workflow:analytics:explorate - Domain and dataset exploration/workflow:analytics:analyze - Dataset analysis and visualizationSoftware development lifecycle operations.