BA-Kit
Health Uyari
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 7 GitHub stars
Code Uyari
- process.env — Environment variable access in .agent/mcp-bridge/index.js
Permissions Gecti
- Permissions — No dangerous permissions requested
This tool is an agent squad designed for requirements engineering. It provides 21 specialized AI agents that use reflective "System 2 Thinking" to assist with business analysis tasks across multiple platforms like Claude Code and Antigravity IDE.
Security Assessment
The overall security risk is Low. The scanner found no hardcoded secrets in the repository, and the tool does not request any dangerous system permissions. There is a warning regarding environment variable access within an internal JavaScript bridge file (`.agent/mcp-bridge/index.js`). While interacting with environment variables is standard practice for configuring MCP servers, developers should still inspect this file to ensure it is only reading necessary configurations rather than exfiltrating sensitive system data. No evidence of malicious shell command execution or suspicious network requests was found.
Quality Assessment
The project is actively maintained, with its most recent code push occurring today. It is fully licensed under the permissive and standard MIT license. However, community trust and visibility are currently very low. The repository has only 7 GitHub stars, indicating that the project has not been widely adopted or heavily vetted by a large open-source audience yet.
Verdict
Use with caution — the code is actively maintained and cleanly licensed, but its low community adoption means you should review the MCP bridge file before deploying it in sensitive environments.
Agent Squad for Requirements Engineering — 21 Specialists with System 2 Reflection. Runs on Antigravity IDE, Claude Code, Claude CoWork.
🏆 BA-Kit (Antigravity Edition)
Agent Squad for Requirements Engineering
21 Agent Specialists for Requirements Engineering
System 2 Reflection • Multi-Platform (Antigravity • Claude Code • Claude CoWork)
🎯 What is BA-Kit?
BA-Kit is not a library of prompts. It is an agent squad for agentic AI platforms.
It replaces the single-chatbot approach with 21 specialists running on:
- Antigravity IDE (Google DeepMind) — Agent Skills, MCP, System 2
- Claude Code (Anthropic) — CLI: project-level reasoning, CI/CD, Git
- Claude CoWork (Anthropic) — Desktop: non-technical BA, document synthesis
Summon specialists: @ba-writing for specs, @ba-strategy for context, @ba-facilitation for workshops.
Each agent uses System 2 Thinking (Reflective Loops) — self-critique before responding to reduce hallucination.
🤖 The Agent Squad (21 Agents)
🔴 The Orchestrator
| Agent | Role | Capability |
|---|---|---|
@ba-master |
Dispatcher | Strategy, Routing, Context Management. |
🔵 Core Agents (The Foundation)
| Agent | Role | Capability |
|---|---|---|
@ba-identity |
Chief of Staff | Stakeholder Mapping, RACI, Competency Grid. |
@ba-elicitation |
Journalist | Funnel Questioning, "Colombo" Method. |
@ba-writing |
Architect | Visual UI Scan, Gherkin Drafting (BDD). |
🟡 Specialized Agents (The Experts)
| Agent | Role | Capability |
|---|---|---|
@ba-validation |
QA Lead | Visual QA, Edge Case Detection. |
@ba-traceability |
CCB Secretary | Grep Verification (No Hallucinations). |
@ba-nfr |
SRE Architect | Web-Validated ISO 25010 Standards. |
@ba-process |
Lean Master | Whiteboard Vision, BPMN Waste Analysis. |
@ba-prioritization |
Product Mgr | MoSCoW, RICE, WSJF Frameworks. |
@ba-solution |
Investor | Python-Verified ROI & NPV Math. |
@ba-conflict |
Mediator | Harvard Negotiation, ADR Drafting. |
@ba-export |
Publisher | Compliance Check, Pandoc Formatting. |
🟣 Advanced Agents
| Agent | Role | Capability |
|---|---|---|
@ba-metrics |
Data Scientist | SPC Charts, Defect Density, Cpk stats. |
@ba-root-cause |
Investigator | 5 Whys, Fishbone, Pareto Analysis. |
@ba-innovation |
R&D Scientist | A/B Testing, Hypothesis Designs. |
🟢 Strategic & eBook-Powered Agents (NEW in v2.7)
| Agent | Role | Capability |
|---|---|---|
@ba-strategy |
Strategist | PESTLE, SWOT, Business Model Canvas, Porter's 5 Forces. |
@ba-facilitation |
Facilitator | Workshop Design, ODEC Framework, Group Dynamics. |
@ba-systems |
Systems Analyst | Stocks & Flows, Leverage Points, System Archetypes. |
@ba-agile |
Agile Analyst | User Story Mapping, MVP Definition, Hypothesis-Driven. |
🔗 Integration Agents (NEW in v2.9)
| Agent | Role | Capability |
|---|---|---|
@ba-jira |
Jira Bridge | Story→Ticket Transport, Sprint Planning, Transport Gate Reflection. |
@ba-confluence |
Confluence Bridge | Markdown→XHTML Publishing, Document Import, Version Tracking. |
🚀 Quick Start (Antigravity Native)
1. Installation
Copy the workflows into your Agent's brain:
cp -r ba-kit/.agent/skills/* ~/.gemini/antigravity/skills/
2. Summoning
In your chat, simply type @ followed by the Agent Name:
User: "@ba-writing I need a login feature."
@ba-writing: "Architect online. I see you want a Login. Shall we use Email/OTP or Social Auth? Let's draft the Happy Path first..."
3. The "Flash Mode"
You can switch agents instantly to handle complex tasks:
User: "This requirement seems risky. @ba-solution check the ROI."
@ba-solution: "Investor here. I'll calculate the NPV using Python..."
🧠 System 2 Intelligence (New in v2.4)
All agents now follow a Reflective Cognitive Loop:
- Analysis (System 1): Fast pattern matching.
- Action (System 1): Draft content.
- Reflection (System 2): STOP & THINK.
- Critic: "Did I hallucinate that dependency?"
- Action: Verify with
greporpython.
- Output: Verified, High-Precision Answer.
📁 Repository Structure
ba-kit/
│
├── .agent/skills/ # 21 Agent Skills (ba-master, ba-writing, ba-jira, ...)
├── .agent/scripts/ # BM25+ Knowledge Search Engine
├── .agent/data/ # 786 Indexed Knowledge Entries (23 domains)
│
├── docs/ # Documentation & Guides
│ ├── README.md # Documentation index
│ ├── agent-cheat-sheet.md # All 21 agents at a glance
│ ├── prompt-library.md # 28 copy-paste prompts by phase
│ ├── ai-foundation-for-ba.md # AI Foundation primer (bilingual)
│ ├── ai-tools-guide.md # Tool selection matrix
│ ├── design-prototype-guide.md # Stitch MCP, Figma, vibe coding
│ ├── antigravity-protocol.md # Runtime specification
│ ├── architecture-decisions.md # Naming, identity, CMMI
│ ├── junior-start.md # 4-week onboarding for new BAs
│ └── knowledge_base/ # Core & specialized BA knowledge
│
├── templates/ # Document Templates
│ ├── prd-template.md # Product Requirements Document
│ ├── brd-template.md # Business Requirements Document
│ ├── srs-template.md # Software Requirements Spec (IEEE 29148)
│ ├── frd-template.md # Functional Requirements Document
│ └── ... # + 6 more templates
│
├── ebooks/ # Synthesized eBook Knowledge (6 files)
│
├── AGENT.MD # Squad configuration (Antigravity runtime)
├── QUICK-START.md # 2-minute setup
├── USAGE-GUIDE.md # How the squad works
├── WORKFLOW-COOKBOOK.md # 23 real-world scenario recipes
└── README.md # This file
🔍 Knowledge Search Engine (New in v2.8)
BA-Kit now includes a BM25+ Knowledge Search Engine with 786 indexed entries across 23 domains.
# Search for any BA concept
python3 .agent/scripts/ba_search.py "acceptance criteria gherkin"
# Search specific domain
python3 .agent/scripts/ba_search.py "GDPR compliance" --domain compliance
# Search across all domains
python3 .agent/scripts/ba_search.py "stakeholder analysis" --multi-domain
# View statistics
python3 .agent/scripts/ba_search.py --stats
23 Domains: writing, elicitation, validation, nfr, process, prioritization, traceability, conflict, solution, systems, agile, identity, workshop, innovation, metrics, modeling, ux-research, business-rules, integration, compliance, communication, testing, data-analytics.
📄 License
MIT License. Free to use for personal and enterprise projects.
Built for the Antigravity Age.
Code Less. Think More.
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi