ba-kg

Builds a traceability knowledge graph of BA artifact IDs with Mermaid diagrams and edge tables.

Updated Jul 28, 2026
One-click install
npx skills add https://github.com/truongnat/Restly --skill ba-kg-truongnat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ba-kg
Source: https://github.com/truongnat/Restly/tree/main/.agents/skills/ba-kg
Command: npx skills add https://github.com/truongnat/Restly --skill ba-kg-truongnat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Business analysis sessions produce many artifacts (Epics, User Stories, Acceptance Criteria, APIs, Tests) whose relationships become hard to track. This Skill links those IDs into a searchable knowledge graph so traceability and gap detection stop being manual guesswork. ## Core Features & Use Cases - Trace Graph Construction: Scans session artifacts for IDs (Epic/US/AC/FR/BR/API/Screen/Test) and builds node and edge tables with cited sources. - Mermaid Visualization: Renders the graph as a Mermaid flowchart inside KG.md for quick visual inspection. - Orphan Detection: Lists IDs with no edges so unlinked requirements stay visible instead of being silently dropped. - Use Case: After a requirements workshop, run the skill over the session artifacts to produce KG.md showing which user stories trace to which acceptance criteria, and which FRs have no test coverage. ## Quick Start Use the ba-kg skill to scan the current session artifacts and write KG.md with nodes, edges, a Mermaid graph, and orphans.

Frequently Asked Questions about ba-kg

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a requirements traceability graph from BA artifacts?▼

Run the skill over session artifacts containing IDs like US-001 or AC-001. It scans for explicit mappings, builds node and edge tables, renders a Mermaid flowchart, and writes everything to KG.md from its template.

What artifact types does the knowledge graph support?▼

The graph tracks Epic, User Story, Acceptance Criteria, Functional Requirement, Business Rule, API, Screen, and Test entities. Edges use relations such as implements, traces, tests, and maps, each citing its source artifact.

Can the skill answer questions about requirement coverage?▼

Yes, you can pass an optional focus question. The skill answers it in the query_answers section of KG.md, referencing the relevant node IDs so the reasoning stays traceable.

What happens to IDs that have no relationships?▼

Unlinked IDs are listed in the orphans table with a suggested link rather than being dropped. The skill never invents edges without citing both ends, so the graph only reflects documented relationships.

What are the limitations of a table-based knowledge graph?▼

It is a lookup-oriented trace graph, not a vector database or semantic search engine. It only captures relationships explicitly stated in session artifacts, so implicit or undocumented dependencies will not appear.