skills.rest
TRRaveendra
TRRaveendraCOMMUNITY
Explore all skills by this author →
GitHub

sdlc-agent-01-jira-requirement

Fetches Jira tickets and produces validated requirement artifacts for a Databricks SDLC pipeline.

1|2|Updated Aug 10, 2026
Search Tags:#automation#requirements#multi-agent#vector search#jira#sdlc#databricks
One-click install
npx skills add https://github.com/TRRaveendra/AI-Agents-Databricks --skill sdlc-agent-01-jira-requirement-trraveendra
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdlc-agent-01-jira-requirement
Source: https://github.com/TRRaveendra/AI-Agents-Databricks/tree/main/ai-agent-skills/databricks-sdlc-agent-skills/01-jira-requirement-agent
Command: npx skills add https://github.com/TRRaveendra/AI-Agents-Databricks --skill sdlc-agent-01-jira-requirement-trraveendra

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires databricks-sdk, and includes references (resource) components.

What problem does it solve? It automates the first stage of a 15-agent Databricks SDLC pipeline by turning a raw Jira ticket (or simulated ticket row) into a structured, contract-validated Requirement Package that downstream agents can consume without manual handoffs. ## Core Features & Use Cases - Jira Ticket Ingestion: Polls the Jira REST API or reads simulated rows from the state.tickets Delta table, extracting descriptions, attachments, comments, and acceptance criteria. - Attachment Parsing & Embedding: OCRs and parses PDF/DOCX/XLSX attachments into text, then chunks and embeds them into the knowledge.requirements_index Vector Search index for downstream retrieval. - Contract-Validated Output: Writes requirement.json and attachments.json to /Volumes/{catalog}/state/artifacts/{ticket}/, validates against a strict JSON output contract, and logs full traces to state.agent_runs. - Use Case: A data platform team receives a new Jira ticket for a pipeline change; this agent fetches it, parses the attached spec documents, and hands a validated Requirement Package to the Requirement Validation Agent automatically. ## Quick Start Ask the agent to process Jira ticket PROJ-123 and write its Requirement Package artifact to the lakehouse for the next pipeline stage.

Frequently Asked Questions about sdlc-agent-01-jira-requirement

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

FAQPage Schema
How do I automate Jira ticket intake in a Databricks pipeline?▼

Poll the Jira REST API with the ticket key, or read a simulated row from the state.tickets Delta table when jira_mode=simulated. Extract the description, attachments, comments, and acceptance criteria, then write a requirement.json artifact to the ticket's Unity Catalog volume path.

What Databricks API should agents use instead of Genie Code?▼

Use the Foundation Model API on Model Serving (e.g., databricks-claude-sonnet-4-5) via the OpenAI-compatible chat completions endpoint, since Genie Code has no public headless API. The Genie Agents Conversation API is only for natural-language data questions, not code generation.

How are Jira ticket attachments processed for downstream agents?▼

Attachments such as PDFs, DOCX, XLSX, and images are OCR-parsed into plain text, then chunked and embedded into the knowledge.requirements_index Vector Search index. Downstream agents retrieve this content semantically instead of re-reading raw files.

What happens when the agent output fails contract validation?▼

The agent gets one repair retry with the validation error appended to its context. If it still fails, the run is routed to state.needs_human so approval-gate agents can review it instead of silently passing bad output downstream.

Can this agent run without a real Jira instance?▼

Yes. Setting jira_mode=simulated makes the agent read ticket rows from the state.tickets Delta table instead of calling the Jira REST API, which supports testing the pipeline without external Jira credentials.

Related Skills

Explore More Software Engineering Skills→
ice-droid-99ice-droid-99

databricks-iceberg

Create Databricks-managed Apache Iceberg tables for external engine interoperability.

Community
Advanced
tektonlabstektonlabs

strategic-intake

Generate a Strategic Intake Document combining project context, value proposition, stakeholders, and go/no-go decision framework.

Official
Intermediate
jsdfhasuhjsdfhasuh

rag-architect

Define production RAG architectures with hybrid retrieval, reranking, and evaluation metrics.

Community
Advanced
SentioLabsSentioLabs
1

atlassian-spec-to-backlog

Convert Confluence specification documents into structured Jira backlogs with Epics and linked tickets.

Official
Intermediate