Auto-review Jira ticket quality with OpenRouter GPT and coaching comments

Jira trigger → AI quality score → auto-comment on low scores

Who

Team leads or project managers using Jira Cloud

You get

Automatically evaluate new Story/Bug/Task tickets; low-quality ones receive coaching comments

You need

n8n · jira

Steps

1. Configure trigger and threshold

   After importing the template into n8n, configure the Jira Trigger node: select Jira Software Cloud credentials, set event filter to issue_created with issuetype in (Story, Bug, Task). Then configure the Set Score Threshold node, setting SCORE_THRESHOLD to your desired cutoff (default 7).

2. Configure AI quality evaluation

   Connect the OpenAI Quality Evaluator (OpenRouter Chat Model) to the Quality Analysis Agent. In the Quality Analysis Agent, verify the prompts: the user message passes ticket type, title, description, and reporter; the system message defines 5 scoring criteria (title clarity, description completeness, acceptance criteria, reproduction steps/user scenario, scope & dependencies), each scored 1-3, with a specified JSON output structure.

   Execution prompt · Source text。Quality Analysis Agent node Text / User Message field

   Copy prompt

   =Evaluate this Jira ticket:
   
   <ticket>
   Type: {{ $('When JIRA Ticket Created').first().json.issue.fields.issuetype.name }}
   Title: {{ $('When JIRA Ticket Created').first().json.issue.fields.summary }}
   Description: {{ $('When JIRA Ticket Created').first().json.issue.fields.description ?? "No description provided." }}
   Reporter: {{ $('When JIRA Ticket Created').first().json.issue.fields.reporter.displayName }}
   </ticket>
   
   Return the evaluation JSON.

   Execution prompt · Source text。Quality Analysis Agent node System Message field

   Copy prompt

   You are a Jira ticket quality reviewer. Your role is to evaluate whether 
   a ticket contains enough information for a developer to start working on it 
   without asking clarifying questions.
   
   Evaluate the ticket on these 5 criteria:
   
   1. **Title clarity** — Is the title specific and action-oriented? (not "Fix bug" or "Update page")
   2. **Description completeness** — Does it explain the context, the problem, and the expected behavior?
   3. **Acceptance criteria** — Are there clear, testable conditions for "done"?
   4. **Reproduction steps** — For bugs: are steps to reproduce present? For stories: is there a user scenario?
   5. **Scope & dependencies** — Are unknowns, blockers, or related tickets mentioned?
   
   For each criterion, assign a score from 1 to 3:
   - 1 = Missing or too vague to be useful
   - 2 = Present but incomplete
   - 3 = Clear and sufficient
   
   Output a JSON object with this exact structure:
   {
     "scores": {
       "title_clarity": 1-3,
       "description_completeness": 1-3,
       "acceptance_criteria": 1-3,
       "reproduction_steps": 1-3,
       "scope_dependencies": 1-3
     },
     "total": 5-15,
     "normalized_score": 1-10,
     "missing": ["list of the criteria scored 1"],
     "comment": "2-3 sentence coaching comment addressed directly to the ticket author. Friendly tone. Name exactly what is missing and why it matters. Do not mention the score."
   }
   
   Return only the JSON object. No preamble, no markdown fences.

3. Configure score parsing

   In the Parse Normalized Score node (Code node), keep the default JS code: extract JSON from the AI output, strip markdown code block markers, parse as object and return. Throws error if parsing fails.

   Execution prompt · Source text。Parse Normalized Score node JS Code field

   Copy prompt

   const response = $input.first().json.output ?? $input.first().json.text ?? "";
   
   const cleaned = response
     .replace(/^```json\s*/i, "")
     .replace(/^```\s*/i, "")
     .replace(/\s*```$/i, "")
     .trim();
   
   let scores;
   
   try {
     scores = JSON.parse(cleaned);
   } catch (error) {
     throw new Error(`Invalid JSON returned by Quality Checker Agent.\n${error.message}`);
   }
   
   return scores;

4. Configure conditional branch

   In the Check Score Threshold node (If node), set the condition: normalized_score < SCORE_THRESHOLD. Ensure the left value comes from Parse Normalized Score output and the right value from Set Score Threshold.

5. Configure comment action

   In the Add Comment to JIRA Ticket node, configure Jira credentials and verify the comment template includes coaching advice, quality score, and missing items list. If the score meets the threshold, the workflow ends at the No Action Needed node.

   Execution prompt · Source text。Add Comment to JIRA Ticket node Comment field

   Copy prompt

   ={{ $json.comment }}
   
   **Quality score: {{ $json.normalized_score }}/10**
   Missing: {{ $json.missing.join(', ') }}
   
   _This comment was generated automatically to help keep our backlog clean._

You are an n8n workflow setup assistant. The user wants to replicate a Jira ticket quality auto-review workflow. Help the user: 1) Confirm they have Jira Cloud and OpenRouter credentials; 2) Import the workflow from template https://n8n.io/workflows/16693/; 3) Check node configurations step by step, especially the Quality Analysis Agent system message and OpenRouter model selection; 4) For testing, create a low-quality Jira ticket first to verify the comment triggers. Note: default model is openai/gpt-oss-20b:free; change if needed.