Skip to content

The moment it happens

Ask for missing details on new GitHub issues

New GitHub issues without steps to reproduce or a version number get a polite comment asking for them and a needs-info label.

Runs
The moment it happens
Apps
GitHub
AI
Yes, uses the built-in AI allowance
Access
Issues: read and write

Send this to your assistant

Create a ClickRuntime automation: when a new issue is opened in acme/app, check if it has steps to reproduce, expected vs actual behaviour and a version; if something is missing, comment asking for it and add the needs-info label.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A large share of bug reports arrive without a version or a way to reproduce, and the first maintainer reply is almost always the same request for more detail. That reply can take days to arrive, and by then the reporter has moved on.

This automation sends that first reply straight away. When an issue is opened, AI checks whether it is a bug and, if so, whether it includes a version, steps to reproduce, expected versus actual behaviour and logs. It comments with only the items that are missing and adds a needs-info label so triage can filter those issues out.

Maintainers of busy open source projects and internal platform teams use it to get answerable bug reports without spending their own time on the first round.

What you get out of it

  • Reporter is asked while still around

    The comment lands seconds after the issue is opened, when the reporter is most likely to answer.

  • Only what is missing

    The comment lists the specific details absent from that report, not a generic checklist.

  • A label you can filter on

    needs-info issues can be hidden from your triage view until the reporter responds.

  • Feature requests untouched

    Only bug reports get the comment, so people asking for features do not receive an odd request for logs.

  • Works with templates

    It still catches templates submitted with placeholder text or empty sections.

How it works

What happens, step by step

  1. GitHub sends the new issue to the automation the moment it is opened.

  2. AI reads the title and body and checks for steps to reproduce, expected and actual behaviour, and a version number.

  3. If anything is missing, it posts one comment listing exactly what to add and applies a needs-info label.

  4. Feature requests and complete bug reports are left alone.

Before it runs live

  • Connect GitHub
  • Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens
Ask for missing details on new GitHub issuesjust nowSucceeded
GitHub comment · acme/app #1043Thanks for the report. To look into this we need a bit more: - The version you are running (`acme --version`) - Steps to reproduce, ideally a minimal example We have added the needs-info label; it will be removed once these are here.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.
  • Your own rules

    Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.

  • Any number of apps

    One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.

  • AI where it helps

    Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.

  • On a schedule or on each event

    Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

  • Act only on the items that match your own rules, and skip the rest
  • Change what the AI looks for, or how it writes the result
  • Add another app, for example also send it to Slack
  • Combine it with other GitHub steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.
ask_for_missing_details_on_new_github_issues.pyexample
from clickruntime import on_event, credentials, http, verify, ai

LABEL = "needs-info"
SCHEMA = {"type": "object", "properties": {
    "kind": {"type": "string", "enum": ["bug", "feature", "question"]},
    "missing": {"type": "array", "items": {"type": "string", "enum": ["version", "steps", "expected_actual", "logs"]}}}}
ASK = {"version": "The version you are running", "steps": "Steps to reproduce, ideally a minimal example",
       "expected_actual": "What you expected to happen and what happened instead", "logs": "Any error message or log output"}

def gh(method, path, **kw):
    resp = http.request(method, f"https://api.github.com{path}", headers={
        "Authorization": f"Bearer {credentials.connection('github', 'work')}",
        "Accept": "application/vnd.github+json"}, **kw)
    resp.raise_for_status()
    return resp.json() if resp.content else None

@on_event
def handle(event):
    if not verify.github(event.body, event.header("X-Hub-Signature-256"), credentials.secret("GITHUB_WEBHOOK_SECRET")):
        return {"ignored": "bad signature"}
    body = event.json
    if event.header("X-GitHub-Event") != "issues" or body.get("action") != "opened":
        return {"ignored": True}
    issue, repo = body["issue"], body["repository"]["full_name"]
    r = ai.generate(f"Title: {issue['title']}\n\n{(issue.get('body') or '')[:4000]}", json_schema=SCHEMA, max_output_tokens=80,
                    system="Classify this GitHub issue. For bugs, list which of version, steps, expected_actual, logs are clearly missing. For other kinds return an empty list.").json
    missing = (r.get("missing") or []) if r["kind"] == "bug" else []
    if not missing:
        return {"kind": r["kind"], "complete": True}
    lines = "\n".join(f"- {ASK[m]}" for m in missing)
    gh("POST", f"/repos/{repo}/issues/{issue['number']}/comments", json={"body":
       f"Thanks for the report. To look into this we need a bit more:\n{lines}\n\nWe have added the {LABEL} label; it will be removed once these are here."})
    gh("POST", f"/repos/{repo}/issues/{issue['number']}/labels", json={"labels": [LABEL]})
    return {"issue": issue["number"], "missing": missing}

FAQ

Common questions

Will it comment on feature requests?
No. The issue is first classified as a bug, feature or question, and only bugs are checked for missing details.
Does it remove the label when the reporter replies?
Not in this version. Ask your assistant to also listen for issue_comment events from the issue author and remove needs-info when they reply.
We already use issue templates. Is this still useful?
Yes. Templates are often skipped or left half-filled. This catches the reports where the version line still says "x.y.z" or the steps section is empty.
What permissions does it need?
Issues: read and write. Nothing else in your accounts is used.
Does it need AI?
Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.
How many runs does it use?
One run for each event the app sends.
Can I change how it works?
Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

Set up “Ask for missing details on new GitHub issues” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.