brainstorming
Structured design dialogue that validates ideas before implementation begins.
investigating-pagerduty-incidents
Generate weekly PagerDuty incident reports for fan-audio and fusion services with root cause analysis from GCP logs. Outputs a Word document ready to paste into Slack.
Full skill instructions
You are a PagerDuty incident investigator for the Music Mission MIQ team at Spotify.
Services: fan-audio, fusion Output: Word document with actionable insights and debugging links
pd incident list --since "$(date -v-7d '+%Y-%m-%d')" --statuses resolved --services "fan-audio" "fusion" --output json
pd incident list --services "fan-audio" "fusion" --output json
pd rest get -e /incidents/INCIDENT_ID/alerts | jq '.alerts[0].body.contexts[0].href'
For each unique error pattern, query a 1-hour window around incident time:
# Find actual errors at incident timestamp
gcloud logging read 'resource.labels.container_name="fan-audio-backend-worker" AND severity="ERROR" AND timestamp>="2025-11-19T22:00:00Z" AND timestamp<="2025-11-19T23:00:00Z"' \
--project=fan-audio-2 \
--limit=30 \
--format=json | \
jq '[.[] | select(.jsonPayload.exc_info or (.jsonPayload.message and (.jsonPayload.message | test("DEADLINE|TypeError|Exception") and (test("UserWarning|Clipped") | not))))] | .[0]'
# Get error frequency for the week
gcloud logging read 'resource.labels.container_name="fan-audio-backend-worker" AND severity="ERROR"' \
--project=fan-audio-2 \
--limit=200 \
--freshness=7d \
--format=json | \
jq -r '[.[] | select(.jsonPayload.message and (.jsonPayload.message | test("Error|Exception|DEADLINE"))) | .jsonPayload.message] | group_by(.) | map({error: .[0], count: length}) | sort_by(.count) | reverse | .[:5]'
Create pagerduty-report-YYYY-MM-DD.docx using python-docx. Keep it concise and actionable.
Structure:
Python Template:
from docx import Document
from docx.shared import RGBColor
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
def add_hyperlink(paragraph, url, text):
"""Add a hyperlink to a paragraph."""
part = paragraph.part
r_id = part.relate_to(url, 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink', is_external=True)
hyperlink = OxmlElement('w:hyperlink')
hyperlink.set(qn('r:id'), r_id)
new_run = OxmlElement('w:r')
rPr = OxmlElement('w:rPr')
new_run.append(rPr)
new_run.text = text
hyperlink.append(new_run)
paragraph._p.append(hyperlink)
return hyperlink
doc = Document()
# Title and date
doc.add_heading('PagerDuty Weekly Report', level=1)
p = doc.add_paragraph('Nov 13-20, 2025')
p.runs[0].italic = True
# Summary
doc.add_heading('Summary', level=2)
doc.add_paragraph('7 incidents (all resolved, low urgency)', style='List Bullet')
doc.add_paragraph('fan-audio: 6 incidents, fusion: 1 incident', style='List Bullet')
# Key Issues (group by root cause)
doc.add_heading('Key Issues', level=2)
p = doc.add_paragraph()
p.add_run('Spotbot gRPC Timeouts (fan-audio-backend-worker)').bold = True
doc.add_paragraph('51 DEADLINE_EXCEEDED errors when calling Spotbot for track recommendations', style='List Bullet')
doc.add_paragraph('Impact: 6 incidents over the week', style='List Bullet')
p = doc.add_paragraph('Link: ', style='List Bullet')
add_hyperlink(p, 'https://oliver.spotify.net/ui/component/fan-audio-backend-worker/incident', 'Oliver Investigation')
# Action Items
doc.add_heading('Action Items', level=2)
doc.add_paragraph('Add circuit breaker/retry logic for Spotbot gRPC calls', style='List Bullet')
doc.add_paragraph('Add millisecond jitter to prevent session creation race conditions', style='List Bullet')
# Links
doc.add_heading('Debugging Links', level=2)
p = doc.add_paragraph()
add_hyperlink(p, 'https://console.cloud.google.com/logs/query;query=resource.labels.container_name%3D%22fan-audio-backend-worker%22%0Aseverity%3D%22ERROR%22;duration=P7D?organizationId=642708779950&project=fan-audio-2', 'GCP Logs - Backend Worker')
doc.save('pagerduty-report-2025-11-20.docx')
Tell the user:
Structured design dialogue that validates ideas before implementation begins.
Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.
Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.
Introduction to the obra skills system with mandatory skill invocation rules and best practices.
Execute a written implementation plan with critical review and task checkpoints.
Delegate independent tasks to specialized agents working concurrently with isolated context.
Isolated git worktrees with smart directory selection and safety verification.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Plan searchable and shareable content that drives traffic, builds authority, and generates leads.
README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.
Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.
Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.
The world's fastest calendar for remote work
Capture, organize, and utilize your knowledge effortlessly.
Instant Summaries of Audio & Video Interviews with AnySummary
Transform PDFs into engaging mind maps.
Chat with any PDF instantly
Create an optimal daily plan using your voice
A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.
AskYourPDF Pricing Plans: Tailored to Your Needs