Works with the AI Agents you already use
Production Bug Detective
Reproduce production defects from logs, traces, versions, and user impact, then validate a minimal safe fix.
$9.99
Production Bug Detective
Example session with this skill installed
Users report duplicate notifications after retrying a save. Create a production bug investigation plan.
- Read your context and instructions
- Compiled the production bug detective
Production Bug Detective: practical plan
Bug investigation
Define the symptom
Confirm affected users, notification types, time window, app versions, frequency and whether the underlying save is duplicated or only the notification. Avoid collecting message content unless necessary.
Reconstruct evidence
Correlate request IDs, retry attempts, queue messages, database records and notification provider responses. Compare healthy and affected traces. Check recent deployments and provider behavior.
Hypotheses
- Client retries after timeout while server commits successfully.
- Queue delivery is at-least-once without idempotency.
- Consumer acknowledges after sending rather than recording completion.
Reproduction and fix
Create a test that injects a timeout after commit and replays the same request. Add an idempotency key or deduplication record with a bounded retention policy. Ensure notification side effects are transactional or recoverable.
Rollout
Deploy behind a feature flag if possible. Monitor duplicates, dropped notifications and queue lag. Define rollback and data cleanup steps. Document the confirmed cause only after evidence supports it.
Measurement and review
Record the baseline, source, date range, denominator and owner. Use one primary measure plus quality guardrails; compare like-for-like cohorts and disclose missing data. Treat estimates as scenarios, not observed outcomes.
Risks and controls
Check relevance, consent, disclosure, workload and downside before scaling. Keep an evidence trail, obtain human review for material commitments, and pause if trust, quality or compliance signals deteriorate.
Next steps
- Confirm the goal, audience and available capacity.
- Gather the minimum evidence for a first test.
- Assign an owner, budget and review date.
- Run a small pilot, record outcomes and decide whether to iterate, expand or stop.
Connects securely to your tools. The creator never sees your data.
About this skill
Create a practical, evidence-led Production Bug Detective workflow. Reproduce production defects from logs, traces, versions, and user impact, then validate a minimal safe fix. Distinguish observations from assumptions, request missing inputs, give actionable recommendations with owners and measurable outcomes, and flag uncertainty. Avoid fabricated metrics, unsupported guarantees, deceptive tactics and unnecessary personal data.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago