SkillVaultskills Browse all 500 skills

Reliability · Version 1.1.0 · Reviewed 2026-08-02

Runbook Automation Advisor

Reduce production risk in automation candidates and safety interlocks with evidence, explicit trade-offs, and a verification plan.

4 method steps 4 documented failure modes 4 diagnostic checks 7 quality gates

Decides which manual response steps to automate and designs safe, reversible automation around them.

₹149 one-time

Get this skill archive

What this skill helps you do

  • Automation candidates
  • Safety interlocks
  • Human-in-the-loop design

How Runbook Automation Advisor works

You provide

Impact window, telemetry, and dependency state

It inspects

Saturation and blast radius behind automation candidates

It decides

A safety interlocks plan that stabilizes before diagnosing

You verify

Detect, mitigate, and resolve times recorded separately

What it checks first

Runbook Automation Advisor decides which manual response steps to automate and designs safe, reversible automation around them. Use it when the work involves Automation candidates, Safety interlocks, Human-in-the-loop design.

  1. User-visible impact and error-budget consumption rather than component health.
  2. Saturation signals — queue depth, pool utilization, connection counts — near the onset.
  3. Whether the system recovered on its own, which indicates saturation rather than corruption.
  4. The blast radius and what boundary should have contained it.

Failure modes it recognizes

  • Retry amplification turning a partial failure into a total outage.
  • A shared dependency creating correlated failure across supposedly independent services.
  • Slow resource exhaustion invisible until a hard limit is crossed.
  • A rollback blocked by an incompatible migration.

Answers it will reject

  • Treating the trigger as the root cause, which stops the analysis before the fragility is identified.
  • Adding a runbook step where a boundary would remove the failure mode.
  • Measuring availability as a mean, which hides regional and tenant-level outages.

Decision rules it applies

  • Stabilize user impact before completing diagnosis.
  • Bound every retry with a budget, jitter, and a circuit breaker.
  • Prefer removing a failure mode over detecting it faster.

Evidence it asks for

  • Record time-to-detect, time-to-mitigate, and time-to-resolve separately.
  • Quantify impact in customer terms: failed requests, affected accounts, duration.
  • Verify recovery with the same signal that detected the failure.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to automation candidates.
  2. Trace concrete failure or abuse paths for safety interlocks; do not report checklist items without a mechanism.
  3. Prioritize human-in-the-loop design findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Automation candidates assessment
  • Safety interlocks decision and action plan
  • Human-in-the-loop design verification checklist

Evidence requirements

  • User-visible symptoms and SLO impact
  • Timeline, telemetry, deploys, and dependency state
  • Current mitigations and operational constraints

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Which of our incident response steps should we automate first, and how do we avoid automation making things worse?

Expected output

Automate the steps that are frequent, deterministic, and reversible, and leave judgment steps to humans. The interlock that matters is a bounded blast radius plus a kill switch, because automation that acts during a partial failure can amplify it...

Boundaries and compatibility

Ideal for

  • Automation candidates: produce a decision or artifact grounded in supplied evidence.
  • Safety interlocks: produce a decision or artifact grounded in supplied evidence.
  • Human-in-the-loop design: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Replacing incident command authority
  • Calling a trigger the root cause without a causal chain

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.