Fortify

Production workflows fail. APIs time out, rate limits hit, networks drop. This skill adds the five resilience layers you should have built in from the start: input validation, exponential backoff retries, fallback strategies, circuit breakers, and proper timeouts. It's opinionated about what's retryable (500s, timeouts) versus what's not (auth failures, bad requests). The audit checklist is genuinely useful for code review. Run this when you're tired of getting paged at 3am because your workflow has no error handling, or when you need to harden something before it goes to production. Pairs well with the evaluate skill to actually test your failure scenarios.

skills.sh installs: 342
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill fortify --agent claude-code

Installs into .claude/skills of the current project.

Files

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the guardrails-safety reference in the agent-workflow skill for defense-in-depth patterns and error boundary design.

Make the workflow resilient. Every external call will fail eventually — model APIs, tools, databases, third-party services. Fortify ensures the workflow handles failure gracefully.

Fortification Layers

Layer 1: Input Validation

Validate all inputs before processing
Return clear error messages for invalid input
Set size limits on all input fields

Layer 2: Retry with Backoff For transient failures (network errors, rate limits, timeouts):

Retry strategy:
  max_retries: 3
  initial_delay: 1s
  backoff_multiplier: 2
  max_delay: 30s
  retryable_errors: [429, 500, 502, 503, 504, TIMEOUT, CONNECTION_ERROR]
  non_retryable_errors: [400, 401, 403, 404]

Layer 3: Fallback Responses When retries are exhausted:

SKILL.md on GitHub