Works with the AI tools you already use
API Change Risk Starter
Screen a proposed API change for client breakage, rollout gaps, data-contract drift, retry hazards, and the specialist review needed next.
Free
See it in action
You say
We want to rename status=pending to status=queued, add a nullable field, and retire v1 in 60 days. Three mobile versions and two partner integrations may still consume the old enum. Produce a quick risk screen, rollout questions, and specialist handoff. Do not edit code or claim the change is safe.
Your agent does
Risk screen: enum replacement is potentially breaking, nullable-field impact depends on client generation rules, and the 60-day retirement window lacks verified consumer coverage. Preserve the old value during migration, inventory consumers, test generated clients, define telemetry and rollback gates, then route the work to enum-evolution and API-retirement specialists.
About this skill
The problem
Changing an API contract without a rigorous impact assessment often leads to broken clients, failed rollouts, and emergency rollbacks. Developers frequently lack a structured way to screen for compatibility risks before code is written.
What it does
- Analyzes diffs between old and new API contracts to identify breaking changes.
- Maps the impact across producers, servers, and known client integrations.
- Screens for specific risks in retry logic, message ordering, and observability.
- Identifies gaps in rollout and rollback plans before implementation begins.
- Provides a structured diagnostic report with pre-implementation gates.
Why this beats prompting it yourself
This skill enforces a strict diagnostic workflow that prevents common oversight, such as assuming server-side tests prove client compatibility. It maintains a clear boundary between supplied facts and hypotheses, ensuring you don't mistake assumptions for verified evidence.
Use cases
- Screening GraphQL schema changes for nullability or enum evolution risks.
- Evaluating the impact of changing webhook signatures or payload structures.
- Planning the deprecation window for legacy API versions with coexisting clients.
- Assessing pagination or rate limit changes for potential integration failures.
Known limitations
This skill performs no external actions or code execution. It relies entirely on sanitized material provided by the user and cannot discover unknown consumers or verify real-world telemetry.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account
Frequently Asked Questions
Popular in Documentation
incident-postmortem
Transform raw incident logs and Slack threads into blameless, structured postmortems and 5-Whys RCA reports.
Changelog & Release Notes Generator
Generate beautiful release notes and changelogs automatically from commits, pull requests, and deployments.
Context Engineering — Optimize What Your AI Agent Sees and When
Systematic framework for engineering AI agent context at the right level of abstraction
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.