Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Api Compatibility

ASecurity

Use when evaluating whether an API change is backward compatible — diffing OpenAPI/Swagger or JSON Schema, deciding breaking vs non-breaking, or picking a SemVer bump for an API. Triggers: "breaking change", "backward compatible", "API compat", "OpenAPI diff", "schema diff", "will this break clients", "oasdiff", "deprecate endpoint", "version bump for API".

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsrustgorailsapi

Works with

cliapi

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add matthews-wong/claude-code-plugins --skill api-compatibility --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Api Compatibility?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Api Compatibility
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/matthews-wong-api-compatibility/badge)](https://www.skillsdirectory.com/skills/matthews-wong-api-compatibility)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: api-compatibility
description: >
  Use when evaluating whether an API change is backward compatible — diffing
  OpenAPI/Swagger or JSON Schema, deciding breaking vs non-breaking, or picking
  a SemVer bump for an API. Triggers: "breaking change", "backward compatible",
  "API compat", "OpenAPI diff", "schema diff", "will this break clients",
  "oasdiff", "deprecate endpoint", "version bump for API".
---

# API Compatibility

Decide whether a contract change can break existing consumers. The golden rule:
**a change is safe only if every existing valid client request still succeeds and
every existing client can still parse the response.**

## Direction is everything

Required-ness inverts between request and response:

- **Request**: making a field *required* or *adding* a validated constraint is
  BREAKING (old callers omitting it now fail). Making a field *optional* is safe.
- **Response**: *removing* a field or *narrowing* its type is BREAKING (clients
  parsing it break). *Adding* an optional field is safe (tolerant readers).

## Fast classification

BREAKING: removed endpoint/method/field; new required request field; type change
or narrowing; tightened validation; removed response enum value; auth scope
narrowed; changed status code; renamed field.

NON-BREAKING: new endpoint; new optional request field; new optional response
field; loosened validation; previously-required request field made optional;
new response enum value; docs/examples.

The full matrix (with edge cases like `oneOf`/`anyOf`, nullability, arrays,
`additionalProperties`, and format changes) is in
`./reference/compat-rules.md`.

## Preferred tooling

- OpenAPI: `oasdiff breaking base.yaml revision.yaml` — purpose-built, exit code
  signals breaking changes; ideal for CI. Fall back to `openapi-diff`.
- Trust the tool's verdict but still explain each finding in plain terms and add
  a migration path — a raw diff is not guidance.

## Managing an unavoidable break

1. Prefer additive evolution over mutation (add v2 field, keep v1).
2. If you must break: bump the major version, keep the old version running,
   announce a deprecation window, and add `Deprecation`/`Sunset` headers.
3. Never silently reuse a field name with new semantics — that is a hidden break.

## Guardrails

- Do not declare "safe" without checking request vs response direction.
- Whether a response field is consumer-relied is an assumption — state it; when
  unsure, treat removal as breaking.
- SemVer: breaking = major, additive = minor, docs = patch.

Attribution

matthews-wongmatthews-wong
View sourceSee grades on GitHubMore from matthews-wong →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →