Skip to content

bg-szy/TOP-SKILLS / skills/agent-skills/breaking-changes-management

breaking-changes-management

Verified

Manage breaking API changes, migration guides, deprecation notices, and semver versioning. Use when introducing breaking changes, writing migration paths, updating changelogs, or releasing major versions.

Breaking Changes Management

Use this skill when behavior, interfaces, configuration, or compatibility contracts change in a way that can break consumers.

  • Leverage native parallel subagent dispatch and 200k+ context windows where available.

Activation Conditions

Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.

  • Releasing a major version
  • Renaming or removing public APIs
  • Changing request or response shapes
  • Replacing config keys, env vars, CLI flags, or file formats
  • Writing migration notes, deprecation notices, or upgrade checklists

Workflow

  1. Identify the exact consumer-visible break.
  2. State who is affected and from which version.
  3. Provide the replacement path or mitigation.
  4. Add before/after examples.
  5. Update CHANGELOG.md and any setup or usage docs that changed.

Required Outputs

  • Changelog entry with a clear BREAKING label
  • Migration guide with old usage, new usage, and upgrade steps
  • Deprecation timeline if removal is delayed
  • Validation notes for any examples or scripts that changed

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.

  • GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
  • Claude Code: keep the folder in a local skills directory or a compatible plugin source.
  • Codex: install or sync the folder into $CODEX_HOME/skills/breaking-changes-management and restart Codex after major changes.

MCP Availability And Fallback

Preferred MCP Server: None required

  • Fallback prompt: "Use the Breaking Changes Management skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding."
  • Do not claim an MCP operation was used when the active host does not expose it.
  • Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.

Anti-Patterns

  • Starting work before the plan or gate is clear: Execution drifts when success criteria are implied instead of explicit.
  • Treating verification as optional cleanup: The last mile is where regressions and missing updates are usually hiding.
  • Mixing planning, implementation, and release work in one jump: You lose the causal chain that explains why a change is safe.

Verification Protocol

Before claiming "skill applied successfully":

  1. Pass/fail: The Breaking Changes Management workflow starts from explicit success criteria, constraints, and stop conditions.
  2. Pass/fail: Required evidence is collected before any completion, approval, or readiness claim.
  3. Pass/fail: The next action follows the documented gate order without skipping review or verification steps.
  4. Pressure-test scenario: Apply the workflow under time pressure with one failing check and one tempting shortcut.
  5. Success metric: Zero rationalizations; blocked, failed, or unverified work is reported as such.

Migration Checklist

  • Old behavior described precisely
  • New behavior described precisely
  • Replacement path documented
  • Upgrade steps ordered and testable
  • Rollback or compatibility notes included
  • README/setup docs updated if user-facing behavior changed

References & Resources

Documentation

Scripts

Related Skills

  • development-workflow: Use it when the workflow also needs planning, quality gates, and delivery tracking.
  • code-quality: Use it when the workflow also needs two-stage review (spec compliance first, then code quality), maintainability, and refactoring guidance.
  • systematic-debugging: Use it when the workflow also needs root-cause debugging before proposing fixes.
  • test-driven-development: Use it when the workflow also needs test-first implementation and regression safety.
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall