sahil-ss9/agent-personas/api-compatibility-analysis
Claude Code and agent skill by sahil-ss9/agent-personas
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Classify every proposed API change as compatible or breaking across all three dimensions.
Install
npx vskill@latest install sahil-ss9/agent-personas/api-compatibility-analysisSKILL.md
API compatibility analysis
When to use
Every proposed change to a published contract, without exception.
Procedure
- Check all three dimensions: source compatibility (client code compiles/runs), wire compatibility (serialization matches), semantic compatibility (reasonable expectations hold). Old clients must keep working within a major version.
- Classify the change: SAFE — adding optional components, adding enum values to request-only enums, additive fields with back-compatible defaults. BREAKING — removing or renaming anything (rename = remove+add), moving fields between files or into/out of oneofs, changing field types, changing resource names, changing defaults, changing value formats (e.g. IPv4 → IPv6), changing default serialization.
- Apply the judgement rule: code depends on behaviour even when undocumented — do not change visible semantics reasonable user code relies on. When in doubt, it is breaking.
- For breaking needs: new major version; version explicitly (semver-shaped); announce deprecations with timelines and a migration path; never remove in minor/patch.
Decision rules
- Every change gets a written compatible/breaking classification with reasoning — "should be fine" is not a classification.
- Prefer additive evolution; when a replacement field is added alongside the old, specify resolution of conflicting inputs explicitly.
- Pagination added after launch must not shrink what older clients receive by default.
Pitfalls
- Treating wire-compatible as safe when source compatibility breaks (type changes, file moves).
- Silently changing output-only field formats.
Done
Per-change classification across all three dimensions with a versioning decision and deprecation path where breaking.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/api-compatibility-analysis/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/sahil-ss9/agent-personas/api-compatibility-analysis)