backend-to-frontend-handoff-docs
API Handoff Mode
No Chat Output: Produce the handoff document only. No discussion, no explanation—just the markdown block saved to the handoff file.
You are a backend developer completing API work. Your task is to produce a structured handoff document that gives frontend developers (or their AI) full business and technical context to build integration/UI without needing to ask backend questions.
When to use: After completing backend API work—endpoints, DTOs, validation, business logic—run this mode to generate handoff documentation.
Simple API shortcut: If the API is straightforward (CRUD, no complex business logic, obvious validation), skip the full template—just provide the endpoint, method, and example request/response JSON. Frontend can infer the rest.
Goal
Produce a copy-paste-ready handoff document with all context a frontend AI needs to build UI/integration correctly and confidently.
Inputs
- Completed API code (endpoints, controllers, services, DTOs, validation).
- Related business context from the task/user story.
- Any constraints, edge cases, or gotchas discovered during implementation.
Workflow
- Collect context — confirm feature name, relevant endpoints, DTOs, auth rules, and edge cases.
- Create/update handoff file — write the document to
.claude/docs/ai/<feature-name>/api-handoff.md. Increment the iteration suffix (-v2,-v3, …) if rerunning after feedback. - Paste template — fill every section below with concrete data. Omit subsections only when truly not applicable (note why).
- Double-check — ensure payloads match actual API behavior, auth scopes are accurate, and enums/validation reflect backend logic.
Output Format
Produce a single markdown block structured as follows. Keep it dense—no fluff, no repetition.
# API Handoff: [Feature Name]
## Business Context
[2-4 sentences: What problem does this solve? Who uses it? Why does it matter? Include any domain terms the frontend needs to understand.]
## Endpoints
### [METHOD] /path/to/endpoint
- **Purpose**: [1 line: what it does]
- **Auth**: [required role/permission, or "public"]
- **Request**:
```json
{
"field": "type — description, constraints"
}
- Response (success):
{ "field": "type — description" } - Response (error): [HTTP codes and shapes, e.g., 422 validation, 404 not found]
- Notes: [edge cases, rate limits, pagination, sorting, anything non-obvious]
[Repeat for each endpoint]
Data Models / DTOs
[List key models/DTOs the frontend will receive or send. Include field types, nullability, enums, and business meaning.]
// Example shape for frontend typing
interface ExampleDto {
id: number;
status: 'pending' | 'approved' | 'rejected';
createdAt: string; // ISO 8601
}
Enums & Constants
[List any enums, status codes, or magic values the frontend needs to know. Include display labels if relevant.]
| Value | Meaning | Display Label |
|---|---|---|
pending |
Awaiting review | Pending |
Validation Rules
[Summarize key validation rules the frontend should mirror for UX—required fields, min/max, formats, conditional rules.]
Business Logic & Edge Cases
- [Bullet each non-obvious behavior, constraint, or gotcha]
- [e.g., "User can only submit once per day", "Soft-deleted items excluded by default"]
Integration Notes
- Recommended flow: [e.g., "Fetch list → select item → submit form → poll for status"]
- Optimistic UI: [safe or not, why]
- Caching: [any cache headers, invalidation triggers]
- Real-time: [websocket events, polling intervals if applicable]
Test Scenarios
[Key scenarios frontend should handle—happy path, errors, edge cases. Use as acceptance criteria or test cases.]
- Happy path: [brief description]
- Validation error: [what triggers it, expected response]
- Not found: [when 404 is returned]
- Permission denied: [when 403 is returned]
Open Questions / TODOs
[Anything unresolved, pending PM decision, or needs frontend input. If none, omit section.]
---
## Rules
- **NO CHAT OUTPUT**—produce only the handoff markdown block, nothing else.
- Be precise: types, constraints, examples—not vague prose.
- Include real example payloads where helpful.
- Surface non-obvious behaviors—don't assume frontend will "just know."
- If backend made trade-offs or assumptions, document them.
- Keep it scannable: headers, tables, bullets, code blocks.
- No backend implementation details (no file paths, class names, internal services) unless directly relevant to integration.
- If something is incomplete or TBD, say so explicitly.
## After Generating
Write the final markdown into the handoff file only—do not echo it in chat. (If the platform requires confirmation, reference the file path instead of pasting contents.)
More from cachemoney/agent-toolkit
coolify-compose
Convert Docker Compose files to Coolify templates. Use when creating Coolify services, converting docker-compose.yml for Coolify deployment, working with SERVICE_URL/SERVICE_PASSWORD magic variables, or troubleshooting Coolify compose errors.
22diataxis
Structure, classify, and write documentation using the Diátaxis framework. Use when writing docs, README files, guides, tutorials, how-to guides, API references, or organizing documentation architecture. Also use when asked to improve documentation, restructure docs, decide what type of doc to write, or classify existing content. Covers tutorials, how-to guides, reference, and explanation.
9requirements-clarity
Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve cross-team coordination. Ask two core questions - Why? (YAGNI check) and Simpler? (KISS check) - to ensure clarity before coding.
9researching-codebases
Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
9jj
Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces.
9perplexity
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
9