go
The main entry point for all coding tasks. Refines your raw prompt into an expert-level prompt, then builds using TDD with full verification. Use this for everything.
SKILL.md.claude/skills/go/SKILL.md
GitHubYou received a raw prompt from a non-technical user. You MUST refine it first, then execute it using the full build workflow.
Raw input: $ARGUMENTS
Phase 1: Refine the Prompt
Transform the raw input by adding:
Scope — Check CLAUDE.md build order to identify the F-number, exact file paths, and which services are involved.
References — Point to existing patterns to follow:
- Services: follow
services/ingestion/service.py - Schemas: follow
schemas/test_cases.py - Routes: follow
routes/test_cases.py
- Services: follow
LLD mapping — Which PRD feature, LLD section, data models, API endpoints
Dependencies — What's already built that this connects to
Verification — Tests to write, endpoints to curl, commands to run
Show the refined prompt:
Refined prompt: [your enhanced version]
Phase 2: Map to PRD + LLD
Before writing any code:
- Find the F-number in @docs/PRD.md
- Find the matching component in @docs/LLD.md Section 2 — confirm exact file path, data model (Section 4), and API endpoint (Section 3)
- State: "Building [component] at [path], covering [F-number]."
Phase 3: Write the Test FIRST (RED)
Create service-one/src/tests/test_<module>.py BEFORE the implementation.
Tests must cover:
- Happy path — normal input → expected output
- Edge case — empty input, missing fields, boundary values
- Error path — invalid input, downstream failure
Mock all external dependencies (LLM, DB, HTTP). Run to confirm FAILS:
poetry run pytest service-one/src/tests/test_<module>.py -v
Phase 4: Implement (GREEN)
Write minimum code to make tests pass. Follow these rules:
- All I/O functions must be
async - Pydantic v2 models for request/response — no raw dicts
- LLM calls only through
api/llm/interfaces.py temperature=0on evaluation/judge callsflush()notcommit()— session dependency handles transactions- File paths must match LLD Section 2 exactly
- No hardcoded secrets — use
os.getenv()
Run tests to confirm GREEN:
poetry run pytest service-one/src/tests/test_<module>.py -v
Phase 5: Production Checklist
Before declaring done:
- No
requests.get/post— usehttpxasync - No blocking DB calls in
async def - All HTTP calls have
timeout=set - No hardcoded secrets
- Health endpoints untouched
- No direct SDK imports in service code
Phase 6: Explain in Plain English
Tell the owner:
- What was built — one sentence, no jargon
- Where it lives — file paths
- Which requirement — F-number
- How to verify — command or endpoint
Phase 7: Show Git Commands (never execute)
git add <specific files>
git commit -m "feat(F<number>): <short description>"
git push origin stage