smallTechOrg/zero-shot-claude-boilerplate
Agent Claude Code
Main orchestrator for a zero-shot build. Plans each phase, fans out code-generator instances per slice (in parallel) and qa-auditor per slice. Turns an idea plus the API keys in .env into a working, thoroughly-tested agent, one phase per invocation with a human testing gate between phases. Owns the git/PR surface for…
smallTechOrg/zero-shot-claude-boilerplate
Agent Claude Code
Implements ONE independent slice of a phase — any combination of backend (src/), frontend (frontend/), and their tests — running in parallel with other code-generator instances. agent-builder specifies exactly which surfaces each instance owns. Owns spec/api.md contract fidelity for its slice. Also the fix worker for…
smallTechOrg/zero-shot-claude-boilerplate
Agent Claude Code
Read-only quality gate. REVIEWS the new code (logic, security, spec-fidelity, style) AND RUNS the phase gate tests against the real LLM/API (keys from .env), the golden-path/live-server smoke, and the UI tests — exercising the EXACT path the user will test so it works first time — and also performs the whole-tree…
smallTechOrg/zero-shot-claude-boilerplate
Agent Claude Code
THE SINGLE DESIGN AUTHORITY. Writes the complete, ruthlessly-scoped spec under spec/ — the product spec AND the architecture (incl. the ## Stack section) AND the agent-graph AND the phased plan — from an idea + intake answers, then self-reviews it for completeness, coherence, scope, testability, independent slicing…
smallTechOrg/zero-shot-claude-boilerplate
Command Claude Code
Turn a zero-shot idea into a perfectly-working, thoroughly-tested agent (alias for the zero-shot-build skill).
smallTechOrg/zero-shot-claude-boilerplate
Command Claude Code
Diagnose and fix a bug, error, failing test, or spec/code drift, then verify (alias for the zero-shot-fix skill).
smallTechOrg/zero-shot-claude-boilerplate
Command Claude Code
Reconcile spec and code so they match — spec wins — then verify (alias for the zero-shot-sync skill).
smallTechOrg/zero-shot-claude-boilerplate
Settings file Claude Code
Agent settings declaring 4 allowed tools.
smallTechOrg/zero-shot-claude-boilerplate
Skill Claude CodeCodex
Turn a zero-shot idea into a perfectly-working, thoroughly-tested, spec-driven agent. One intake round (which also collects the API keys into .env), then the agent-builder builds one phase at a time — autonomous within a phase, with a human testing gate between phases. Also used to add a new capability to an existing…
smallTechOrg/zero-shot-claude-boilerplate
Skill Claude CodeCodex
Diagnose and fix a problem in an existing agent — a bug description, a runtime error/stack trace, failing tests, or spec/code drift — then verify the fix. Calls the worker agents directly; runs autonomously to a verified result.
smallTechOrg/zero-shot-claude-boilerplate
Skill Claude CodeCodex
Reconcile spec and code so they match. Audits the whole tree for drift, brings code in line with the spec (spec wins), and verifies. Calls worker agents directly; runs autonomously to a CLEAN audit.
smallTechOrg/zero-shot-claude-boilerplate
Instructions file
Claude Code instructions for smallTechOrg/zero-shot-claude-boilerplate, covering claude code — entry point, what this repo is, your first action every session, spec manifest (read in this order when spec is complete) and if the spec is not ready.