← ClaudeAtlas

poc-spec-driven-builderlisted

Use this skill whenever the user wants Claude Code to build a proof of concept (PoC), prototype, or "prove this idea works" — even if they just describe an idea informally and don't say "PoC" or "skill." Also trigger for "build this from scratch," "design then build," or any request to validate technical feasibility before full development. Works on any language/framework — the stack is researched fresh each time, never assumed. This skill runs the whole pipeline autonomously and without pausing to ask the user clarifying questions — (0) verify git + gh CLI are present (refuses to proceed otherwise), (1) research best practices for the idea's domain/stack, (2) write a lightweight SRS (requirements spec), (2.5) file a tracking ticket in whichever of Jira/Monday.com/GitHub Issues is available and branch feat/<ticket>-<slug> off dev, (3) derive a full test-case matrix that covers every SRS requirement BEFORE any implementation code is written, (4) build to make the tests pass, (5) report results, open questions,
th3r-dev/th3-skills · ★ 2 · Web & Frontend · score 66
Install: claude install-skill th3r-dev/th3-skills
# PoC Spec-Driven Builder Turns a loosely-described idea into a working, evidence-backed proof of concept — research → spec (SRS) → test matrix → implementation → verification → PR — run end-to-end without interrupting the user for cla~rification. Ambiguity is resolved by making the most reasonable assumption and logging it, not by asking. This mirrors how modern AI coding agents are meant to work: specs and tests are the source of truth the agent builds *to*, not decisions made ad hoc while writing code. A PoC only proves something if what it's proving was written down first. Stack-agnostic by design: Step 1 always researches the conventions of whatever language/framework the target repo actually uses (Rust, TypeScript, Python, Go, Dioxus, Next.js, …) — nothing here assumes a particular stack. What's fixed is the *process* (spec → tests → build → ticket → PR), not the technology. ## Core principle: never block on questions Default behavior for this skill is autonomous execution. When something is unspecified: 1. Pick the most conventional, lowest-risk, industry-standard choice for that domain. 2. Write it into the SRS's **Assumptions** section with a one-line rationale. 3. Keep going. Only break this rule if the user's message contains an explicit, irreversible constraint that's actually contradictory (e.g., they named two mutually exclusive databases) — then state the conflict plainly and pick one anyway, noting it's an assumption to revisit, rather than stopping. ##