# Shaft Developer

> Use when starting any SHAFT testing task to select exactly one lifecycle, implementation, or tool specialist before doing the work.

- Skill: `shafthq/shaft-developer` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add shafthq/shaft-developer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/shafthq/shaft-developer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: shafthq (https://skillmd.com/u/shafthq)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/shafthq/shaft-developer

---


# SHAFT Developer

## Routing

- Lifecycle: [`shaft-requirements-analysis`](../shaft-requirements-analysis/SKILL.md), [`shaft-test-planning`](../shaft-test-planning/SKILL.md), [`shaft-test-case-design`](../shaft-test-case-design/SKILL.md), [`shaft-test-data-design`](../shaft-test-data-design/SKILL.md), [`shaft-test-environment`](../shaft-test-environment/SKILL.md), [`shaft-test-execution`](../shaft-test-execution/SKILL.md), [`shaft-test-monitoring`](../shaft-test-monitoring/SKILL.md), [`shaft-failure-analysis`](../shaft-failure-analysis/SKILL.md), [`shaft-flaky-test-analysis`](../shaft-flaky-test-analysis/SKILL.md), [`shaft-defect-reporting`](../shaft-defect-reporting/SKILL.md), [`shaft-execution-reporting`](../shaft-execution-reporting/SKILL.md), [`shaft-stakeholder-reporting`](../shaft-stakeholder-reporting/SKILL.md), [`shaft-accessibility-testing`](../shaft-accessibility-testing/SKILL.md), [`shaft-nonfunctional-test-design`](../shaft-nonfunctional-test-design/SKILL.md)
- Implementation: [`shaft-automated-test-authoring`](../shaft-automated-test-authoring/SKILL.md), [`shaft-page-objects`](../shaft-page-objects/SKILL.md), [`shaft-fluent-api`](../shaft-fluent-api/SKILL.md), [`shaft-locator-design`](../shaft-locator-design/SKILL.md), [`shaft-web-actions`](../shaft-web-actions/SKILL.md), [`shaft-mobile-actions`](../shaft-mobile-actions/SKILL.md), [`shaft-api-testing`](../shaft-api-testing/SKILL.md), [`shaft-database-testing`](../shaft-database-testing/SKILL.md), [`shaft-assertions`](../shaft-assertions/SKILL.md), [`shaft-guide-search`](../shaft-guide-search/SKILL.md), [`shaft-test-recording`](../shaft-test-recording/SKILL.md), [`shaft-recording-codegen`](../shaft-recording-codegen/SKILL.md), [`shaft-change-verification`](../shaft-change-verification/SKILL.md)
- Tools: [`shaft-mcp`](../shaft-mcp/SKILL.md), [`shaft-cli`](../shaft-cli/SKILL.md)

Read [the deterministic routing map](references/routing.md), select the single
closest specialist for the current deliverable, and load only that skill. A
natural-language web, mobile, or API scenario whose output is generated test
code starts at `shaft-test-recording`, then returns here for
`shaft-recording-codegen` after the recording is persisted and replay-proven.
Return here only when the user asks for a distinct next deliverable. Never guess
SHAFT syntax, tool names, execution evidence, or product behavior.