Claude Skill Builder — Testing & QA agent for Claude Code
Builds Claude Code skills in ~/.claude/skills/ / (SKILL.md, scripts, tests), incl.
How to install Claude Skill Builder
Installs to ~/.claude/agents/uribelandscapes-claude-agents-claude-skill-builder.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/UribeLandscapes/claude-agents/HEAD/agents/claude-skill-builder.md -o ~/.claude/agents/uribelandscapes-claude-agents-claude-skill-builder.md Restart Claude Code, or start a new session, for it to be picked up.
What Claude Skill Builder does
name: claude-skill-builder description: Builds Claude Code skills in ~/.claude/skills// (SKILL.md, scripts, tests), incl. API helpers with secret handling. Returns files, test counts, secret-scan result. tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"] model: sonnet not_for: "Not for harness config (claude-harness-engineer), router/bin/lib tooling (router-tooling-engineer), agent files (agent-librarian), or running a skill." capabilities: [skill.build]
Role
Builds one
Alternatives in Testing & QA
- Helper Author — Owns the shared Cypress helper library for component automation 41k ★
- Logic Hacker — Red Team persona for Business Logic and Auth manipulation 548 ★
- Review Code Quality — Reviews code changes for code quality, conventions, readability, DRY violations, error handling, test coverage 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Stamity Implementer
Builds one planned unit — code plus the tests that prove it — inside the unit's file set, runs the local gates
Prober
Runs a build, test, lint, or any command and returns a pass/fail probe (exit code, warn/error counts) instead
Design Archeologist
Long-running codebase scan. Extracts de-facto design tokens from existing UI code, clusters them by frequency,
God Executor
Implements one planned slice test-first in a fresh context and returns the files changed plus the recorded ver
Data Seeder
Use this agent when you need to generate realistic test data, create seed scripts, or build test fixtures for
API Automation Agent
Use for this project's API test automation lifecycle — discovering API context, resolving auth, designing test
Related Skills
Test After Change Diagnostics.V1
If any program code changes, run unit-tests and follow up on the test-result (fix code if there is an error).
Genlayer Agent Playbook
Agent-ready GenLayer builder playbook: confirmed GenVM nondet bug catalog, contract skeletons, direct-mode tes
Generate API Tests From Swagger
Sinh API test cases và automation scripts từ Swagger/OpenAPI specification. Hỗ trợ 2 mode — SPEC (chỉ test cas