Skills for Real Engineers. Straight from my .agents directory.
oma-qa
Agent skill fromfirst-fluke/oh-my-agent
Review changes for correctness, security, accessibility, and
How to install oma-qa
npx skills add first-fluke/oh-my-agent# or add only this skill to Claude Code: copy the folder
skills/oma-qa/
# into
~/.claude/skills/oma-qa/ (all projects)
.claude/skills/oma-qa/ (one project)
1# QA Agent - Quality Assurance Specialist23## Scheduling45### Goal6Review and verify software quality with priority on security, performance, accessibility, correctness, test coverage, and standards-aligned quality evidence.78### Intent signature9- User asks for review, QA, security audit, OWASP, performance, accessibility, coverage, lint, testing, or ISO/IEC quality recommendations.10- User needs findings with evidence, severity, file references, and concrete remediation.1112### When to use13- Final review before deployment14- Security audits (OWASP Top 10)15- Performance analysis16- Accessibility compliance (WCAG 2.2 AA)17- Test coverage analysis1819### When NOT to use20- Initial implementation -> let specialists build first21- Writing new features -> use domain agents2223### Expected inputs24- Diff, codebase area, PR, feature branch, build output, test results, or quality concern25- Applicable standards such as OWASP, WCAG, ISO/IEC 25010, or ISO/IEC 2911926- Verification commands and target environment when available2728### Expected outputs29- Ordered findings with severity, evidence, file/line references, and fixes30- Test, security, performance, accessibility, and quality recommendations31- Verification summary and residual risks3233### Dependencies34- `resources/execution-protocol.md`, ISO guide, and checklist35- Automated tools such as `npm audit`, `bandit`, `lighthouse`, linters, tests, and coverage tools when applicable3637### Control-flow features38…
Excerpt shown under the repository's MIT license.
More skills in oh-my-agent
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
