Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add anhtester/antigravity-testing-kit --skill rbt_manual_testinggit clone --depth 1 https://github.com/anhtester/antigravity-testing-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/anhtester/antigravity-testing-kit/rbt_manual_testing)<a href="https://agentmods.dev/skills/anhtester/antigravity-testing-kit/rbt_manual_testing"><img src="https://agentmods.dev/badge/skills/anhtester/antigravity-testing-kit/rbt_manual_testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anhtester/antigravity-testing-kit/rbt_manual_testing"><img src="https://agentmods.dev/badge/skills/anhtester/antigravity-testing-kit/rbt_manual_testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.05513 |
| Opus 5.5 | $0.00022 | $0.02205 |
| Sonnet 5.5 | $0.00011 | $0.01103 |
| Haiku 4.5 | $0.00006 | $0.00551 |
Grade A, and why
RBT Manual Testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RBT Manual Testing
Description
Đây là Master Skill cho mọi tác vụ sinh manual test cases. Skill cung cấp 2 chế độ hoạt động (modes) để phù hợp với mọi quy mô yêu cầu:
| Mode | Khi nào dùng | Thời gian |
|---|---|---|
| QUICK | Module đơn giản, cần TC nhanh, requirements rõ ràng | 1 lượt (không chờ user) |
| FULL RBT | Module phức tạp, cần phân tích rủi ro, hệ thống lớn | 6 bước tuần tự (có checkpoint) |
Nguyên tắc cốt lõi:
- Human Strategy: Con người xác định chiến lược, mức độ rủi ro và tiêu chuẩn
- AI Execution: AI thực hiện phân tích, viết TCs và rà soát lỗ hổng
- Human Verification: Con người kiểm tra lại kết quả trước khi chốt
When to Use
Sử dụng skill này khi:
- Sinh manual test cases từ requirements / user stories
- Phân tích requirements để phát hiện ambiguity
- Phân rã hệ thống thành modules / features
- Xây dựng traceability matrix
- Áp dụng Risk-Based Testing (đánh giá rủi ro cho test cases)
- Chuẩn hóa test cases sang bảng Markdown (Jira/Excel format)
- Sinh test cases nhanh từ requirements đơn giản
KHÔNG sử dụng skill này khi:
- Cần sinh automation code → dùng
qa_automation_engineer - Cần inspect DOM / sinh locator → dùng
ui_debug_agent/smart_locator_agent - Chỉ cần sinh test data → dùng
test_data_generator
Mode Routing — Cách chọn mode
Agent tự động chọn mode dựa trên trigger keywords và ngữ cảnh:
→ Mode QUICK
Kích hoạt khi:
- User dùng workflow
/generate_testcases_from_requirements - User nói: "sinh test cases nhanh", "tạo TC từ requirement này", "viết test cases cho form..."
- Requirements đã rõ ràng, scope nhỏ (1 module / 1 tính năng)
- User không yêu cầu phân tích rủi ro hay quy trình bài bản
→ Mode FULL RBT
Kích hoạt khi:
- User dùng workflow
/generate_manual_testcases_rbt - User nói: "quy trình 6 bước", "phân tích RBT", "sinh test cases đầy đủ", "sinh bộ TC bài bản"
- Scope lớn (nhiều modules, hệ thống phức tạp)
- User yêu cầu Traceability Matrix hoặc đánh giá Risk Level
- Requirements chưa rõ ràng, cần phân tích Ambiguity
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 419 lines · 55 tokens per session scan A 084077d983f8
RBT Manual Testing is a skill published in the GitHub repository anhtester/antigravity-testing-kit (147 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 5,513 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
shaft-developer
Use when starting any SHAFT testing task to select exactly one lifecycle, implementation, or tool specialist before doing the work.
shaft-test-case-design
Use when designing reviewable test cases or scenarios with traceability, data, steps, expected results, techniques, priorities, and boundary coverage.
shaft-accessibility-testing
Use when testing web or mobile accessibility for WCAG conformance, keyboard and focus behavior, semantics, errors, or user impact.
shaft-api-testing
Use when implementing or repairing SHAFT.API tests for HTTP requests, authentication, payloads, schemas, responses, contracts, or service workflows.
shaft-automated-test-authoring
Use when implementing or repairing executable SHAFT Java tests for web, mobile, API, database, CLI, TestNG, JUnit, or Cucumber behavior.
shaft-change-verification
Use when edited SHAFT Java needs a reuse plan, preview diff, guardrail check, approved application, focused test, and evidence-backed verdict.