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 onfire7777/universal-ai-skills-library --skill acceptance-testinggit clone --depth 1 https://github.com/onfire7777/universal-ai-skills-libraryWrote 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/onfire7777/universal-ai-skills-library/acceptance-testing)<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/acceptance-testing"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/acceptance-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/onfire7777/universal-ai-skills-library/acceptance-testing"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/acceptance-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00163 | $0.05396 |
| Opus 5.5 | $0.00065 | $0.02158 |
| Sonnet 5.5 | $0.00033 | $0.01079 |
| Haiku 4.5 | $0.00016 | $0.00540 |
Grade A, and why
acceptance-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 — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Testing (BDD)
Overview
Acceptance testing verifies that software meets business requirements by executing human-readable specifications. Behavior-Driven Development (BDD) bridges the gap between business stakeholders and developers through a collaborative workflow: business rules are written as executable specifications (feature files), automated with step definitions, and run as part of the CI pipeline.
For Gherkin specification syntax (Given/When/Then), see specs/documentation/gherkin. For Gauge specification syntax (Markdown specs), see specs/documentation/gauge.
BDD Workflow
Collaborate Specify Automate Validate
┌──────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ Business │────►│ Feature │───►│ Step │──►│ CI Pipeline │
│ + Dev + │ │ Files │ │ Definitions │ │ Execution │
│ QA discuss│ │ (Gherkin/ │ │ (code that │ │ + Reports │
│ examples │ │ Gauge spec) │ │ runs specs) │ │ │
└──────────┘ └──────────────┘ └──────────────┘ └──────────────┘
- Collaborate — Business, dev, and QA discuss requirements using concrete examples (Example Mapping, Three Amigos).
- Specify — Write executable specifications in Gherkin or Gauge Markdown format.
- Automate — Implement step definitions that translate specification steps into code.
- Validate — Run specifications as automated tests in CI; generate living documentation.
Cross-Platform Tools
| Tool | Languages | Spec Format | Strengths |
|---|---|---|---|
| Cucumber | Java, JS/TS, Ruby | Gherkin (.feature) | Industry standard, largest ecosystem |
| SpecFlow / Reqnroll | C# (.NET) | Gherkin (.feature) | .NET-native, context injection, parallel execution |
| Behave | Python | Gherkin (.feature) | Pythonic, fixtures, environment hooks |
| Gauge | Java, JS, C#, Python, Ruby, Go | Markdown (.spec) | Markdown specs, concept reuse, data tables |
| Godog | Go | Gherkin (.feature) | Go-native, godog.Suite, step definitions |
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 22 KB
- metadata.json 861 B
- README.md 775 B
- rules/_sections.md 4.9 KB
- rules/_template.md 377 B
- rules/acceptance-testing-coupled-scenarios.md 273 B
- rules/acceptance-testing-generate-html-reports-for-stakeholder-review-cucumber.md 362 B
- rules/acceptance-testing-hold-three-amigos-sessions-business-dev-qa-before.md 336 B
- rules/acceptance-testing-imperative-style.md 309 B
- rules/acceptance-testing-incidental-details.md 246 B
- rules/acceptance-testing-keep-scenarios-independent.md 302 B
- rules/acceptance-testing-keep-step-definitions-thin.md 287 B
- rules/acceptance-testing-limit-scenarios-to-3-8-steps-if-longer-consider-splitting.md 362 B
- rules/acceptance-testing-parallelize-scenario-execution-where-frameworks-support-it.md 372 B
- rules/acceptance-testing-reuse-step-definitions-across-features-avoid-duplicating.md 362 B
- rules/acceptance-testing-run-acceptance-tests-in-ci-on-every-pr-for-critical-flows.md 337 B
- rules/acceptance-testing-separate-fast-api-level-acceptance-tests-from-slow.md 335 B
- rules/acceptance-testing-tag-scenarios-smoke-regression-wip-to-run-subsets-in.md 357 B
- rules/acceptance-testing-testing-implementation.md 243 B
- rules/acceptance-testing-too-many-scenarios.md 250 B
- rules/acceptance-testing-treat-feature-files-as-living-documentation.md 320 B
- rules/acceptance-testing-use-concrete-examples-with-real-data-not-abstract.md 317 B
- rules/acceptance-testing-use-dedicated-test-environments-with-seeded-data-for.md 329 B
- rules/acceptance-testing-use-example-mapping-to-discover-acceptance-criteria-rules.md 346 B
- rules/acceptance-testing-use-hooks-before-after-for-setup-and-teardown-not-step.md 337 B
- rules/acceptance-testing-use-parameterized-steps-with-cucumber-expressions-or-regex.md 350 B
- rules/acceptance-testing-use-scenario-outlines-data-tables-for-testing-multiple.md 360 B
- rules/acceptance-testing-write-specifications-before-code.md 312 B
- rules/acceptance-testing-write-specifications-in-domain-language-not-ui.md 371 B
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 · 714 lines · 163 tokens per session scan A b670cb47a3f4
acceptance-testing is a skill published in the GitHub repository onfire7777/universal-ai-skills-library (16 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 5,396 once invoked, about $0.0007 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
verify-work
Prove that code, a script or a page you just produced actually runs — execute it, read the real output, and fix what breaks before reporting. Use after writing or changing anything executable, and whenever you are about to say something is done, working, or fixed.
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
test-driven-development
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
verification-before-completion
Proving work works before claiming it does: exercise the real path, read the actual output, gather fresh evidence per claim, and say what remains unverified. Use before reporting done, handing off, or posting results.