From bee
Generates contextual manual verification steps after builds — provides commands, URLs, and actions for frontend, backend, CLI, greenfield, or library changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bee:try-it-yourselfThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
After showing the execution summary, always append a contextual "Try it yourself" block that tells the developer how to manually verify the changes. This is user education — help the developer see what was built with their own eyes.
After showing the execution summary, always append a contextual "Try it yourself" block that tells the developer how to manually verify the changes. This is user education — help the developer see what was built with their own eyes.
Generate the verification steps from the context summary and the spec. Pick the right type based on what was built:
When context-gatherer flagged "UI-involved: yes":
When new endpoints, services, or business logic were added:
orders table — you should see the new status column")When greenfield or first slice:
[test command] to confirm."Keep it short — 2-4 concrete steps, not a tutorial. Use the developer's actual project paths and commands.
**Try it yourself:**
1. `npm run dev` → open http://localhost:5173
2. Press Cmd+N — a new note should appear in the sidebar
3. Type something in the editor, wait 2 seconds — you should see "Saved" in the status bar
npx claudepluginhub incubyte/ai-plugins --plugin beeVerifies code changes by running the app and observing runtime behavior at the user-facing surface (CLI, API, GUI, etc.). Skips tests and typechecking.
Runs parallel specialized agents to verify implementations, run tests (unit/e2e/integration/perf/LLM), grade quality (0-10 scale), and suggest improvements. Use before merging.
Enables autonomous testing and verification mode where Claude thoroughly tests, iterates, and validates its own work across frontend, backend, CLI, and build tools.