$npx -y skills add Geeksfino/openskills --skill openskills-e2e-test-runbookRun deterministic OpenSkills end-to-end validation across runtime tests and example agents, then report tool calls, activation behavior, and regressions.
| 1 | # OpenSkills E2E Test Runbook |
| 2 | |
| 3 | Use this skill for confidence checks before merging runtime, tooling, or example-agent changes. |
| 4 | |
| 5 | ## Test Layers |
| 6 | |
| 7 | 1. Runtime regression tests |
| 8 | 2. Sandbox-focused tests |
| 9 | 3. Example-agent behavior checks |
| 10 | 4. Optional binding smoke tests |
| 11 | |
| 12 | ## Baseline Commands |
| 13 | |
| 14 | ```bash |
| 15 | cargo test -p openskills-runtime |
| 16 | ``` |
| 17 | |
| 18 | Example-agent checks (from example directories): |
| 19 | |
| 20 | ```bash |
| 21 | npm install |
| 22 | npm start "What skills are available?" |
| 23 | npm start "Create a new skill called 'note-taker'." |
| 24 | ``` |
| 25 | |
| 26 | ## E2E Expectations |
| 27 | |
| 28 | - Skills discover successfully. |
| 29 | - Skill activation occurs for matching prompts. |
| 30 | - Tool calls align with intent (activation, file reads/writes, script runs). |
| 31 | - No unexpected sandbox failures. |
| 32 | |
| 33 | ## Reporting Format |
| 34 | |
| 35 | - What was run |
| 36 | - What passed |
| 37 | - What failed |
| 38 | - Repro command for each failure |
| 39 | - Suggested next fix |