alibaba/Agent Skill Eval (skill-up)
Run skill-up behavioral evals on your Agent Skills in CI — across claude_code, codex, qodercli, and qwen_code engines.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| engine | Agent engine: claude_code / codex / qodercli / qwen_code. Leave empty to let the repo's eval.yaml declare it. | no | "" |
| model | Passed to `skill-up run --model` when non-empty; otherwise the eval config / CLI default is used. | no | "" |
| provider | Resolves base-url from a built-in table (public: dashscope). Ignored when base-url is set. | no | "" |
| api-key | Model credential. engine non-empty -> routed to ANTHROPIC_API_KEY / OPENAI_API_KEY / QODER_PERSONAL_ACCESS_TOKEN; engine empty -> passed via `skill-up --api-key`. Always source this from a GitHub secret. | no | "" |
| base-url | Model API endpoint (public). Defaults to the agent CLI's own public endpoint when empty. | no | "" |
| open-sandbox-api-key | OPENSANDBOX_API_KEY; only needed when evals use the opensandbox environment. | no | "" |
| skill-target | Skill directory or eval config path, resolved against the checked-out repo root. | no | . |
| skill-up-version | skill-up version. Ignored when the image already ships skill-up (the default). | no | latest |
| skill-up-command | The skill-up command itself; must start with `skill-up`. | no | skill-up run |
| parallelism | Passed to `--parallelism` when non-empty (1-256). | no | "" |
| agent-install-command | Optional custom install command, for a custom image missing a target engine CLI. | no | "" |
Outputs
| name | description |
|---|---|
| exit-code | skill-up exit code (0 = all evals passed). |
| report-dir | Directory with the JSON / JUnit / HTML reports, relative to the workspace (e.g. skill-up-workspace), so host steps can consume it. |