.claude/skills/mochi-agent-eval-kitRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Evaluate recorded agent replies against explicit required, forbidden and exact text expectations without calling a model.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/mochi-agent-eval-kitRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/mochi-agent-eval-kitRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/mochi-agent-eval-kitRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @hznetnewpower/mochi-agent-eval-kitclawhub inspect @hznetnewpower/mochi-agent-eval-kit --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:ec374ab8bfc8293e5f57b83bd6ad0f68b414bbe049e08e12cec2c0aa8bafa0b1LICENSEreferences/input.mdreferences/zh-CN.mdsamples/request.jsonscripts/requirements.txtscripts/run.pyscripts/runtime.pyscripts/task.pyskill-card.mdSKILL.mdtests/case.jsontests/smoke.py- Introduces deterministic evaluation of recorded agent replies against required, forbidden, and exact-text expectations, without calling a model. - Adds an offline Python helper that creates reports and artifacts in the workspace while protecting selected inputs and rejecting paths outside it. - Documents input handling, realistic and held-out test cases, and limits on claims about live execution. - Includes five bundled smoke tests for sample behavior, invalid input, CLI artifacts, workspace boundaries, and non-overwrite behavior.