.claude/skills/screen-automation-engineerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
强大的屏幕理解与控制,并创建可维护流程
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/screen-automation-engineerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/screen-automation-engineerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/screen-automation-engineerRuntime, 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 @xiaozs-com/screen-automation-engineerclawhub inspect @xiaozs-com/screen-automation-engineer --version 1.2.6This 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.
sha256:35d6984c2af2ed14fd23df1c4e13c630ed272c50fbfa84cd396cbb2ba89ad682agents/openai.yamlreferences/agent-bridge.mdreferences/browser-enhancement-testing.mdreferences/current-task.mdreferences/user-guide.mdreferences/workflow-agent-phases.mdreferences/workflow-lifecycle.mdreferences/workflow-standard.mdreferences/workflow-trust.mdscripts/resolve_cli.ps1scripts/resolve_cli.shscripts/workflow_dev.ps1scripts/workflow_dev.shskill-card.mdSKILL.mdVersion 1.2.6 refocuses the skill around safer, more practical screen tasks and reusable workflow delivery. - Clarifies when to handle a task directly versus build a reusable workflow, with guidance for using visual, accessibility, browser, and external-tool capabilities. - Strengthens user-in-the-loop safeguards for credentials, authentication, payments, and other high-risk actions. - Adds workflow references for Agent phases, lifecycle, trust boundaries, current-task operations, and user guidance. - Updates workflow development and delivery guidance, including validation, bounded recovery, stopping behavior, and first-run instructions. - Removes the obsolete skill-card.md file.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:c33b47d4655ddd066788912f862eb34c6261e1a4d294529af58bdafb4c33bb5dsha256:570167e7b19152a99ed7c8d9710353eb454f4f0405e3e5e5f18b3093e22586a4sha256:5699f025ecfb1fab9cbe4c9ba70a7a5d3e6f8a72514931d8c7183ef6137c68a8sha256:7ef54288e42a63046c76ac3759b684ced895280f7244bcdb3b98b94438782ea1sha256:2df301deae07f5d65ae83e9e6e0587caff188222eb867a226f7f4a2a38c459b9