{"id":68486,"plugin_id":"plugins_6adf87c4f2648191a3db16e324db4c36","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-28T13:17:38.089Z","digest":"565858e56829136672f34957f2be1fee49dd05e91034c8bdf0749806f0f491ad","against":null,"payload":{"description":"Set up OmniSkill after installation or check which skill workflows this host can execute. Use for first-run onboarding and capability troubleshooting, not for a general coding environment installation.\n","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":262}],"name":"setup","skill_md_contents":"---\nname: setup\ndescription: >\n  Set up OmniSkill after installation or check which skill workflows this host\n  can execute. Use for first-run onboarding and capability troubleshooting,\n  not for a general coding environment installation.\n---\n\n# Set up OmniSkill\n\n1. Identify the intended job: create, audit, improve, port, or package a skill.\n   Reuse the user's current request when it already says this.\n2. Check which host capabilities are actually exposed: files, search, patch,\n   shell, Python, and external documentation. Do not probe credentials or assume\n   a signed-in account. A skills-only install requires no MCP connection or key.\n3. Read `../host-workspace-operator/SKILL.md` if files are involved. Confirm the\n   source and output scope; preserve unrelated work and existing authorization.\n4. Report which operations can run here and which require a later host session.\n   Without execution tools, design and static review can continue; tests remain\n   unverified. Without source access, ask for the specific source needed.\n5. Continue to `../omni-skill/SKILL.md` with one concrete task. Offer examples\n   only when no task was supplied: turn an SOP into a skill, audit a skill's\n   activation boundary, or adapt a skill for another host.\n\nDo not install the optional CLI, dependencies, hooks, or background services as\npart of setup unless the user requests them. Inspect commands before executing\nbundled scripts. Never report installation or a passing test without host output.\n\nComplete when the capability limits and next supported task are clear. Carry\nthose facts into the router so onboarding does not repeat on each step.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}