{"id":19367,"plugin_id":"plugins_6a97f99a25c08191a853f2805bcc6efb","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:31.817Z","digest":"06cbafd37680917ddd590667e4b6cac755518d3080eef1f03304647faaf5e9f2","against":null,"payload":{"description":"AI DevKit · Check local AI DevKit readiness and run setup only when status shows onboarding or harness integration gaps.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":269}],"name":"ai-devkit-setup","skill_md_contents":"---\nname: ai-devkit-setup\ndescription: AI DevKit · Check local AI DevKit readiness and run setup only when status shows onboarding or harness integration gaps.\n---\n\n# AI DevKit Setup\n\nUse this skill when a user wants to onboard AI DevKit, prepare a harness, repair local AI DevKit integration, or check whether setup is needed.\n\nKeep the workflow status-driven and simple. Prefer the installed `ai-devkit` binary; if it is unavailable, use `npx ai-devkit@latest`.\n\n## Execution Notes\n\n- Under filesystem sandboxing, run `ai-devkit status --json` and any `ai-devkit setup` command outside the sandbox. These commands inspect and modify host-level agent configuration; sandboxed runs can produce false failures or block setup writes, especially for integrations that execute harness commands and access paths like `~/.pi/agent`.\n\n## Workflow\n\n1. Run readiness first:\n\n   ```bash\n   ai-devkit status --json\n   ```\n\n2. Identify failed or warning checks that setup can fix. Setup covers local integrations like hooks, built-in skills, and session tracking for `codex`, `pi`, and `claude`; it does not fix auth, missing package managers, or host tools requiring user installation.\n\n3. Run the narrowest setup command, for example:\n\n   ```bash\n   ai-devkit setup --agent codex,pi,claude\n   ```\n\n   If the user asked for broad onboarding and several supported harnesses need setup, `ai-devkit setup` is acceptable.\n\n4. Re-run `ai-devkit status --json` and report what changed plus any remaining manual actions.\n\n## Boundaries\n\n- Do not run setup before checking status unless the user explicitly asks to force setup.\n- Do not claim setup is complete without a fresh status check from this session.\n- Do not modify secrets, auth tokens, or unrelated harness config manually. Point the user to the failing status item instead.\n- Ask before destructive cleanup or replacing existing user-managed configuration.\n- Keep output concise: status command, setup command if run, final readiness, and remaining user actions.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}