菜单
Gemini-native organization-wide CI recovery — scans all open PRs, classifies failures, and applies remediation with 2M+ token grounding
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Gemini-native AI slop detection — scans all repos for AI-generated anti-patterns with 2M+ token grounding
Gemini-native autonomous close-out orchestrator — 20-step pipeline with whole-project grounding and hard gates
Gemini-native morning investigation pipeline — syncs repos, checks infra, and dispatches parallel probes with 2M+ token grounding
Gemini-native self-healing CI pipeline — autonomous fix loop with whole-project grounding
Gemini-native per-PR CI monitoring — polls GitHub Actions, auto-fixes introduced failures, and reports state with 2M+ token grounding
Gemini-native end-of-day reconciliation — snapshot baselines and verify boundaries across all repos with 2M+ token grounding
| name | ci-recovery |
| description | Gemini-native organization-wide CI recovery — scans all open PRs, classifies failures, and applies remediation with 2M+ token grounding |
| capability | skill.ci_recovery |
| node_name | node_skill_ci_recovery_orchestrator |
| dot_color | 208 |
Organization-wide CI recovery pipeline that polls all open PRs across OmniNode-ai repositories, leveraging Gemini's massive context window to accurately classify failures and orchestrate automated remediation.
flaky_test: Identified through known-flaky history or recent re-run pass.infra_issue: Runner timeouts, network glitches, or connection refusals.config_error: Missing dependencies, lock file mismatches, or env var drift.real_failure: Genuine regressions requiring code changes.gh run rerun for flaky or infra issues.ci-fix-pipeline for configuration errors or real failures.--repos: Comma-separated repo names to scan.--dry-run: Classify failures without applying fixes.--max-fixes: Hard cap on fix attempts per cycle.