Interact with the Rudder control plane through the `rudder` CLI to manage tasks, approvals, comments, Library files, and organization skills during heartbeats. Use for Rudder coordination only, not for the domain work itself.
Review Rudder agent work. Use for review/第一性原理/PM review of Codex sessions, PRs, commits, UI, releases, regressions, or agent outcomes. Separates author-claimed proof from reviewer-verified proof. For functional or UI reviews, run the real Rudder scenario with Browser or Computer Use when available instead of accepting from diffs.
Route Rudder development work when a request is ambiguous or spans lifecycle stages: requirements, advisor/product analysis, UI design, implementation, verification, review, commit/push, and handoff. Use for stage selection, reviewer gates, aborted-run recovery, component-lab work, scoped performance optimization, and risky dirty-worktree cleanup. Keep thin: if the prompt clearly names release, UI polish, run/debug, local preview, data path, Desktop recovery, PR preview, mock data, or review-only work, use the narrower maintainer skill directly.
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles shared work files, memory decay, weekly synthesis, and file-based recall. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing shared work notes.
Maintain and execute Rudder releases across npm, GitHub Releases, and Desktop portable assets. Use this skill whenever the user asks about 发版, release, publishing to npm, canary/stable promotion, GitHub Release assets, Desktop distribution, `npx @rudderhq/cli@latest start`, `npx @rudderhq/cli start`, broken npm `latest` dist-tags, full Desktop install smoke tests, GitHub Release API/rate-limit failures, version bumps, rollback, obsolete canary GitHub Release/tag cleanup after stable promotion, first-time package bootstrap, npm token-based fallback publishing, or release workflow failures. Prefer this skill for both planning and hands-on release operations in the Rudder repository, even when the user only asks "现在要做什么" or "帮我发版".
Debug and analyze Rudder agent run transcripts, run logs, and execution traces. Use this skill whenever the user mentions: - "debug run", "分析 run", "查看 run" - "为什么这个 agent 执行失败", "run 出错了" - "transcript 怎么看", "run 的日志" - a run ID or run ID prefix - "最近 30 个 run", "recent runs", "run 质量", "分析这个 org 最近运行" - agent execution, tool calls, stdout/stderr 调试 Prefer this skill whenever the user wants to understand what happened during one run or a recent batch of runs, even if they only have a partial run ID, org name, agent/runtime, or timeframe. Do not default to raw SQL first; use Rudder's run-intelligence path first, then fall back only if needed.
Execute screenshot-driven Rudder UI polish and narrow visible interaction fixes. Use when the user points at a Rudder screen or screenshot and asks to adjust density, alignment, badges, labels, cards, menus, hover affordances, empty states, redundant pages, onboarding steps, or other narrow small-to-medium UI behavior, especially with Chinese prompts like "这里有点丑", "对齐一下", "去掉这个页面", "改成这个 UI", "先说说/优化一下", or "弄个截图给我看". Also use for narrow UI fixes even when the user mentions an advisor/reviewer skill, unless they explicitly ask for reviewer agents, repeated review rounds, or an acceptance gate. Prefer build-advisor for pure advice with no implementation request, and advisor-review-loop-maintainer for high-stakes proposal plus reviewer gates.
Create new agents in Rudder through the `rudder` CLI with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.