菜单
Use when configuring, auditing, or debugging rtime-assistant agent tooling, MCP client snippets, tool installation status, validation plans, context-lane routing, or read-only runtime snapshots for AI-agent control surfaces.
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
Use when auditing, reviewing, or planning Obsidian/Zotero citation workflows for the rtime `brain` library, especially citekey crosswalks, BibTeX coverage, Zotero URI clues, Obsidian wikilinks, DocPack citation anchors, or Mac/orangepi read-only citation review.
Use when auditing, selecting samples, building, validating, or reviewing DocPack outputs for the rtime `brain` knowledge library, especially learning materials, PDFs, Office files, citation mapping, Obsidian-readable Markdown, or Mac/orangepi DocPack workflows.
Use when auditing, indexing, reviewing, or planning display modules for the rtime `brain` library, especially Obsidian vault signals, Zotero/Better BibTeX links, DocPack citation readiness, SQLite/BM25 index readiness, or Mac/orangepi read-only library workflows.
Use when inspecting or troubleshooting the rtime-assistant runtime, Feishu/Lark bridge candidate, run logs, queue/access/output modules, Docker production Compose checks, systemd templates, or Mac/orangepi runtime diagnostics without changing live services.
Use when inspecting, planning, or reviewing rtime assistant reminders, schedulers, notifications, workflow automation, timer health, or automation run-log surfaces without sending messages or mutating runtime state.
Use when planning dynamic context unlocking, building ContextUnlockPlan or Context Pack skeletons, explaining why context should be loaded, routing requests across brain/rtime-hub/runtime evidence, or designing why-context behavior without reading sensitive data.
| name | rtime-agent-control |
| description | Use when configuring, auditing, or debugging rtime-assistant agent tooling, MCP client snippets, tool installation status, validation plans, context-lane routing, or read-only runtime snapshots for AI-agent control surfaces. |
Use this skill for read-only agent control-plane diagnostics. The stable
command surface is the rtime-agent-control CLI package in
packages/rtime-agent-control.
From <repo-root> on Mac or
<repo-root> on orangepi, read:
AGENTS.mddocs/agent-control-mcp.mddocs/tooling-packaging.mddocs/tooling-installation.mddocs/assistant-profile-policy.mddocs/logging-and-audit.mdInstall locally when needed:
scripts/install-rtime-tooling.sh --tool rtime-agent-control --profile mac
python -m pip install -e packages/rtime-agent-control
rtime-agent-control doctor
Read-only checks:
rtime-agent-control tooling --repo-root <repo-root>
rtime-agent-control config-render --repo-root <repo-root> --tool rtime-agent-control
rtime-agent-control validation-plan --repo-root <repo-root> --module agent-control
rtime-agent-control context-plan "configure agent MCP debugging" --repo-root <repo-root>
rtime-agent-control runtime-snapshot --repo-root <repo-root>
printf '{"jsonrpc":"2.0","id":1,"method":"tools/list"}\n' | rtime-agent-control-mcp
For package, MCP, skill, plugin, or installer changes, run:
python -m py_compile packages/rtime-agent-control/src/rtime_agent_control/*.py
PYTHONPATH=packages/rtime-agent-control/src python -m pytest tests/test_rtime_agent_control_cli.py tests/test_rtime_agent_control_mcp.py -q
scripts/validate-codex-plugin.py plugins/rtime-agent-control
bash -n plugins/rtime-agent-control/scripts/rtime-agent-control-mcp.sh
bash -n scripts/install-rtime-tooling.sh
git diff --check