菜单
Manually consult GLM-5.2 (Z.ai) via the `zai` CLI — fast by default, `--deep` for reasoning. The user-invoked `/zai:glm` surface; complementary to Claude, never a replacement. For autonomous cross-checks use the `ask-glm` skill instead.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/terrylica/cc-skills --skill glm命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
user wants to create a macOS Calendar event with sound alarms and paired Reminders, schedule a meeting, RSVP to an invitation, or set reminders.
Park a draft message/text in macOS Notes for the operator to review and edit, then read it back before acting (e.g. before sending to a real person). Notes is the source of truth (AppleScript CRUD, iCloud-synced, provenance-stamped with the Claude Code session UUID); Stickies is a best-effort view-only desktop mirror. Use whenever you draft something a human should confirm/edit before it is sent or committed — messages, replies, announcements, anything outbound. TRIGGERS - park this draft, park the message, hold this draft, let me edit first, draft for my approval, save to notes for review, read back the draft.
Programmatic Firecrawl usage via the public API, academic paper routing, recursive deep research, and raw corpus persistence.
基于 SOC 职业分类
正在显示 SKILL.md
| name | glm |
| description | Manually consult GLM-5.2 (Z.ai) via the `zai` CLI — fast by default, `--deep` for reasoning. The user-invoked `/zai:glm` surface; complementary to Claude, never a replacement. For autonomous cross-checks use the `ask-glm` skill instead. |
| argument-hint | [--deep] [--effort max] [--file PATH] <question> |
| allowed-tools | Bash |
| disable-model-invocation | true |
/zai:glm)Self-Evolving Skill: This skill improves through use. If the
zaiinvocation drifted, a flag changed, or the passthrough broke, fix this file immediately — don't defer. Only update for real, reproducible issues.
Run the zai CLI to consult GLM-5.2 with the user's arguments, then relay the answer
(note it's GLM's, not Claude's).
zai chat $ARGUMENTS
--deep/--effort, keep them (extended reasoning). Otherwise it runs fast.--file <path> (GLM-5.2 accepts ~1M input tokens).zai websearch "<query>" / zai read <url> instead.zai plugin's references/CAPABILITIES.md.This is the manual surface (
disable-model-invocation: true) — it fires only when the user types/zai:glm. When Claude should consult GLM on its own initiative, that's theask-glmskill, not this one.
After running this skill, reflect before closing the task:
zai call fail or a flag not behave as documented? Fix the command or the
argument-hint here immediately, and note it in the zai plugin's references/CAPABILITIES.md./zai:glm when ask-glm or zai websearch fit better? Sharpen
this skill's description so the right surface triggers next time.Do NOT defer. The next invocation inherits whatever you leave behind.