linear-finish-install

tjcages/linear · Agent Skill

完成Linear追蹤的設定，撰寫規則以始終啟用並檢查Linear MCP的驗證。

總覽

發布者	tjcages社群
儲存庫	tjcages/linear ↗
技能資料夾	`linear-finish-install`
星	10
附帶檔案	5
授權	MIT
最近更新	2026年7月29日
連結	技能原始碼 ↗ · 儲存庫 ↗

Mozgi 檢查

我們在技能檔案中發現的內容。詳細資訊需訂閱。

安全性

低風險 · 未發現明顯風險 — 完整報告會顯示細節

相容性

僅含說明 — 適用於多數代理

相似技能

找到 144 個相似技能

訂閱另含

安裝

技能就是一個含 SKILL.md 的資料夾。選擇你的代理，在專案根目錄的終端機（macOS、Linux 或 Windows 的 Git Bash）執行指令。

把提示貼到 Claude、Codex 或其他助理：它會自行檢查並安裝技能。

Install the “linear-finish-install” skill from mozgi.io (https://mozgi.io/skills/tjcages-linear-finish-install/) for me.

1. Download the archive: https://mozgi.io/skills/tjcages-linear-finish-install/download
   If it fails, take the skill folder from the source: https://github.com/tjcages/linear/tree/main/skills/linear-finish-install
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “linear-finish-install” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/linear-finish-install/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/tjcages/linear.git /tmp/linear
mkdir -p .claude/skills
cp -r /tmp/linear/skills/linear-finish-install .claude/skills/linear-finish-install

重新啟動 Claude Code — 技能就會出現在清單中，手動呼叫：/linear-finish-install。要套用到所有專案，請放在 ~/.claude/skills。

git clone --depth 1 --branch main https://github.com/tjcages/linear.git /tmp/linear
mkdir -p .agents/skills
cp -r /tmp/linear/skills/linear-finish-install .agents/skills/linear-finish-install

Codex 會從目前資料夾往上到儲存庫根目錄，在 .agents/skills 中尋找技能；用 /skills 或 $linear-finish-install 呼叫。所有專案：~/.agents/skills。

git clone --depth 1 --branch main https://github.com/tjcages/linear.git /tmp/linear
mkdir -p .cursor/skills
cp -r /tmp/linear/skills/linear-finish-install .cursor/skills/linear-finish-install

Cursor 啟動時會載入技能；在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案：~/.cursor/skills。

git clone --depth 1 --branch main https://github.com/tjcages/linear.git /tmp/linear
mkdir -p .gemini/skills
cp -r /tmp/linear/skills/linear-finish-install .gemini/skills/linear-finish-install

任務符合時，Gemini CLI 會提議啟用技能，由你確認。所有專案：~/.gemini/skills。

技能檔案

5 個檔案下載 ZIP

安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。

SKILL.md 內容

作者原文 · 唯讀

Finish Linear tracking install

Chat: RESPONSE.md ↗. Auth: AUTH.md ↗. Snippet: ALWAYS_ON.md ↗. Optional weekly health: AUTOMATION.md ↗.

Install is complete when always-on is loaded and Linear MCP auth works. Same skills + same SoT assumption on every harness. Cursor Automation is optional.

Do these in order. Lead with the next action each turn.

1. Always-on (required)

Cursor: list user rules. If no rule titled linear-tracking (always-on), add one with cursor_dialog (item=rule, scope=user, action=add, title + ALWAYS_ON.md body). If it exists, skip.

Claude Code / Codex / file-based: ensure ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md, and/or ~/.agents/AGENTS.md contain the ALWAYS_ON block between markers:

<!-- linear-tracking-always-on -->
…ALWAYS_ON.md body…
<!-- /linear-tracking-always-on -->

Idempotent: replace the block if markers exist; else append.

2. Linear MCP (required)

Call list_teams (or get_user).

Fail → AUTH.md steps for this agent; stop after giving links.
Pass → continue.

Useful links:

Cursor MCP: Cursor Settings → MCP ↗
Linear MCP docs: Linear MCP ↗
Claude connectors: claude.ai settings ↗ or /mcp in Claude Code

3. Monitor Automation (optional — Cursor only)

If this is Cursor and the user wants a weekly digest: open Automations (open_automation) and point at AUTOMATION.md ↗. Default schedule Monday 7:00 AM local (convert cron to UTC — see AUTOMATION.md).

Non-Cursor: skip. They can run /linear-monitor anytime.

Do not block “install complete” on Automation.

4. Report

Restate:

1. Always-on: done / already present / failed (where)

2. Linear auth: ok / needs OAuth

3. Install: complete if 1+2 ok — Automation offered / skipped / deferred

One next action only.

常見問題

linear-finish-install 技能有什麼用途？

完成Linear追蹤的設定，撰寫規則以始終啟用並檢查Linear MCP的驗證。

如何安裝 linear-finish-install？

打開本頁的「安裝」區塊並選擇你的代理 — Claude Code、Codex、Cursor 或 Gemini CLI：那裡有把技能資料夾複製到正確位置的現成指令。也可以複製「透過助理」分頁中的提示，讓助理自行檢查並安裝技能。

linear-finish-install 適用哪些 AI 模型？

技能是純 Markdown 指示（Agent Skills 格式），因此 linear-finish-install 適用任何讀取 SKILL.md 的代理：Claude Code、Codex、Cursor、Gemini CLI、GitHub Copilot、OpenCode 等。只有在任務符合技能描述時，模型才會載入指示。

linear-finish-install 是免費的嗎？

此技能由 tjcages 公開發布，採用 MIT 授權。技能本身免費 — 你只需向 AI 供應商支付實際使用的 token 費用。

安裝技能安全嗎？

技能是代理會遵循的指示，安裝前請閱讀 SKILL.md 及相關檔案。技能資料夾中的腳本只有在代理執行時才會運行 — 留意它的動作，不要授予多餘權限。

技能和 MCP 伺服器或外掛有何不同？

MCP 伺服器或外掛為模型提供新工具 — 會執行並回傳結果的程式碼。技能提供的是知識與流程：如何處理任務、要遵循哪些步驟、好的成果長什麼樣子。它不需要伺服器或 API 金鑰。

總覽