linear-methodology
tjcages/linear · Agent Skill
Route Linear 透過設定、同步、監控、維護的方法論來追蹤工作,並保持專案資料的正確性。
前往安裝 ↓總覽
| 發布者 | |
|---|---|
| 儲存庫 | tjcages/linear ↗ |
| 技能資料夾 | linear-methodology |
| 星 | 10 |
| 附帶檔案 | 7 |
| 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-methodology” skill from mozgi.io (https://mozgi.io/skills/tjcages-linear-methodology/) for me. 1. Download the archive: https://mozgi.io/skills/tjcages-linear-methodology/download If it fails, take the skill folder from the source: https://github.com/tjcages/linear/tree/main/skills/linear-methodology 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-methodology” 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-methodology/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-methodology .claude/skills/linear-methodology
重新啟動 Claude Code — 技能就會出現在清單中,手動呼叫:/linear-methodology。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-methodology .agents/skills/linear-methodology
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-methodology 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-methodology .cursor/skills/linear-methodology
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-methodology .gemini/skills/linear-methodology
任務符合時,Gemini CLI 會提議啟用技能,由你確認。所有專案:~/.gemini/skills。
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Linear Methodology
> Keep Linear useful by making it reflect the project, the repository, and the work actually happening.
What it does
- Anchors tracking to the project's North Star and real roadmap.
- Sets up or repairs projects, milestones, issues, labels, and dependencies.
- Reconciles Linear with repository evidence instead of trusting stale tickets.
- Keeps active work current and closes the loop when work ships.
How it works
1. Read RESPONSE.md ↗ for concise, action-first chat.
2. Read AUTH.md ↗, then verify Linear access before any call.
3. Route the request:
- Set up, backfill, or start tracking →
linear-setup - Sync, audit, or rescue a board →
linear-sync - Check project health →
linear-monitor - Finish installation →
linear-finish-install
4. Apply linear-discipline throughout the session.
5. Use METHODOLOGY.md ↗ when the routed skill needs deeper guidance.
Default ambiguous requests like “set up Linear tracking” to linear-setup.
常見問題
linear-methodology 技能有什麼用途?
Route Linear 透過設定、同步、監控、維護的方法論來追蹤工作,並保持專案資料的正確性。
如何安裝 linear-methodology?
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-methodology 適用哪些 AI 模型?
技能是純 Markdown 指示(Agent Skills 格式),因此 linear-methodology 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-methodology 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。