linear-discipline
tjcages/linear · Agent Skill
在開發過程中,透過查詢-先於-建立、生命週期更新和封閉迴圈紀律來保持Linear tracking的誠實性。
前往安裝 ↓總覽
| 發布者 | |
|---|---|
| 儲存庫 | tjcages/linear ↗ |
| 技能資料夾 | linear-discipline |
| 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-discipline” skill from mozgi.io (https://mozgi.io/skills/tjcages-linear-discipline/) for me. 1. Download the archive: https://mozgi.io/skills/tjcages-linear-discipline/download If it fails, take the skill folder from the source: https://github.com/tjcages/linear/tree/main/skills/linear-discipline 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-discipline” 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-discipline/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-discipline .claude/skills/linear-discipline
重新啟動 Claude Code — 技能就會出現在清單中,手動呼叫:/linear-discipline。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-discipline .agents/skills/linear-discipline
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-discipline 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-discipline .cursor/skills/linear-discipline
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-discipline .gemini/skills/linear-discipline
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 discipline (always-on)
Chat rules: RESPONSE.md ↗. Auth before Linear calls: AUTH.md ↗.
Detect tracking
Tracked if the repo has a “Linear tracking” (or equivalent) section in CLAUDE.md, AGENTS.md, or .cursor/rules/* that names team + project.
Skipped if .linear-tracking-skip exists at repo root.
If tracked
Follow the protocol written in-repo:
1. Search before create.
2. Non-trivial work → file/update an issue in the named project + milestone.
3. Backlog → In Progress at start → Done only when shipped.
4. Close the loop before session end (state and/or comment).
5. Prefer Linear’s generated branch names.
Before any Linear tool call: Step 0 auth.
If untracked and not skipped (soft nudge — 1B)
Ask once, one line, no preamble:
> This repo isn’t tracked in Linear. Set it up now? (~10–20 min)
- Yes → hand off to
linear-setup(do not bootstrap inline without that skill’s gates). - No → create
.linear-tracking-skipat repo root; stay quiet next time. - Never auto-create Linear projects or issues from a nudge alone.
- Never nudge from Automation /
linear-monitorruns.
If skipped
Stay quiet about setup. Still use Linear MCP for explicit user requests.
Out of scope
Full bootstrap → linear-setup. Rescue/audit → linear-sync. Health digest → linear-monitor.
常見問題
linear-discipline 技能有什麼用途?
在開發過程中,透過查詢-先於-建立、生命週期更新和封閉迴圈紀律來保持Linear tracking的誠實性。
如何安裝 linear-discipline?
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-discipline 適用哪些 AI 模型?
技能是純 Markdown 指示(Agent Skills 格式),因此 linear-discipline 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-discipline 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。