jira-api
Skill1 starsChanged 2 months agoMITView on GitHub
Jira 票務操作:查票、開票、改狀態、編輯、留言。透過 CLI 腳本操作 Jira Cloud(curl + REST API 為 fallback)。 當使用者提到 Jira、票、issue、transition、comment,或提到任何 Jira 票號格式(如 `WEB-1234`,依專案而定、不限特定 key)時使用此 skill。
2 other projects use a version of this.
Adopted by
Most recently taken up by
- anthropics/claude-tag-pluginstheir own version, first seen Oct 13, 2026
- BlakeHastings/claude-code-artifactstheir own version, first seen Jun 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- anthropics/claude-tag-plugins★ 60same name
- BlakeHastings/claude-code-artifacts★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- codebase-inventorySkill
- code-commentsSkill
- codex-goal-writerSkill
- generate-specSkill
- git-commitSkill
- glab-mr-reviewSkill
- glab-mrSkill
- handoff-auditSkill
- linear-task-lifecycleSkill
- reject-and-redoSkill
- setup-serenaSkill
- setup-skill-syncSkill
- subagent-goSkill
- wtSkill
The file
Files
Jira 操作 Skill
透過 CLI 腳本或 curl + Jira Cloud REST API v3 操作 Jira。不需要 MCP server。
優先使用 CLI 腳本
腳本路徑:這個 skill 目錄下的 scripts/jira.sh。
優先用腳本操作,腳本失敗才 fallback 到 curl。
JIRA=<this-skill-dir>/scripts/jira.sh
$JIRA my # 查我的未完成票
$JIRA search "project = WEB" 10 # JQL 搜尋(可指定 maxResults)
$JIRA get WEB-1169 # 取得單一 issue
$JIRA assign WEB-1553 WEB-1554 WEB-1555 # 批量指派給自己
$JIRA transitions WEB-1169 # 查可用狀態轉換
$JIRA transition WEB-1169 Done # 改狀態(支援名稱或 ID)
$JIRA comment WEB-1169 "留言內容" # 加留言
$JIRA create WEB 任務 "標題" --parent WEB-1272 --desc "描述" # 開票
$JIRA edit WEB-1169 --summary "新標題" --desc "新描述" # 編輯環境設定
Credentials 存在 ~/.zshrc 的環境變數中,腳本會自動讀取:
| 變數 | 用途 |
JIRA_EMAIL | 登入帳號 |
JIRA_TOKEN | API Token |
JIRA_BASE | Jira Cloud URL(如 https://tintint.atlassian.net) |
預設值
以下是範例專案的設定,套用到別的 Jira 站台或專案時,換成該專案實際的專案 key,不要假設
WEB通用。
- 預設專案 key:
WEB(使用者可指定其他專案) - 預設 maxResults:
20
描述支援 Markdown
--desc 的內容會透過 build_adf 轉成 Jira ADF。直接寫 Markdown 就會正確 render,不需要手組 ADF JSON。
Block 語法:
#~######→ heading(1~6 級)-/*開頭 → 無序列表1.2.開頭 → 有序列表``` lang ... ```→ fenced code block(可帶語言)- 空行分段
Inline 語法:
`code`→ inline code mark**bold**→ 粗體- URL → 自動 link mark
@username→ Jira mention(會自動查 accountId)
範例:
$JIRA create WEB 漏洞 "標題" --parent WEB-757 --desc "## 現象
頁面 \`/xxx\` 冒出 error。
## 根因
- \`format.ts:37\` 的 \`new Date()\` 不一致
- SSR 與 hydrate 時 now 差距造成 text mismatch
## 修正方向
1. 改成接受 \`now\` 參數
2. 用 \`useEffect\` 延後注入"限制:
- Bold 不能跨行
- Inline code 不能包含反引號
- 不支援表格、引言、圖片、task list
- 需要更複雜的結構時,fallback 到 curl 手組 ADF
Fallback:curl 直接呼叫
如果腳本異常,改用 curl + REST API v3 直接呼叫。載入環境變數、API 端點、Issue Types、Transition ID 對照表都在 references/curl-fallback.md——只有腳本失敗才需要讀那份文件,正常操作不會用到。
操作原則
- 查詢前確認範圍:如果使用者沒指定專案,預設用
WEB(這是範例站台的預設值,換專案時要換成該站台實際的專案 key) - 建立前確認內容:開票前先跟使用者確認 summary、type、parent(如果是子任務)
- 改狀態前先查 transitions:不同狀態下可用的 transition 不同,一律先查再改
- 結果用表格呈現:查票結果用 Markdown 表格,方便閱讀
- 錯誤處理:如果 curl 回傳非 2xx,把錯誤訊息顯示給使用者
- 搜尋要廣不要窄:
text ~只搜 summary + description 的文字,很容易漏掉子任務。搜尋某個功能領域的票時,應該用多條件聯集(OR),例如同時搜關鍵字、parent issue、場景代號(C2/C4/C6 等),而不是只靠單一text ~ - 子任務要分開查:
$JIRA search預設不包含子任務(issueType in (子任務, "Bug Sub-task"))。查某個功能或 epic 的完整待辦時,要額外執行一次子任務查詢:# 查故事/任務層 $JIRA search 'assignee=currentUser() AND text ~ "關鍵字" AND status NOT IN (完成,Done)' # 查子任務層(用 parent in (...)) $JIRA search 'assignee=currentUser() AND issueType in (子任務,"Bug Sub-task") AND project=WEB AND status NOT IN (完成,Done)'
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

