send-to-linear by casper-studios/casper-marketplace
npx skills add https://github.com/casper-studios/casper-marketplace --skill send-to-linear将非结构化输入转化为结构清晰的 Linear 工单。
按以下顺序查找团队配置(首次匹配即生效):
~/.claude/skills/send-to-linear/references/config.local.json~/.agents/skills/send-to-linear/references/config.local.jsonreferences/config.json(捆绑的默认配置,相对于此技能文件)使用找到的第一个 .local 配置文件。否则回退到捆绑的 config.json。
如果任何位置都不存在 .local 文件 并且 捆绑配置中的必填字段(team、)为空,:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
default_assignee未找到本地配置文件。捆绑的
references/config.json包含空的默认值,并且会在本技能更新时被覆盖。请在以下路径之一创建本地覆盖文件:
~/.claude/skills/send-to-linear/references/config.local.json~/.agents/skills/send-to-linear/references/config.local.json
复制捆绑的
references/config.json作为起点,并填写您的团队、项目、负责人、标签和约定。
工单模板遵循相同的模式:
~/.claude/skills/send-to-linear/references/ticket-template.local.md~/.agents/skills/send-to-linear/references/ticket-template.local.mdreferences/ticket-template.md(捆绑的默认模板)该模板很少需要自定义,因此如果只存在捆绑版本,则不会提示。
接受以下任意组合:
mcp__fireflies__* 工具)、粘贴的文本或文件如果用户的输入模糊或不完整,请在继续之前提出一个澄清性问题。不要过度询问。
特别针对 Fireflies 记录:同时获取摘要(fireflies_get_summary)和完整记录(fireflies_get_transcript)。使用摘要进行主题识别,使用完整记录进行细节提取。
对于短输入(<5K 字符):在主上下文中直接提取。
对于长输入(>5K 字符,例如完整的通话记录):启动并行子代理,每个主要主题或时间段一个,以提取:
使用 references/ticket-template.md 中的格式,写入 .claude/scratchpad/linear-tickets-YYYY-MM-DD.md。
每个包含来自源材料的真实示例的工单必须包含该示例的逐字记录 — 不要通过总结来模糊具体细节。
对于简短/简单的输入,跳过此步骤。对于通话记录或长篇 Slack 线程:
启动一个验证子代理,该代理读取完整的源材料和起草的工单,然后生成一个差距列表:
使用发现的任何差距更新草稿。
停止。 告知用户文件已准备就绪,并在 Linear 中创建任何内容之前,等待明确的指令。
用户可以重组、合并、拆分、重命名、添加注释,或告知您跳过某些事项。在继续之前,将所有反馈应用到草稿板文件。
使用“设置”中的解析顺序读取配置,然后:
mcp__linear__list_teams — 解析团队 IDmcp__linear__list_issue_labels — 解析标签 IDmcp__linear__list_projects — 解析项目 ID(如果已配置)mcp__linear__list_cycles 附带 type: "current" — 解析当前周期(如果 assign_to_current_cycle 为 true)使用 mcp__linear__create_issue 创建每个已批准的工单:
team: 来自配置project: 来自配置assignee: 来自配置cycle: 当前周期编号state: 来自配置的 default_statuslabels: 与工单的 Labels 字段匹配title: 来自工单description: 完整的工单正文,使用 Markdown 格式links: 源链接(如果可用,例如 Fireflies 记录 URL、Slack 永久链接)将创建的工单标识符报告给用户。
每周安装数
77
仓库
GitHub 星标数
9
首次出现
12 天前
安全审计
已安装于
cline77
github-copilot77
codex77
kimi-cli77
gemini-cli77
cursor77
Turn unstructured input into well-structured Linear tickets.
Look for team configuration in this order (first match wins):
~/.claude/skills/send-to-linear/references/config.local.json~/.agents/skills/send-to-linear/references/config.local.jsonreferences/config.json (bundled defaults, relative to this skill file)Use the first .local config found. Otherwise fall back to the bundled config.json.
If no .local file exists anywhere AND the bundled config has empty required fields (team, default_assignee), stop and prompt the user :
No local config found. The bundled
references/config.jsonhas empty defaults and will be overwritten whenever this skill updates.Create a local override at one of these paths:
~/.claude/skills/send-to-linear/references/config.local.json~/.agents/skills/send-to-linear/references/config.local.json
Copy the bundled
references/config.jsonas a starting point and fill in your team, project, assignee, labels, and conventions.
Same pattern for the ticket template:
~/.claude/skills/send-to-linear/references/ticket-template.local.md~/.agents/skills/send-to-linear/references/ticket-template.local.mdreferences/ticket-template.md (bundled default)The template rarely needs customization, so no prompt if only the bundled version exists.
Accept any combination of:
mcp__fireflies__* tools), pasted text, or a fileIf the user's input is ambiguous or incomplete, ask one clarifying question before proceeding. Do not over-interrogate.
For Fireflies transcripts specifically: fetch both the summary (fireflies_get_summary) and full transcript (fireflies_get_transcript). Use the summary for topic identification, the full transcript for detail extraction.
For short input (<5K chars): extract directly in the main context.
For long input (>5K chars, e.g. full call transcripts): launch parallel subagents, one per major topic or time segment, to extract:
Write to .claude/scratchpad/linear-tickets-YYYY-MM-DD.md using the format from references/ticket-template.md.
Every ticket with a real-world example from the source MUST include that example verbatim — do not summarize away specifics.
Skip for short/simple input. For call transcripts or long Slack threads:
Launch a verification subagent that reads the full source material and the drafted tickets, then produces a gap list:
Update the draft with any gaps found.
STOP. Tell the user the file is ready and wait for explicit instruction before creating anything in Linear.
The user may restructure, merge, split, rename, add notes, or tell you to skip items. Apply all feedback to the scratchpad file before proceeding.
Read config using the resolution order from Setup, then:
mcp__linear__list_teams — resolve team IDmcp__linear__list_issue_labels — resolve label IDsmcp__linear__list_projects — resolve project ID (if configured)mcp__linear__list_cycles with type: "current" — resolve current cycle (if assign_to_current_cycle is true)Create each approved ticket with mcp__linear__create_issue:
team: from configproject: from configassignee: from configcycle: current cycle numberstate: from config default_statuslabels: matched from ticket's Labels fieldtitle: from ticketdescription: full ticket body in markdownlinks: source link if available (e.g. Fireflies transcript URL, Slack permalink)Report created ticket identifiers back to the user.
Weekly Installs
77
Repository
GitHub Stars
9
First Seen
12 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
cline77
github-copilot77
codex77
kimi-cli77
gemini-cli77
cursor77
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
40,000 周安装
React Email JSON 渲染器 - 将 JSON 规范转换为 HTML/纯文本邮件 | Vercel Labs
277 周安装
Auto-Skill 自进化知识系统:AI助手自动化技能管理与知识库构建指南
271 周安装
阿里云产品API发现工具 - 自动化收集OpenAPI元数据与技能规划
275 周安装
lesson经验提取存储工具 - 从对话中自动捕获技术陷阱与决策原则
280 周安装
AI写作痕迹去除工具 - 让AI生成文字更自然有人味 | 中文优化指南
282 周安装
小红书自动化发布与互动工具 - RedBookSkills 实现图文视频一键发布、内容检索与数据管理
282 周安装