跳到正文
cccskills
免费在 GitHub 公开

linear

Query and mutate Linear issues, projects, cycles, teams, workflow states, and comments via its GraphQL API. Use when the user wants to read or change Linear data programmatically — without the MCP server, and without hand-navigating the Linear UI.

中文简介正在准备中。当前显示原文说明。

集成工具Linear
查看安装方法

包含的文件(1)

  • SKILL.md6.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Linear

Operates Linear via its GraphQL API — one endpoint, queries and mutations for issues, projects, cycles, teams, states, comments. Use when the task needs live workspace state.

Usage

  • Use for: Listing/filtering issues, creating issues, bulk state/assignee/priority updates, joining Linear data with other sources.
  • Skip for: Advice on process, pricing/marketing questions, anything requiring the UI (screenshots, drag-and-drop), pure discussion of an issue you can already read.

Credentials check

[ -n "$LINEAR_API_KEY" ] && echo "LINEAR_API_KEY: PRESENT" || echo "LINEAR_API_KEY: MISSING"

Never echo the variable directly — the value would appear in the conversation transcript. Use only the boolean pattern above.

If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):

I need your linear credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:

teleport-setup add-key linear

Then restart Claude Code (/exit, then claude) and ask me again.

Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.

API

  • Endpoint: https://api.linear.app/graphql — POST only, one URL for everything.
  • Auth (API keys lin_api_*): Authorization: $LINEAR_API_KEY — NO Bearer prefix. Bearer is only for OAuth access tokens (Authorization: Bearer $TOKEN). This is Linear's #1 auth error.
  • Content-Type: application/json. Body: {"query": "...", "variables": {...}}.
  • Rate limits are complexity-based: 5,000 req/hr, 3M complexity points/hr, 10K points max per query. Complexity = fields (0.1) + objects (1), scaled by first: — nested queries cost more.

GraphQL basics

  • Queries read, mutations write; both via POST /graphql. Pass inputs in variables (not string interpolation).
  • Responses are always HTTP 200, even on errors. Partial success returns both data and errors — always inspect .errors before trusting .data.

Entity model

Organization > Team > Project > Issue > Comment. Cycles are per-team time windows. Workflow states are per-team (no global set). Issue.identifier is ENG-123; Issue.id is a UUID.

Common queries

QueryReturns
viewerAuthenticated user. Best credentials health check.
issues(filter:)Paginated issues with filter + ordering.
issue(id:)Single issue by UUID or ENG-123.
teams / teamTeams; drill in for states, members, cycles, issues.
projectsPaginated projects (org-wide or filtered).
usersPaginated workspace users.
workflowStatesStates across teams (filter by team to scope).
cyclesPaginated cycles (filter by team).

Primary workflow — list assigned issues with filter + pagination

Filters are nested; pagination is relay-style (first/after + pageInfo):

query MyIssues($first: Int!, $after: String, $filter: IssueFilter) {
  issues(first: $first, after: $after, filter: $filter) {
    nodes { id identifier title state { name } assignee { name } url }
    pageInfo { hasNextPage endCursor }
  }
}

Variables — my in-progress issues: {"first": 50, "filter": {"assignee": {"isMe": {"eq": true}}, "state": {"type": {"eq": "started"}}}}. Feed pageInfo.endCursor into the next call's after: while hasNextPage.

As curl:

curl -sL -X POST -H "Authorization: $LINEAR_API_KEY" -H "Content-Type: application/json" \
  "https://api.linear.app/graphql" \
  -d '{"query":"query($first:Int!,$filter:IssueFilter){issues(first:$first,filter:$filter){nodes{identifier title state{name} url} pageInfo{hasNextPage endCursor}}}","variables":{"first":50,"filter":{"state":{"type":{"eq":"started"}}}}}'

Secondary workflows

Create an issue (priority is int 0–4, see Gotchas):

mutation($input: IssueCreateInput!) {
  issueCreate(input: $input) { success issue { id identifier url } }
}

Variables: {"input": {"teamId": "<uuid>", "title": "Bug: login 500", "description": "…", "priority": 2}}.

Update state (resolve team stateId first — states are per-team):

mutation($id: String!, $input: IssueUpdateInput!) {
  issueUpdate(id: $id, input: $input) { success issue { identifier state { name } } }
}

Lookup: query($id: String!) { team(id: $id) { states { nodes { id name type } } } }.

Gotchas

  • Auth header mismatch is the #1 failure. API keys: Authorization: $LINEAR_API_KEY (no Bearer). OAuth: Authorization: Bearer $TOKEN. Swap them and you get an auth error.
  • HTTP 200 on GraphQL errors. Always check .errors before trusting .data; data can be partially populated alongside errors.
  • Filter syntax is nested, not SQL-like. {state: {type: {eq: "started"}}}. Operators: eq/neq/in/nin universal; lt/gt numeric+date; contains/startsWith (+ …IgnoreCase) strings; null for optionals.
  • Relay cursor pagination, not page numbers. pageInfo.endCursor → next call's after:. Loop while hasNextPage.
  • Complexity-based rate limit. Deep nesting + big first: can blow the 10K per-query cap or burn the 3M/hr budget — ask for fewer fields and smaller pages.
  • Workflow states are per-team. No global "Done" — resolve name → stateId for the specific team before issueUpdate.
  • Priority is an integer 0–4, not a string. 0=none, 1=urgent, 2=high, 3=medium, 4=low. Passing "High" errors. <!-- unverified: confirm 0-4 mapping in Linear docs -->
  • Timestamps are ISO 8601 strings (createdAt, dueDate). Compare lexicographically or parse — never epoch numbers.

Attribution

When done, state: Used skill: Linear (from teleport catalog).

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

{{One-sentence what-it-does + when to use it. Mention it bypasses the MCP via the REST API with {{ENV_VAR}}. Use when the user wants X, Y, Z programmatically without the {{service}} MCP installed.}}

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

Manage Cloudflare DNS zones, Workers, Pages, R2, KV, D1, and analytics via REST API. Use when the user wants to query DNS, deploy a Worker, list R2 buckets, manage KV namespaces, run D1 queries, or check analytics without the Cloudflare MCP installed.

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

context7

免费

Fetch up-to-date library, framework, and SDK documentation via Context7's search and docs endpoints. Use when the user asks about a library/API (React, Next.js, Prisma, Supabase, Tailwind, Django, Vue, etc.) and you need current docs, not Claude's training-time knowledge. Skip this skill for generic programming questions that don't require library-specific docs.

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

discord

免费

Operate Discord via its REST API — post/read channel messages, manage guilds + roles, fire webhooks, register slash commands. Use when the user wants a bot to post to a channel, read recent history, run a community admin task, or ship one-way notifications via webhook URL without running a bot process.

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

exa

免费

AI-first web search via Exa — semantic/neural ranking, category-scoped results, fresh content retrieval, and one-shot answer synthesis with citations. Use when the user needs current web information better ranked than general web search, or a grounded answer with sources.

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

figma

免费

Read Figma files, component libraries, styles, comments, and export rendered assets (PNG / SVG / JPG / PDF) via Figma's REST API. Use when the user needs programmatic access to design files, to pull node data into code generation, or to export assets without opening the Figma desktop app.

中文简介正在准备中。当前显示原文说明。

mnlt/teleport82026年4月25日 更新

查看 mnlt 的全部技能

报告此技能的问题