Uses the Linear MCP to gather issue requirements and task scope for coding work.
Install
mkdir -p .claude/skills/linear-tonkeeper && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17512" && unzip -o skill.zip -d .claude/skills/linear-tonkeeper && rm skill.zipInstalls to .claude/skills/linear-tonkeeper
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Retrieve Linear task context via Linear MCP for implementation work. Use when the developer needs requirements, scope, or acceptance criteria from a ticket.Key capabilities
- →Retrieve Linear task context for implementation work
- →Collect context using read-focused Linear MCP tools
- →Extract problem statements, scope, and acceptance criteria
- →Summarize findings for an implementation plan
- →List Linear issues, projects, teams, and users
- →Search Linear documentation and list comments
How it works
The skill uses the Linear MCP server to gather issue context for developers. It collects data using read-focused Linear MCP tools and then extracts relevant information.
Inputs & outputs
When to use linear
- →Get task acceptance criteria
- →Fetch ticket requirements
- →List project issues
- →Retrieve issue status
About this skill
Linear
Overview
This skill uses the Linear MCP server to gather issue context for developers implementing tasks. It is context-oriented and read-only by default.
Prerequisites
- Linear MCP server must be connected and accessible via OAuth
- Confirm access to the relevant Linear workspace and teams
Required Workflow
Follow these steps in order. Do not skip steps.
Step 0: Set up Linear MCP (if not already configured)
If any MCP call fails because Linear MCP is not connected, pause and set it up:
- Add the Linear MCP:
codex mcp add linear --url https://mcp.linear.app/mcp
- Enable remote MCP client:
- Set
[features] rmcp_client = trueinconfig.tomlor runcodex --enable rmcp_client
- Set
- Log in with OAuth:
codex mcp login linear
After successful login, the user must restart Codex. Finish the answer and instruct them to restart and retry.
Windows/WSL note: If connection errors appear on Windows, configure Linear MCP via WSL:
{"mcpServers":{"linear":{"command":"wsl","args":["npx","-y","mcp-remote","https://mcp.linear.app/sse","--transport","sse-only"]}}}
Step 1
Clarify the implementation goal and scope for the task. Confirm relevant identifiers (issue ID, team key, project if needed).
Step 2
Use read-focused Linear MCP tools to collect context:
get_issue,list_issues,list_my_issueslist_issue_statuses,list_issue_labelsget_project,list_projectsget_team,list_teams,list_userslist_documents,get_document,search_documentationlist_comments,list_cycles
Step 3: Build implementation context
From retrieved data, extract and present:
- Problem statement
- Scope and out-of-scope boundaries
- Acceptance criteria / definition of done
- UX, API, and technical constraints
- Dependencies, risks, and blockers
- Open questions and assumptions that must be clarified before coding
Step 4
Summarize findings for the developer and map them to an implementation plan and test plan.
Guardrails
- Do not create or update Linear entities unless the user explicitly asks.
- Do not run project-management workflows (triage, planning, redistribution) by default.
- Prefer read calls first; if write actions are requested later, confirm intent and scope before proceeding.
When not to use it
- →When the user explicitly asks to create or update Linear entities
- →When running project-management workflows by default
- →When write actions are requested without confirmation
Prerequisites
Limitations
- →Does not create or update Linear entities by default
- →Does not run project-management workflows by default
- →Requires user confirmation for write actions
How it compares
This skill automates the extraction and presentation of Linear task context, which would otherwise require manual navigation and synthesis of information from the Linear interface.
Compared to similar skills
linear side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| linear (this skill) | 0 | 21d | No flags | Beginner |
| task-master | 22 | 5mo | Review | Intermediate |
| agile-product-owner | 10 | 7mo | Review | Beginner |
| writing-plans | 15 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by tonkeeper
View all by tonkeeper →You might also like
task-master
sfc-gh-dflippo
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and maintain organized development workflows across features and branches.
agile-product-owner
davila7
Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity tracking. Use for story writing, sprint planning, stakeholder communication, and agile ceremonies.
writing-plans
obra
Use when you have a spec or requirements for a multi-step task, before touching code
feature-design-assistant
davila7
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.
task-coordination-strategies
wshobson
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
github-project-management
ruvnet
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning