Linear Skill for Claude Code

A Claude Code skill for managing Linear issues, projects, and teams, combining MCP tools, a TypeScript SDK, and direct GraphQL API access.

Agent skills

Visit website github.com

Linear Skill for Claude Code is a Claude Code skill for working with Linear issues, projects, and teams. It combines simple operations through a Linear MCP server, more complex operations through TypeScript SDK scripts, and direct GraphQL queries for advanced cases.

It adds a label taxonomy for consistent categorization and agent routing, high-level commands for initiatives and status updates, sub-issue management, mandatory discovery checks before creating new issues or projects to avoid duplicates, and image uploads to Linear's storage.

The skill checks its own configuration on first use and reports what is missing, and it can pre-compile its CLI for faster startup, falling back to running TypeScript directly when it has not been built.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies