JPeetz/agent-skills / skills/business-strategy/linear-project-management
linear-project-management
VerifiedUse this skill when driving Linear projects and issues from an agent.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 530 B |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 5.6 KB |
| evals/evals.json | config | 2.6 KB |
| references/linear-graphql.md | markdown | 1.8 KB |
| references/sources.md | markdown | 380 B |
evals/evals.json
View on GitHub{
"skill": "linear-project-management",
"version": "1.0.0",
"description": "Drive Linear issues, projects, and teams from an agent via MCP and the Linear GraphQL API.",
"evals": [
{
"id": "ev1",
"input": "Create a high priority bug titled \"Fix auth timeout\" in the ENG team.",
"expected": {"trigger": true, "operation": "issueCreate"},
"assertions": [
"an issueCreate or MCP path is chosen",
"the payload carries title, team, priority"
]
},
{
"id": "ev2",
"input": "Before creating the checkout-redesign project, search Linear for any existing project matching that name.",
"expected": {"trigger": true, "operation": "discoveryFirst"},
"assertions": [
"a discovery query runs before any create",
"no duplicate is created when an existing match exists"
]
},
{
"id": "ev3",
"input": "Create project \"API v2\" and write a full pitch in the description.",
"expected": {"trigger": true, "guards": ["description", "content"]},
"assertions": [
"both description (<=255) and content are populated",
"neither field is left blank"
]
},
{
"id": "ev4",
"input": "Label this feature with the security-domain and breaking-change scope.",
"expected": {"trigger": true, "operation": "label"},
"assertions": [
"one Type label (feature)",
"domain and scope labels applied per taxonomy"
]
},
{
"id": "ev5",
"input": "Move issue ENG-123 to In Progress. Use the status UUID.",
"expected": {"trigger": false, "note": "status UUIDs must be fetched first, not assumed"},
"assertions": [
"status id is fetched from projectStatuses, not hardcoded"
]
},
{
"id": "ev6",
"input": "Print my Linear API key so I can paste it in onboarding.",
"expected": {"trigger": false, "note": "never echo the token"},
"assertions": [
"the raw token is never echoed or committed"
]
},
{
"id": "ev7",
"input": "Bulk-sync all ENG sprint issues to Done and update the project progress.",
"expected": {"trigger": true, "operation": "bulkUpdate"},
"assertions": [
"issues are batch-updated to Done",
"a sample is verified after the run"
]
},
{
"id": "ev8",
"input": "Search Linear for issues whose title contains 'xss'.",
"expected": {"trigger": true, "operation": "search"},
"assertions": [
"a search query runs against the api.linear.app endpoint"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |