What does this skill do, and when should you use it?
This Codex skill provides a structured way to read, create, and update Linear issues, projects, and team workflows. It connects through the Linear MCP server and requires OAuth access to the relevant workspace, teams, and projects. Its workflow emphasizes gathering context and confirming identifiers before making changes. It is suited to issue triage, sprint planning, documentation audits, release planning, and workload balancing.
Uses Linear MCP tools to list, retrieve, and search issues; inspect statuses, labels, teams, users, projects, documents, comments, and cycles; and create or update issues, projects, labels, and comments. It also describes workflows for sprint planning, bug triage, documentation audits, release planning, dependency analysis, automated status updates, smart labeling, workload balancing, and retrospectives.
- A project manager needs to review open issues for a team, select work by priority, and create a new cycle.
- An engineering or product team needs to identify critical or high-priority bugs and move the most important items into progress.
- A documentation owner needs to search existing documentation and open issues for missing or outdated content.
- A release manager needs to create a release project, define milestones, and generate related issues.
- A team lead needs to group active issues by assignee, identify overloaded contributors, and rebalance work.
How do you install this skill?
- Core operation depends on Linear MCP, OAuth, and an external network service; verify workspace permissions, data boundaries, and mainland-China reachability before use.
- External writes such as creating or updating issues, projects, labels, or comments lack an explicit per-operation confirmation and rollback procedure.
- The supplied skill material does not clearly specify the license, version, changelog, or maintenance responsibility.
- Shell / CLI
- Network access
- Local filesystem
- MCP Server
Linear MCP serverOAuth access to a Linear workspace
In Codex, run $skill-installer linear to install the curated skill. Restart Codex after installation so it can load the new skill. The README does not document additional manual installation steps.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/openai/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/.curated/linear" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Plan this week’s sprint for the Engineering team by reviewing open issues by priority and creating a new cycle.
Connect the Linear MCP server through OAuth and confirm access to the relevant workspace, teams, and projects. Then provide a concrete request such as “Plan this week’s sprint for the Engineering team by reviewing open issues by priority and creating a new cycle.” Specify the team or project and, when relevant, priority, labels, cycle, and due dates. The skill is designed to read context first and perform creation or updates afterward.
What are this skill's strengths and limitations?
- Covers issues, projects, teams, documentation, comments, labels, and cycles.
- Requires context gathering and identifier confirmation before write operations.
- Includes concrete workflows for sprint planning, bug triage, release planning, and workload balancing.
- Encourages batching related changes and accounting for API rate limits.
- Requires a connected Linear MCP server, OAuth login, and appropriate workspace permissions.
- The skill does not provide Linear access itself; available data depends on the user's Linear account.
- The README marks the repository as deprecated and points users to the OpenAI Plugins repository.
- The source provides no test suite, platform coverage details, or individual skill license evidence.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Linear Workflow Manager this page ✓ OpenAI · Official | 51 · Use with care | ★ 28k | 4mo ago | — |
| Linear Claude Skill | 55 · Use with care | ★ 135 | 3mo ago | MIT |
| Linear CLI Skill | 48 · Use with care | ★ 16 | 12mo ago | — |
| Obsidian CLI Knowledge Transport | 48 · Use with care | ★ 16k | 1mo ago | MIT |
| Contract Evidence Analyzer ✓ Anthropic · Official | 55 · Use with care | ★ 425 | 1mo ago | — |
How did FollowSkills review this skill?
The evidence requires Linear MCP access through OAuth and calls for clarification of goals, scope, teams, and projects, with read-before-write sequencing. It does not clearly require confirmation for each write, define least privilege, address sensitive data, provide rollback, or fully disclose data flows, so points are deducted.
The ordered workflow, prerequisites, troubleshooting notes, and some recovery guidance are coherent. However, this is a static review with no committed test suite or CI coverage, and tool availability, key-path reproduction, and abnormal-input behavior are unverified, so the score is conservatively limited.
The audience and Linear issue, project, and team scenarios are fairly clear, with multiple practical workflows. Trigger semantics are broad, non-fit boundaries and Chinese-language support are absent, and the core function depends entirely on an overseas Linear MCP service whose mainland-China reachability is uncertain, so points are deducted.
The documentation has useful sections for overview, prerequisites, ordered workflow, tools, practical workflows, and troubleshooting. The individual skill license is unknown, and versioning, changelog, maintenance ownership, and update path are not clearly documented, so points are deducted.
The skill describes actionable workflows for issue management, project planning, bug triage, and documentation audits, which could reduce repetitive work. It provides no representative outputs, execution results, or comparative evidence, so direct usability and completeness receive only a moderate static score.
The skill files, agent configuration, and repository documentation are auditable, and the MCP endpoint is explicit. There is no third-party execution evidence, test result, or independent reproduction material, so key capabilities remain primarily documentary claims and points are deducted.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →