Agent skill

MCP PR Review

by tacticlaunch in tacticlaunch/mcp-linear

Review pull requests in mcp-linear for MCP-specific risks. An agent skill from tacticlaunch/mcp-linear.

MITAuto-check passedDevelopment

Install MCP PR Review

skills CLI
$ npx skills add tacticlaunch/mcp-linear --skill mcp-pr-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tacticlaunch/mcp-linear mcp-pr-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tacticlaunch/mcp-linear.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/mcp-pr-review .claude/skills/mcp-pr-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-pr-review
GitHub stars
147
Token cost
~214 tokens
SKILL.md length
94 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Review pull requests in mcp-linear for MCP-specific risks. An agent skill from tacticlaunch/mcp-linear.

  • Works in 7 steps: Input schema and type guard alignment. → Output schema and normalized service… → Nullable field handling, especially for… → …
  • Tasks that involve Pull requests
  • SKILL.md covers Review focus and Expected output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

MCP PR Review is an agent skill from tacticlaunch/mcp-linear. Review pull requests in mcp-linear for MCP-specific risks. Use this when a branch changes LinearService behavior, tool contracts, registrations, or tests.

Its SKILL.md is about 210 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests and MCP servers. It works with Model Context Protocol. The repository describes itself as: MCP server that enables AI assistants to interact with Linear project management system through natural language, allowing users to retrieve, create, and update issues, projects… The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve MCP servers

Example prompts

  • “/mcp-pr-review”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Input schema and type guard alignment.
  2. Output schema and normalized service output alignment.
  3. Nullable field handling, especially for update and clear operations.
  4. Missing handler or index registration.
  5. Missing TOOLS.md updates.
  6. Direct GraphQL added without a clear SDK rationale.
  7. Missing tests for negative validation paths, nullable updates, or SDK fallback behavior.

What it can do on your machine

Read from SKILL.md and the folder at commit cde0c4f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP PR Review loads about 214 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 94 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~214

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tacticlaunch/mcp-linear at commit cde0c4f, republished under its MIT licence (© tacticlaunch). 94 words, ~214 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-pr-review/SKILL.md (or your agent's skills folder).
name
mcp-pr-review
description
Review pull requests in mcp-linear for MCP-specific risks. Use this when a branch changes LinearService behavior, tool contracts, registrations, or tests.

Use this review workflow for mcp-linear pull requests.

Review focus

  1. Input schema and type guard alignment.
  2. Output schema and normalized service output alignment.
  3. Nullable field handling, especially for update and clear operations.
  4. Missing handler or index registration.
  5. Missing TOOLS.md updates.
  6. Direct GraphQL added without a clear SDK rationale.
  7. Missing tests for negative validation paths, nullable updates, or SDK fallback behavior.

Expected output

  • Findings first.
  • Order findings by severity.
  • Include exact file references.
  • If no issues are found, say so explicitly and call out any remaining live-test risk.

© tacticlaunch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/mcp-pr-review of tacticlaunch/mcp-linear.

Open the folder on GitHubat commit cde0c4f

Compare with similar skills

MCP PR Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP PR Review this skilltacticlaunch/mcp-linear147—~214Automated safety check: PassMIT
Review PRPrefectHQ/fastmcp28k—~3.1kAutomated safety check: PassApache-2.0
ObservalObserval/Observal4.3k—~2.2kAutomated safety check: PassApache-2.0
Code Reviewimbenrabi/Financial-Modeling-Prep-MCP-Server150—~2.6kAutomated safety check: PassApache-2.0
PR Reviewconfluentinc/mcp-confluent167—~4.6kAutomated safety check: NotesMIT
Fix IssuePrefectHQ/fastmcp28k—~842Automated safety check: PassApache-2.0

Similar skills

  • Review PR

    PrefectHQ/fastmcp

    Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict.

    28k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Observal

    Observal/Observal

    A skill your agent uses when starting any task the organization may already have an approved skill, prompt, MCP server, or Agent for: reviewing code, a commit, a diff, or a pull request; writing…

    4.3k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Review

    imbenrabi/Financial-Modeling-Prep-MCP-Server

    Review a PR or working diff against this repo's intent layer (the AGENTS.md hierarchy), toolception pitfalls, and core invariants.

    150 GitHub stars~2.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • PR Review

    confluentinc/mcp-confluent

    Reviews pull requests for the Confluent MCP server. An agent skill from confluentinc/mcp-confluent.

    167 GitHub stars~4.6k tokensUpdated today
    DevelopmentAuto-check: notes
  • Fix Issue

    PrefectHQ/fastmcp

    Carry a selected FastMCP bug from reproduction through a scoped fix, compatibility review, validation, and a monitored pull request.

    28k GitHub stars~842 tokensUpdated today
    DevelopmentAuto-check passed
  • Code Review

    sbroenne/mcp-windows

    Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime.

    108 GitHub stars~1.6k tokensUpdated today
    DevelopmentAuto-check passed

More from tacticlaunch/mcp-linear

  • Add MCP Tool

    tacticlaunch/mcp-linear

    Add or update an MCP tool in the mcp-linear repository. An agent skill from tacticlaunch/mcp-linear.

    147 GitHub stars~347 tokensUpdated 4 days ago
    Auto-check passed
  • Inspect Linear SDK

    tacticlaunch/mcp-linear

    Inspect the Linear SDK and generated GraphQL types before adding or changing a Linear capability in mcp-linear.

    147 GitHub stars~288 tokensUpdated 4 days ago
    Auto-check passed
  • Live Linear Smoke

    tacticlaunch/mcp-linear

    Run safe live smoke tests for mcp-linear against a real Linear workspace.

    147 GitHub stars~251 tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about MCP PR Review

What does MCP PR Review do?

Review pull requests in mcp-linear for MCP-specific risks. An agent skill from tacticlaunch/mcp-linear. MCP PR Review is an agent skill from tacticlaunch/mcp-linear. Review pull requests in mcp-linear for MCP-specific risks.

When should I use MCP PR Review?

MCP PR Review fits situations like: tasks that involve Pull requests; tasks that involve MCP servers.

How do I install MCP PR Review in Claude Code?

Run `npx skills add tacticlaunch/mcp-linear --skill mcp-pr-review -a claude-code`. Or copy the skill folder (.github/skills/mcp-pr-review in tacticlaunch/mcp-linear) into .claude/skills/mcp-pr-review in your project. Claude Code loads it when a task matches its description.

How do I install MCP PR Review in Codex?

Run `npx skills add tacticlaunch/mcp-linear --skill mcp-pr-review -a codex`. Or copy the skill folder (.github/skills/mcp-pr-review in tacticlaunch/mcp-linear) into .agents/skills/mcp-pr-review in your project. Codex loads it when a task matches its description.

Can I use MCP PR Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tacticlaunch/mcp-linear --skill mcp-pr-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-pr-review, .gemini/skills/mcp-pr-review, .github/skills/mcp-pr-review and .opencode/skills/mcp-pr-review in your project.

What does MCP PR Review need to run?

SKILL.md names no scripts, command-line tools or credentials: MCP PR Review is instructions for the agent only.

Does MCP PR Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP PR Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP PR Review use?

MCP PR Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP PR Review use?

About 214 tokens (SKILL.md is roughly 856 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP PR Review?

Skills that share tags, products or a category with MCP PR Review: Review PR (PrefectHQ/fastmcp, 28k stars), Observal (Observal/Observal, 4.3k stars), Code Review (imbenrabi/Financial-Modeling-Prep-MCP-Server, 150 stars) and PR Review (confluentinc/mcp-confluent, 167 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP PR Review?

tacticlaunch (a GitHub organization) maintains it in tacticlaunch/mcp-linear, which has 147 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 4, 2026.

Source: tacticlaunch/mcp-linear on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.