#556 by GitHub stars

EpicGames/unreal-engine-skills-for-claude-code-plugin

Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an exi

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/create-toolset/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

a6aa73ada02a → 0e27bde2b55c

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

skills/unreal-mcp/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

a6aa73ada02a → 0e27bde2b55c

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

skills/unreal-skill/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Not checked yet → After Local scripts

a6aa73ada02a → 0e27bde2b55c

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 0e27bde2b55c5d3f6948532f4296aaa3654d8f4b

git clone --filter=blob:none --no-checkout https://github.com/EpicGames/unreal-engine-skills-for-claude-code-plugin.git .hotskills/epicgames-unreal-engine-skills-for-claude-code-plugin && git -C .hotskills/epicgames-unreal-engine-skills-for-claude-code-plugin checkout --detach 0e27bde2b55c5d3f6948532f4296aaa3654d8f4b # Copy each selected skill directory from .hotskills/epicgames-unreal-engine-skills-for-claude-code-plugin into .claude/skills/<skill-name>/
1.9kGitHub stars
175stars in 7 days
3skills in this repository
1commit in 30 days

Heat

7.9
  • Star growth, last 7 daysAhead of 98% of tracked repositories
  • Star growth, last 24 hoursAhead of 96% of tracked repositories
  • Rank movement, last 7 daysAhead of 95% of tracked repositories
  • Commits, last 30 daysAhead of 54% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 1, 2026Nov 6, 20261,916

Individual skills in this repository

How it works

create-toolset

When your agent uses it

Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an existing one such as `BlueprintTools`, `StaticMeshTools`, `ObjectTools`, `LevelTools`, or `MaterialTools`. Concrete triggers: 'add a tool to X', 'expose this via MCP', 'register a function so Claude/the agent can call it', 'wire this into the toolset registry', 'create a new toolset for Y', 'add a Python toolset', 'make this AI-callable'; adding a `static` method to a `*Tools.cpp/.h/.py` file; editing files under a `Toolsets/` folder; designing tool parameters, return types, or struct schemas for a toolset. SKIP for: invoking existing tools at runtime (use unreal-mcp instead), authoring an Agent Skill (use unreal-skill), generic refactors that happen to touch a toolset file but don't add or redesign a tool, or unrelated uses of the word 'toolset'.

What it loads into context

Frontmatter

263 tokens

Always available to the agent

SKILL.md

5,120 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Principles
  2. Before You Write
  3. Shared Conventions
  4. Documentation
  5. C++ Specifics
  6. Python Specifics
  7. Testing Your Work
  8. Reviewing Your Work

Scripts executed separately

  • ../../hooks/unreal-context.sh
  • ../../hooks/unreal-context.sh
  • ../../hooks/unreal-context.sh
  • ../../hooks/unreal-context.sh

Files

  • ../../.claude-plugin/plugin.jsonasset487 bytes
  • ../../hooks/hooks.jsonasset357 bytes
  • ../../hooks/unreal-context.shruns3,101 bytes
  • ../../hooks/unreal-context.shruns3,101 bytes
  • ../../hooks/unreal-context.shruns3,101 bytes
  • ../../hooks/unreal-context.shruns3,101 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
  • SKILL.mdcore23,258 bytes
Read SKILL.md

# Create Toolset

You are authoring or extending an Unreal Engine toolset: a collection of static, AI-callable functions registered with the `ToolsetRegistry` and exposed through the MCP server. The goal is to expand the surface of things Claude can do inside the editor.

## Principles

A good toolset is:

**Clean**: Design the simplest API that can do useful work in the domain. Don't mirror Unreal's existing APIs directly; they're often unnecessarily complex. A good heuristic: would a technical artist understand this without reading the implementation?

**Complete**: Support CRUD symmetry. If you can set a thing, you should be able to get it. If there's a create, there should be a delete. Getters without setters are fine when mutation isn't possible or useful.

**Composable**: Use consistent types for the same kinds of operation across the toolset. If `get_graph()` returns a `Graph`, then `get_graph_nodes()` should accept a `Graph`. Functions should combine naturally to produce more complex results.
View the complete source on GitHub

Skills included

  • create-toolset
  • unreal-mcp
  • unreal-skill

Repository facts

License
MIT
Created
Jun 8, 2026
Last pushed
Oct 27, 2026
Forks
194
Open issues
7
Project activity
Active

Rank over the last 12 weeks

Now #556 · best #530 · up 435 in 30 days

  1. #561 on Nov 1
  2. #557 on Nov 2
  3. #558 on Nov 3
  4. #557 on Nov 4
  5. #554 from Nov 5 to Nov 6
  6. #556 since Nov 7
68 earlier periods
  1. #870 on Aug 8
  2. #911 on Aug 11
  3. #916 on Aug 13
  4. #894 on Aug 14
  5. #862 on Aug 15
  6. #886 on Aug 16
  7. #906 on Aug 19
  8. #892 on Aug 20
  9. #904 on Aug 21
  10. #849 on Aug 22
  11. #906 on Aug 23
  12. #924 on Aug 25
  13. #906 on Aug 26
  14. #912 on Aug 27
  15. #951 on Aug 28
  16. #867 on Aug 29
  17. #870 on Aug 30
  18. #917 on Aug 31
  19. #952 on Sep 1
  20. #921 on Sep 2
  21. #925 on Sep 3
  22. #867 on Sep 5
  23. #903 on Sep 6
  24. #930 on Sep 7
  25. #927 on Sep 10
  26. #892 on Sep 11
  27. #891 on Sep 12
  28. #890 on Sep 13
  29. #928 on Sep 14
  30. #917 on Sep 15
  31. #930 on Sep 16
  32. #927 on Sep 17
  33. #915 on Sep 18
  34. #907 on Sep 20
  35. #928 on Sep 21
  36. #945 on Sep 22
  37. #937 on Sep 23
  38. #903 on Sep 24
  39. #852 on Sep 25
  40. #893 on Sep 27
  41. #969 on Sep 29
  42. #872 on Oct 1
  43. #889 on Oct 2
  44. #862 on Oct 3
  45. #905 on Oct 4
  46. #925 on Oct 5
  47. #913 on Oct 6
  48. #952 on Oct 7
  49. #991 on Oct 8
  50. #956 on Oct 9
  51. #929 on Oct 10
  52. #930 on Oct 11
  53. #951 on Oct 12
  54. #956 on Oct 13
  55. #973 on Oct 14
  56. #959 on Oct 15
  57. #968 on Oct 16
  58. #947 on Oct 17
  59. #659 on Oct 18
  60. #615 on Oct 19
  61. #578 on Oct 20
  62. #569 on Oct 21
  63. #550 on Oct 22
  64. #541 on Oct 23
  65. #530 on Oct 24
  66. #581 on Oct 25
  67. #578 from Oct 28 to Oct 29
  68. #579 from Oct 30 to Oct 31

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 3, 2026

Risk level changed on Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 13 notes
  • hooks/unreal-context.sh:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/unreal-context.sh:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/unreal-context.sh:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/create-toolset/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/unreal-context.sh:1 Plugin-wide analysis incomplete; see repository notes
  • skills/unreal-skill/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/unreal-skill/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 7 signals by file

hooks/unreal-context.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Executable scriptline 1
    Executable file; content unavailable
  • Executable scriptline 1
    Executable file; content unavailable
  • Executable scriptline 1
    Executable file; content unavailable

skills/unreal-mcp/references/setup.md

  • Network accessline 73
    "unreal-mcp": {       "type": "http",       "url": "http://127.0.0.1:8000/mcp"
  • Network accessline 74
    "type": "http",       "url": "http://127.0.0.1:8000/mcp"     }
  • Network accessline 75
    "url": "http://127.0.0.1:8000/mcp"

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 7 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/plugin.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/create-toolset/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/create-toolset/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/create-toolset/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/create-toolset/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/create-toolset/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

EpicGames/unreal-engine-skills-for-claude-code-plugin: #556 on hotskills, 1.9k stars

[![EpicGames/unreal-engine-skills-for-claude-code-plugin on hotskills](https://hotskills.dev/badge/epicgames-unreal-engine-skills-for-claude-code-plugin.svg)](https://hotskills.dev/skill/epicgames-unreal-engine-skills-for-claude-code-plugin/)