CtrlK
BlogDocsLog inGet started
Tessl Logo

stream-unreal

Build, integrate, and answer how-to questions for Stream Chat in Unreal Engine games and apps. Use for Unreal Engine / UE5 / C++ / Blueprint / UMG project work - plugin install per engine version, StreamChatClientComponent wiring on the HUD, ConnectUser and tokens, channels and messages, the shipped WBP_* chat widgets, theming, cooking, and iOS / Android / desktop packaging. Triggers on unreal, unreal engine, ue5, ue 5.7, ue 5.8, .uproject, .uplugin, Build.cs, umg, blueprint, widget blueprint, StreamChat plugin, UStreamChatClientComponent, UChatChannel, FChannelProperties, WBP_TeamChat, in-game chat, game chat. Chat only - there is no Stream Video or Feeds SDK for Unreal.

76

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered docs-orchestration skill body: concise, concrete, and sequenced with explicit gating checkpoints. Its only meaningful weakness is that the five bundled reference files it delegates to are not shipped alongside SKILL.md, breaking the progressive-disclosure chain.

Suggestions

Ship the five referenced files (RULES.md, setup.md, widgets.md, platforms.md, docs-map.md) in the skill bundle so the one-level-deep links resolve; without them the orchestrator has no detail destinations.

Consider inlining the single most load-bearing rule or a one-line docs-map legend into SKILL.md so the skill still functions if a bundle file is missing.

Verify each in-body link target exists before publishing (e.g. assert all `[...](file.md)` references resolve under the skill directory).

DimensionReasoningScore

Conciseness

Lean and dense throughout: assumes Claude's competence (no explanations of what Unreal/UMG/blueprints are) and carries only curated non-obvious knowledge such as the 'ApiKey/BeginPlay ordering trap' and the docs-coverage caveat, so every token earns its place.

5 / 5

Actionability

Provides executable, copy-paste-ready guidance: a concrete `.uproject`-detection `find` command, the exact docs-URL-to-`.md` transformation, a source-of-truth ladder with specific header paths and URLs, and a numbered Step 2 lookup procedure — no pseudocode.

5 / 5

Workflow Clarity

Clear sequence of Step 0 (three gates) -> Step 1 (classify) -> Step 2 (docs lookup), where each gate is an explicit validation checkpoint ('Hard stop - no release supports these. Say it immediately'; 'say no in the plan, not in a compile error') before any code is written.

5 / 5

Progressive Disclosure

Excellent orchestrator structure — a thin overview with a 'What this skill carries' table and one-level-deep, clearly-signaled links to RULES.md, setup.md, widgets.md, platforms.md, docs-map.md — but none of those five referenced files are present in the bundle, so navigation lands on missing targets.

4 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, third-person description that pairs concrete capabilities with an explicit 'Use for'/'Triggers on' trigger clause and version-specific keywords. It is comprehensive on actions, triggers, and the what/when pair, with clear demarcation from Stream's other SDKs.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build, integrate, and answer how-to questions', 'plugin install per engine version, StreamChatClientComponent wiring on the HUD, ConnectUser and tokens, channels and messages, the shipped WBP_* chat widgets, theming, cooking, and iOS / Android / desktop packaging' — giving comprehensive coverage of the skill's surface.

5 / 5

Completeness

Explicitly answers both 'what' ('Build, integrate, and answer how-to questions for Stream Chat in Unreal Engine') and 'when' ('Use for ... project work' plus an explicit 'Triggers on ...' clause) with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Triggers on unreal, unreal engine, ue5, ue 5.7, ue 5.8, .uproject, .uplugin, Build.cs, umg, blueprint, widget blueprint, StreamChat plugin, UStreamChatClientComponent, UChatChannel, FChannelProperties, WBP_TeamChat, in-game chat, game chat' covers natural phrases, synonyms, version strings, and file extensions comprehensively.

5 / 5

Distinctiveness Conflict Risk

Niche is tightly scoped to 'Stream Chat in Unreal Engine games and apps' and explicitly disambiguated with 'Chat only - there is no Stream Video or Feeds SDK for Unreal', minimizing conflict with sibling skills.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 16 missing

Warning

Total

13

/

16

Passed

Repository
GetStream/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.