CtrlK
BlogDocsLog inGet started
Tessl Logo

et-unitybridge

UnityBridge workflow for AI operations in Unity Editor. Use when checking UnityBridge connectivity, Unity compile or PlayMode state, running deferred UnityBridge commands, operating assets/scenes/GameObjects/Inspector/Prefabs/GameView/screenshots, running Editor tests, or troubleshooting UnityBridge responses.

72

Quality

87%

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

82%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 tight, action-oriented body with concrete executable commands, embedded validation checkpoints for batch/risky operations, and well-signaled one-level-deep references. Minor gaps: write operations are named not fully exemplified, and the references/navigation could be slightly more explicit.

Suggestions

Add one or two complete executable examples for a representative deferred/write command (e.g., a full Compile or AssetImportRequest invocation with its wait semantics) to lift actionability.

Reformat the '按需补读' references as bold-label + link pairs (e.g., **AI 操作**: See [et-unitybridge-ai-ops.md](references/...)) for cleaner navigation.

Consider converting '默认动作' into a single ordered workflow with explicit validation checkpoints marked (e.g., bold 'Validate' steps) to make the sequence and feedback loop more visually explicit.

DimensionReasoningScore

Conciseness

Lean directives with no concept explanations Claude already knows; sections like '省 Token 规则' and '默认动作' are terse and every line carries operational value, matching the lean-and-efficient anchor.

5 / 5

Actionability

Provides copy-paste executable commands ('dotnet ./Bin/ET.UnityBridge.dll {"_t":"Ping"}') and concrete command names, but the bulk write/deferred operations are named rather than fully exemplified, leaving minor gaps.

4 / 5

Workflow Clarity

The numbered '默认动作' sequence includes validation checkpoints (Ping before ops, wait for deferred response, verify PlayMode/not-compiling preconditions, '批量操作前先验证 1 个样本') and an error-recovery feedback loop ('失败时先看 Error / Message'), but it reads as defaults rather than one strictly linear workflow.

4 / 5

Progressive Disclosure

Well-organized sections with a concise overview and two one-level-deep references (et-unitybridge-ai-ops.md, et-unitybridge-cli.md) that are real files and clearly signaled with descriptions; slightly short of the top anchor's clean multi-reference navigation format.

4 / 5

Total

17

/

20

Passed

Description

92%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 strong, specific description that clearly states both the skill's purpose and concrete use-when triggers tied to a distinct Unity tooling niche. The only minor gap is trigger-term variety (synonyms/extensions) versus the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'checking UnityBridge connectivity, Unity compile or PlayMode state', 'operating assets/scenes/GameObjects/Inspector/Prefabs/GameView/screenshots', 'running Editor tests'—giving comprehensive coverage of the tool's capabilities rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both—'UnityBridge workflow for AI operations in Unity Editor' states what, and 'Use when checking... running... operating... troubleshooting' gives concrete trigger phrases for when.

5 / 5

Trigger Term Quality

Good keyword coverage with natural Unity terms (PlayMode, Prefabs, Inspector, GameView, screenshots, Editor tests), but it leans technical and lacks synonyms or the kind of file-extension triggers the top anchor expects.

4 / 5

Distinctiveness Conflict Risk

A narrow UnityBridge/Unity-Editor niche with distinct triggers unlikely to fire for unrelated skills, so conflict risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
egametang/ET
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.