CtrlK
BlogDocsLog inGet started
Tessl Logo

package-add

Install a Unity package from the registry, a Git URL, or a local path. Modifies `manifest.json` and triggers package resolution; may also trigger a domain reload — the final result is delivered after the reload via the request's `requestId`. Use 'package-search' / 'package-list' for discovery first.

59

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/package-add/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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, executable reference for a single-purpose CLI tool: complete call syntax in three variants, documented async result delivery with an explicit error path, and clean section organization. The main costs are redundancy — packageId formats appear twice and the intro mirrors the description — and a placeholder instead of a concrete example payload.

Suggestions

State the packageId formats once (keep the dedicated "## packageId formats" section) and shorten the Input table cell to "The package ID to install; see formats above".

Replace "string_value" in the How to Call example with a realistic value like com.unity.textmeshpro@3.0.6 so the command is directly runnable.

Cut or compress the opening overview paragraph, which restates the frontmatter description verbatim.

DimensionReasoningScore

Conciseness

Mostly lean, but the packageId formats are duplicated nearly verbatim in "## packageId formats" and again in the Input table's description cell, and the opening paragraph repeats the frontmatter description almost word-for-word. Not 4 because these are real, avoidable token costs rather than minor trimming; not 2 because there is no padding or explanation of concepts Claude already knows.

3 / 5

Actionability

The How to Call section gives copy-paste-ready commands covering the plain, --input-file, and stdin heredoc variants, plus a concrete troubleshooting fallback (npx / npm install -g). Not 5 because the example payload uses the placeholder "string_value" instead of one realistic example (e.g. "com.unity.textmeshpro@3.0.6") drawn from the documented formats.

4 / 5

Workflow Clarity

This is a simple single-action skill and the action is unambiguous: one command, one required parameter. The async wrinkle — "Returns Processing immediately with the supplied requestId... success → SchedulePostDomainReloadNotification... failure → an immediate error notification with the underlying Unity error message" — is explicitly sequenced with the error-feedback path documented. Package install is not a destructive or batch operation, so the validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed at this size; sections (formats, processing model, how to call, troubleshooting, input, output) are well-organized and the only external pointer ("Read the /unity-initial-setup skill") is clearly signaled. Not 5 because the body is ~68 lines with the format list and input schema repeating information that could be consolidated into one authoritative section.

4 / 5

Total

16

/

20

Passed

Description

62%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 specific, concrete description that names exact mechanics (manifest.json modification, package resolution, domain reload, requestId-based result delivery) and actively disambiguates sibling tools. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and leaves natural trigger-term coverage thin.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to install, add, or import a Unity package (from the registry, a Git URL, or a local path)."

Include common user synonyms such as "add package", "import", and "UPM/package manager" so natural phrasings match.

Trim the async-delivery mechanics (domain reload, requestId) from the description and keep them in the body — they consume trigger space without aiding skill selection.

DimensionReasoningScore

Specificity

"Install a Unity package from the registry, a Git URL, or a local path" plus "Modifies manifest.json and triggers package resolution" lists several concrete, verifiable actions with the exact file touched. Falls short of 5 because coverage is narrow — no mention of removing/updating or what a successful result contains beyond the async delivery note.

4 / 5

Completeness

The "what" is clear (install a Unity package from registry/Git/local path), but there is no "Use when..." trigger clause — "Use 'package-search' / 'package-list' for discovery first" routes to sibling tools rather than stating when to invoke this skill. Per the judging guidelines a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "install", "Unity package", "Git URL", "registry" are present, but common user phrasings and synonyms ("add a package", "import", "UPM", "package manager") are missing. Not 4 because the natural-term coverage is thin beyond the single verb "install".

3 / 5

Distinctiveness Conflict Risk

"Install a Unity package" carves out a clear niche, and explicitly redirecting discovery to 'package-search' / 'package-list' minimizes confusion with sibling package-manager skills. Not 4 because no realistic overlap scenario remains once the Unity-specific scope and the discovery routing are stated.

5 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
IvanMurzak/Unity-MCP
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.