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.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

67%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.

The body is actionable and clearly explains the async processing model, but it loses conciseness by repeating the description and duplicating the packageId format list across two sections.

Suggestions

Remove the verbatim re-statement of the description in the opening paragraph; let the frontmatter carry it.

Keep the packageId format list in one place and reference it from the Input table instead of duplicating all five formats in the table cell.

Replace the "string_value" placeholder in the example with a realistic packageId (e.g. com.unity.textmeshpro@3.0.6).

Dimension	Reasoning	Score
Conciseness	The opening paragraph restates the frontmatter description almost verbatim, and the packageId format list is duplicated verbatim inside the Input table description, so several tokens could be trimmed without losing information.	3 / 5
Actionability	Concrete, copy-paste-ready CLI invocations are given (run-tool with --input, --input-file, stdin pipe) plus a troubleshooting tip and the input schema; the placeholder "string_value" is the only minor gap.	4 / 5
Workflow Clarity	The Processing model section clearly sequences the async flow (immediate Processing → Client.Add → SchedulePostDomainReloadNotification / error), and the tool itself reports success or failure, leaving only minor validation gaps.	4 / 5
Progressive Disclosure	Sections are well-organized and the only external reference is a one-level-deep pointer to /unity-initial-setup, but the inlined duplication of the format list between two sections is a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

83%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 what the skill does and names related discovery skills. It would benefit from an explicit "Use when…" trigger phrase rather than only a discovery-first prerequisite hint.

Suggestions

Add an explicit trigger clause such as "Use when the user wants to install or add a Unity package" to make the 'when' guidance concrete.

Include a couple of natural synonyms (e.g. "add dependency", "import package") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and sources — "Install a Unity package from the registry, a Git URL, or a local path. Modifies `manifest.json` and triggers package resolution" — with comprehensive coverage of install sources and side effects.	5 / 5
Completeness	The "what" is explicit (install from registry/Git/local, modify manifest, trigger resolution, domain reload) and a "when"-style clause exists ("Use 'package-search' / 'package-list' for discovery first"), but the trigger guidance is a prerequisite hint rather than a concrete use-when phrase.	4 / 5
Trigger Term Quality	Natural terms like "Install a Unity package", "Git URL", "local path", and "package-search / package-list" are present and user-facing, but a few common synonyms (e.g. "add dependency", "import package") are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly scoped to Unity package installation via manifest.json with distinct triggers, and the related discovery skills are explicitly named, minimizing overlap risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: Unity-MCP-Plugin/.claude/skills/package-add/SKILL.md
Commit: e873d6c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.