CtrlK
BlogDocsLog inGet started
Tessl Logo

package-list

List all UPM packages installed in the Unity project — name, version, source, description. Optionally filter by source (registry, embedded, local, git, built-in, local tarball), by name/display/description substring, and by direct-dependency-only.

63

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/package-list/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.

The body delivers concrete, executable CLI guidance with sensible fallbacks and clear organization for a single-step, read-only skill. Its main costs are token redundancy — the same parameters documented three times — and the lack of a realistic filled-in example call, plus inline schema blocks that inflate the overview.

Suggestions

Collapse the "## Inputs" bullets, "## Input" table, and "### Input JSON Schema" into a single parameter presentation (e.g., the table plus enum values) to remove duplication.

Show one realistic example invocation with actual values (e.g., --input '{"nameFilter":"ui","sourceFilter":"Registry"}') instead of only "string_value" placeholders.

Move the raw Input/Output JSON schemas to a reference file (e.g., references/schemas.md) and keep a brief field summary inline, since no bundle currently exists but the body exceeds a lean overview.

DimensionReasoningScore

Conciseness

Parameters are presented three times ("## Inputs" bullets, "## Input" table, "### Input JSON Schema") and the generic "For complex input (multi-line strings, code), save the JSON to a file" aside is padding, so the body is mostly efficient but includes unnecessary duplication that could be tightened.

3 / 5

Actionability

"unity-mcp-cli run-tool package-list --input '{...}'" plus the --input-file, stdin heredoc, and CLI-not-found fallbacks give concrete, mostly executable guidance; the minor gap is that placeholders like "string_value" are never shown filled with a realistic example invocation.

4 / 5

Workflow Clarity

This is a simple, single-purpose, read-only skill and the single action (invoke the CLI tool) is unambiguous, with troubleshooting for the main failure mode, so the simple-skill exception applies and the action scores full clarity.

5 / 5

Progressive Disclosure

Sections are well-organized and clearly headed (Inputs, How to Call, Troubleshooting, Input, Output) with no buried references, but the ~130-line body inlines tool-generated JSON schemas and duplicates the input documentation, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

75%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 highly specific, well-scoped description that comprehensively covers the tool's actions and stays in third person without fluff. Its one real weakness is the absence of any explicit "Use when..." trigger guidance, which both caps completeness and leaves some natural trigger phrasings (e.g., "Package Manager", "which packages are installed") unused.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks which packages are installed in the Unity project, wants to check before adding or removing packages, or mentions UPM/Package Manager packages."

Add one or two natural synonyms such as "Package Manager" or "check installed packages" to broaden trigger term coverage.

Mirror the body's useful "before adding or removing packages" framing into the description to sharpen the when-to-use signal.

DimensionReasoningScore

Specificity

"List all UPM packages installed in the Unity project — name, version, source, description. Optionally filter by source... by name/display/description substring, and by direct-dependency-only" names the domain and multiple concrete actions (list with returned fields, three distinct filter modes) with comprehensive coverage of the tool's capabilities, matching the top anchor.

5 / 5

Completeness

The "what" is clear and detailed ("List all UPM packages installed... name, version, source, description") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural terms like "UPM packages", "installed", "Unity project", and all source-filter keywords users would say, but misses common variations such as "Package Manager" or "check which packages are installed", so a few natural terms are missing rather than coverage being comprehensive.

4 / 5

Distinctiveness Conflict Risk

"List all UPM packages installed in the Unity project" carves out a clear niche (Unity UPM listing) with explicit filter scopes, making it clearly distinguishable from sibling package-management skills with minimal conflict risk.

5 / 5

Total

17

/

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.