CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

78%

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 is highly actionable with copy-paste CLI usage, input/output schemas, and troubleshooting, and the single-action workflow is unambiguous. Its weakness is redundancy: input parameters are specified three separate times and the code example uses placeholder values instead of a worked example.

Suggestions

Consolidate the "## Inputs" bullet list, "## Input" table, and "### Input JSON Schema" into a single parameter specification (e.g., one table with types, defaults, and the enum values) to remove the triple duplication.

Replace the placeholder JSON ("string_value") in the How to Call example with a realistic worked example such as {"sourceFilter": "Registry", "directDependenciesOnly": true}.

DimensionReasoningScore

Conciseness

The three input parameters are documented three times — the "## Inputs" bullet list, the "## Input" table (which repeats the nameFilter prioritization rule verbatim), and the "### Input JSON Schema" — which is real redundancy that could be tightened to a single representation. Not 2 because there is no conceptual fluff explaining things Claude already knows; not 4 because the triple duplication exceeds minor over-explanation.

3 / 5

Actionability

Provides a concrete copy-paste CLI command plus --input-file, a stdin heredoc variant, and a troubleshooting fallback (npm install -g / npx). Not 5 because the example uses placeholder values ("string_value") rather than a worked example with real values such as {"sourceFilter": "Registry"}.

4 / 5

Workflow Clarity

This is a simple, single-purpose, read-only skill where the single action (call unity-mcp-cli run-tool package-list with the documented arguments) is unambiguous, and the Troubleshooting section gives an explicit error-recovery path for a missing CLI. Per the simple-skill exception this scores 5; no validation cap applies since the operation is neither destructive nor batch.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is a self-contained single-tool doc organized under clear headers (Inputs, How to Call, Troubleshooting, Input, Output). Matches 4 (good structure, minor organization gaps) rather than 5 because the duplicated Inputs/Input sections could be consolidated; not 3 because content is appropriately placed inline and navigation is easy.

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.

The description is specific, concrete, and highly distinctive, fully describing what the tool returns and how it can be filtered. Its main weakness is the absence of any "when to use" trigger guidance, which caps completeness and leaves a few natural trigger phrases (e.g., "Package Manager") uncovered.

Suggestions

Add an explicit trigger clause such as "Use when checking which packages are installed in a Unity project, or before adding or removing packages" to satisfy the missing 'when' half of completeness.

Include the natural synonyms users say, e.g., "Unity Package Manager" and "manifest.json", to improve trigger term coverage.

DimensionReasoningScore

Specificity

"List all UPM packages installed in the Unity project — name, version, source, description" plus enumerated filter actions ("filter by source (registry, embedded, local, git, built-in, local tarball)", "by name/display/description substring", "direct-dependency-only") gives multiple concrete actions with comprehensive coverage of the tool's capabilities.

5 / 5

Completeness

The "what" is clear (list installed packages with name, version, source, description, plus filtering), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is concrete and detailed.

3 / 5

Trigger Term Quality

Natural phrases users would say are present ("UPM packages", "Unity project", "installed", "packages"), but common variations like "Package Manager" or "manifest.json" are missing. Good coverage with a few natural terms absent, matching the 4 anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

"UPM packages" and "Unity project" with Unity-specific source enums define a clear niche with distinct triggers and minimal conflict risk with other skills. Not 4, since no closely related skill would plausibly be triggered by these terms.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

IvanMurzak/Unity-MCP

Path

Unity-MCP-Plugin/.claude/skills/package-list/SKILL.md

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.