CtrlK
BlogDocsLog inGet started
Tessl Logo

package-search

Search Unity's package registry plus locally installed packages (Git, local, embedded sources) by query string. Returns available versions and installation status. Online mode fetches exact matches from the live registry then supplements with cached substring matches.

53

Quality

67%

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-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 a concrete CLI invocation and troubleshooting, but it is padded with duplication — the description restated as prose, inputs documented twice, and a bulky inline output schema. Consolidating the input sections and trimming the intro would materially tighten it.

Suggestions

Delete the opening paragraph that restates the frontmatter description, and remove the duplicate 'Inputs' section (keep the more detailed 'Input' table, or vice versa).

Replace placeholder values in the 'How to Call' example with a realistic invocation, e.g. "query": "textmesh", "maxResults": 10.

Trim or collapse the ~90-line Output JSON Schema to the essential fields already summarized in 'Result composition', or move it to a reference file to shorten the main body.

DimensionReasoningScore

Conciseness

Noticeably verbose through duplication: the intro paragraph repeats the frontmatter description almost verbatim, offlineMode semantics are explained twice (the 'Inputs' bullets and again in the 'Input' table), and the ~90-line Output JSON Schema largely restates 'Result composition'. Not 1: no padding with concepts Claude already knows; not 3: the redundancy is pervasive rather than occasional.

2 / 5

Actionability

Concrete, executable commands ('unity-mcp-cli run-tool package-search --input ...' plus --input-file and stdin variants) with a troubleshooting fallback for a missing CLI. Not 5: the example uses placeholders ('query': 'string_value', 'maxResults': 0 — which would return zero results if run literally) instead of a realistic, copy-paste-ready invocation.

4 / 5

Workflow Clarity

As a single-task skill the one action — call package-search with a query — is unambiguous, with error-recovery guidance for a missing CLI; read-only search, so no validation cap applies. Not 5: the duplicated 'Inputs' and 'Input' sections and the 'maxResults': 0 example create minor ambiguity about defaults.

4 / 5

Progressive Disclosure

Headers provide some structure, but the inline ~90-line Output JSON Schema and the duplicated Inputs/Input sections are content that should be split out or consolidated; no bundle files exist to offload to. Not 4: content placement is not 'mostly appropriate' given the redundancy.

3 / 5

Total

13

/

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 concrete, distinctive description with good specificity, but it lacks any 'when to use this' trigger guidance and misses natural synonyms like 'Package Manager' or 'find a package'. Adding a 'Use when...' clause would resolve the biggest gap.

Suggestions

Append a trigger clause such as 'Use when the user asks to find, search for, or check versions/installation status of Unity packages, or mentions the Unity Package Manager.'

Include natural synonyms users would actually say — 'find a package', 'lookup', 'Unity Package Manager' — alongside the existing registry terminology.

Mention the result prioritization (exact name match, display name match, substring) briefly so the 'what' covers what the tool actually returns.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Search Unity's package registry plus locally installed packages (Git, local, embedded sources) by query string. Returns available versions and installation status' — plus online-mode behavior, but omits coverage the body documents (result prioritization, truncated descriptions, top-5 versions).

4 / 5

Completeness

The 'what' is clear and concrete (search registry and installed packages, return versions and install status, online-mode behavior), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4: the 'when' is entirely absent, not just weakly implied.

3 / 5

Trigger Term Quality

Relevant keywords are present ('Search', 'Unity', 'package registry', 'installed packages', 'versions') but natural user phrasings like 'Package Manager', 'find a package', 'lookup', or 'Unity Package Manager' are missing. Not 4: common variations and synonyms users would actually say are absent.

3 / 5

Distinctiveness Conflict Risk

'Search Unity's package registry' carves a clear niche with distinct triggers; minimal overlap risk with generic search or package skills. Voice is third person throughout, so no voice penalty applies.

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.