CtrlK
BlogDocsLog inGet started
Tessl Logo

profiler-get-script-stats

Return script execution timing (frame time, fixed dt, time scale, frame count, runtime) plus Mono / GC memory usage in MB.

60

Quality

76%

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/profiler-get-script-stats/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 well-structured and immediately actionable for calling this read-only tool, with a clean field reference and working commands. Its weaknesses are redundancy — the output schema restates the Fields list and a no-op input is documented three times over — and inline bulk that should be split into a reference file.

Suggestions

Remove the 'complex input' file/stdin boilerplate and the entire Input section for the no-op `nothing` parameter; state instead that the tool takes no meaningful input.

Deduplicate the Fields list against the Output JSON Schema — keep the concise formula table in the body and move the full JSON schema to a `references/` file (or drop it, since the table already conveys the same information).

Show the natural invocation (e.g. `unity-mcp-cli run-tool profiler-get-script-stats --input '{}'`) as the primary example instead of the placeholder `{"nothing": "string_value"}`.

DimensionReasoningScore

Conciseness

Mostly efficient — the Fields list is tight and formula-based — but there is unnecessary padding: a generic 'save the JSON to a file / pipe via stdin' block for a tool whose only input is a no-op `nothing` parameter, and an Input section plus Input JSON Schema for that meaningless parameter. Not 4 because these padded sections clearly could be trimmed.

3 / 5

Actionability

Concrete, copy-paste-ready CLI commands (`unity-mcp-cli run-tool profiler-get-script-stats --input ...`), an `--input-file` variant, and troubleshooting for the CLI-not-found case. Minor gap: the primary example passes a placeholder `{"nothing": "string_value"}` rather than showing the natural invocation, keeping it just below fully-executable ideal.

4 / 5

Workflow Clarity

A simple, single-action skill — run one CLI command — and that action is unambiguous, with an explicit error-recovery path ('If `unity-mcp-cli` is not found... install it globally or use `npx`'). The operation is read-only, so no validation checkpoint is required.

5 / 5

Progressive Disclosure

Sections are clearly headed (Fields, How to Call, Input, Output), but the ~70-line inline Output JSON Schema substantially duplicates the Fields section and is bulk content that belongs in a separate reference file; no bundle files exist to justify inlining it. Better organized than the score-2 'minimal structure' anchor, but not the score-4 'most content appropriately placed'.

3 / 5

Total

15

/

20

Passed

Description

71%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 precise, well-scoped description that fully enumerates the tool's outputs without fluff, held back mainly by the complete absence of a 'when to use' trigger clause. Adding explicit trigger guidance and a few natural synonyms (profiler, FPS, performance) would lift it to top marks.

Suggestions

Append a trigger clause such as 'Use when the user asks about Unity script performance, frame rate/FPS, time scale, or Mono/GC memory usage' to satisfy the missing 'when' and raise completeness.

Include natural synonyms users would say — 'profiler', 'FPS', 'frame rate', 'performance stats' — to broaden trigger-term coverage.

Mention Unity explicitly in the description so it is distinguishable from non-Unity profiling tools at a glance.

DimensionReasoningScore

Specificity

The description enumerates every concrete output the tool returns — "frame time, fixed dt, time scale, frame count, runtime" plus "Mono / GC memory usage in MB" — giving comprehensive, non-generic coverage of capabilities. It exceeds the score-4 anchor because there are no gaps in what is returned, not merely 'several specific actions with minor gaps'.

5 / 5

Completeness

The 'what' is clear and concrete (returns script execution timing and Mono/GC memory stats), but there is no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("frame time", "time scale", "frame count", "runtime", "GC memory") that a Unity developer would plausibly say, but common synonyms like "profiler", "FPS", "performance", or "memory usage" variations are missing. Better than the score-3 anchor's 'missing common variations', short of the score-5 anchor's full synonym coverage.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (Unity Time/Profiler/GC runtime stats with specific field names), making confusion with unrelated skills unlikely; minor overlap risk remains with sibling profiler/memory tools in the same Unity MCP tool suite. Not 5 because 'script execution timing' alone could plausibly route to other performance-inspection tools.

4 / 5

Total

16

/

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.