CtrlK
BlogDocsLog inGet started
Tessl Logo

profiler-load-data

Read back a previously-saved JSON snapshot from `profiler-save-data` and return its raw text.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/profiler-load-data/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 an efficient, fully actionable spec for a simple load tool: executable commands, explicit schemas, enumerated errors, and an OOM guard. The only drag is light redundancy in how the single input parameter is documented.

DimensionReasoningScore

Conciseness

Lean and mostly efficient with no over-explanation of concepts Claude knows; the only slack is mild redundancy where the single "filePath" parameter is restated across the prose "Inputs", the table, and the schema.

4 / 5

Actionability

Provides fully executable, copy-paste-ready CLI invocations (including stdin and --input-file variants) plus explicit input/output JSON schemas and a troubleshooting note.

5 / 5

Workflow Clarity

For this simple single-purpose skill the single action is unambiguous, errors are enumerated, and the 10MB cap is stated up front; it is not a destructive or batch operation, so the simple-skill exception applies.

5 / 5

Progressive Disclosure

Well-organized sections (Inputs, Errors, Behavior, How to Call, Output) with no need for external references; the minor dual presentation of the same single parameter keeps it just below a perfect 5.

4 / 5

Total

18

/

20

Passed

Description

46%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 states a concrete action clearly but omits any trigger guidance and relies on technical jargon rather than natural user phrases, limiting both completeness and trigger-term quality. It is reasonably distinct thanks to the profiler-save-data coupling.

Suggestions

Add a "Use when..." clause naming a natural trigger (e.g., when reloading a profiler snapshot previously saved with profiler-save-data).

Surface a couple of natural-language terms a user might say (e.g., "reload profiler data", "restore snapshot") alongside the technical name.

Optionally note the 10MB cap or parse-ownership in the description so users know the boundary up front.

DimensionReasoningScore

Specificity

"Read back a previously-saved JSON snapshot" and "return its raw text" name the domain and 1-2 concrete actions, but coverage is minimal (only the load half of the save/load pair).

3 / 5

Completeness

The "what" is clear, but there is no "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric.

3 / 5

Trigger Term Quality

Terms like "JSON snapshot", "raw text", and "profiler-save-data" are technical jargon tied to a sibling tool; no natural phrases a user would actually say when they need this.

2 / 5

Distinctiveness Conflict Risk

Being explicitly scoped to files written by profiler-save-data gives it a clear niche with minimal overlap risk; only minor overlap with generic file-reading skills.

4 / 5

Total

12

/

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.

Validation16 / 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.