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.

61

Quality

71%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a tightly scoped, actionable single-purpose skill with executable commands, clear schemas, and an up-front validation guard, weakened only by redundant presentation of the same single input parameter.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but the single `filePath` input is presented three times ("Inputs" list, "Input" table, and the input JSON schema), which could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready CLI commands in three invocation patterns (inline JSON, input-file, stdin pipe), plus explicit input/output JSON schemas and a concrete troubleshooting fix.

3 / 3

Workflow Clarity

For this simple single-task skill the single action (read file, return text) is unambiguous, with an explicit up-front 10 MB rejection check and enumerated error conditions — no destructive/batch feedback loop is needed.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no external references needed and is organized into clear, well-labeled sections; the only cross-reference (unity-initial-setup) is appropriately signaled for a tangential install concern.

3 / 3

Total

11

/

12

Passed

Description

57%

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 and distinctive in third person but lacks an explicit "Use when" trigger clause and relies on internal tool-naming rather than natural user language, leaving it at the middle level on most dimensions.

Suggestions

Add an explicit "Use when..." clause stating when to load a snapshot, e.g. "Use when reading back a snapshot saved by profiler-save-data for inspection or replay."

Include natural-language trigger terms a user would actually say (load, read, restore, snapshot file) alongside the internal tool name.

Consider listing the primary concrete action first (e.g. "Load and return the raw text of a profiler snapshot") to sharpen specificity.

DimensionReasoningScore

Specificity

"Read back a previously-saved JSON snapshot" and "return its raw text" name concrete actions in third person, but only two actions are listed for a single-purpose tool rather than a comprehensive set.

2 / 3

Completeness

It answers "what" (read back a saved snapshot, return raw text) but lacks any "Use when..." trigger clause, so "when" is only implied — capping completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Terms like "JSON snapshot" and "profiler-save-data" are relevant but internal/technical; common natural variations a user would say (load, read, restore, snapshot file) are missing.

2 / 3

Distinctiveness Conflict Risk

The explicit pairing with the producer tool `profiler-save-data` gives it a clear niche and makes it unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

12

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.