profiler-load-data

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

77%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 a well-organized, highly actionable single-purpose reference with explicit error cases and executable CLI examples. Its main weakness is redundancy — the input parameter is documented three times and the invocation block carries boilerplate that could be trimmed.

Suggestions

Consolidate the triplicated input documentation: drop the "## Inputs" bullet list and keep either the "## Input" table or the JSON schema, not both.

Make the stdin/heredoc example tool-specific by replacing the generic {"param": "value"} placeholder with {"filePath": "..."} so it is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Input documentation is stated three times ("## Inputs" bullet list, "## Input" table, and "Input JSON Schema"), and the boilerplate "How to Call" variants add padding — noticeably redundant but not heavily padded elsewhere. The "Uses `System.IO.File.ReadAllText` (BCL)" section is tight and earns above the score-2 anchor.	3 / 5
Actionability	Concrete executable commands are given for direct invocation, `--input-file`, stdin piping, and an install fallback (`npm install -g unity-mcp-cli` / `npx`), plus explicit input/output schemas. Not 5 because the stdin example uses a generic `{"param": "value"}` placeholder instead of `filePath`, so it is not copy-paste correct for this specific tool.	4 / 5
Workflow Clarity	A single-task skill with an unambiguous action (call the tool with `filePath`, receive raw text), an explicit error enumeration ("Returns `[Error]` when `filePath` is empty, the file does not exist, exceeds the 10 MB size cap, or the read fails"), and an up-front 10 MB guard. The operation is read-only and non-destructive, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external reference files, and its content is organized into clear sections (Inputs, Errors, Behavior, How to Call, Input, Output). Per the simple-skill guideline this earns a 5 with well-organized sections alone.	5 / 5
	Total	17 / 20 Passed

Description

53%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 gives a clear, concrete statement of what the skill does and is well-scoped to its companion save tool, but it entirely lacks a "when to use this" trigger clause and offers few natural trigger phrases or synonyms. It is serviceable but would benefit from an explicit use-when sentence.

Suggestions

Add an explicit trigger clause, e.g. "Use when loading or reading back profiler snapshots saved via profiler-save-data."

Include natural trigger synonyms and extensions users would actually say, such as "profiler data", "profiler results", "snapshot file", or ".json".

Clarify the direction of the operation relative to the companion skill (e.g. "the read-side counterpart to profiler-save-data") to further reduce overlap with generic file-reading skills.

Dimension	Reasoning	Score
Specificity	"Read back a previously-saved JSON snapshot from `profiler-save-data` and return its raw text" names the domain plus 1-2 concrete actions, matching the score-3 anchor. It is not 4 because no additional actions or variants are enumerated, and not 2 because the actions stated are concrete rather than generic.	3 / 5
Completeness	The "what" is clearly stated ("Read back a previously-saved JSON snapshot... and return its raw text") but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 2, since the "what" is explicit rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords exist ("JSON snapshot", "profiler-save-data", "raw text") but common natural variations users would say — e.g. "load profiler data", "profiler results", "snapshot file" — are missing, matching the score-3 anchor of some relevant keywords without synonyms.	3 / 5
Distinctiveness Conflict Risk	"previously-saved JSON snapshot from `profiler-save-data`" carves a clear niche with only minor overlap risk against the closely related save tool. Not 5 because no explicit trigger phrase distinguishes it and generic terms like "JSON snapshot" could overlap with other file-reading skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: Unity-MCP-Plugin/.claude/skills/profiler-load-data/SKILL.md
Commit: 4c8056f

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.