assets-modify

Modify an asset file in the project. Use 'assets-get-data' first to inspect the asset structure before modifying. Not allowed to modify asset files in the 'Packages/' folder — modify them in 'Assets/'. Three modification surfaces are available (content, pathPatches, jsonPatch) — see the skill body for details.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/assets-modify/SKILL.md

Quality

Content

70%

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 concrete executable commands and clear modification-surface ordering, and is well-organized as a single file. Its weaknesses are inline schema verbosity and the absence of a post-modification validation checkpoint for a destructive operation.

Suggestions

Add a validation/verification step after modification (e.g. re-run assets-get-data or confirm the patch applied) to raise workflow clarity for this destructive operation.

Trim or move the large inline input/output JSON schemas to a reference file or shorten to the non-obvious fields, keeping the lean prose dominant.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (three surfaces, path syntax, how-to-call, troubleshooting) but embeds large inline input/output JSON schemas (~140 lines) that largely restate tool-introspectable metadata and add padding. Not score 3 because the inline schema bulk could be trimmed or referenced; not score 1 because the surrounding prose is lean and assumes Claude's competence.	2 / 3
Actionability	Provides concrete, copy-paste-ready `unity-mcp-cli run-tool assets-modify` commands plus file/stdin variants, explicit path-syntax examples, and troubleshooting — matching the fully-executable anchor.	3 / 3
Workflow Clarity	Sequencing of the three modification surfaces is stated (jsonPatch → pathPatches → content, 'at least one required'), but this destructive asset-modify operation lacks any validation/verification checkpoint after modification. Per the rubric guideline, missing validation in destructive operations caps workflow clarity at 2; not score 1 because the execution order and requirement are explicit.	2 / 3
Progressive Disclosure	Single self-contained file with well-organized sections (surfaces, path syntax, how to call, troubleshooting, input, output) and no nested multi-level references; for a self-contained skill under the 'no external references needed' rule this qualifies as well-organized. Not score 2 because structure is clear and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

70%

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 well-differentiated, naming concrete modification surfaces and folder constraints. Its main weakness is the absence of an explicit 'Use when...' trigger clause and reliance on internal tool names rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasing (e.g. 'Use when the user asks to edit or update a Unity asset such as a Material, ScriptableObject, or Prefab').

Surface natural terms users would say (asset, prefab, material, modify/update) alongside the tool-internal names to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and constraints ('Modify an asset file', 'Use assets-get-data first', 'Not allowed to modify... Packages/', 'modify them in Assets/') and enumerates the three modification surfaces — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Clearly answers 'what does this do' and gives a sequencing hint, but lacks an explicit 'Use when...' trigger clause. Per the rubric guideline, a missing explicit trigger guidance caps completeness at 2; not score 3 because 'when' is only implied, not score 1 because 'what' is strong.	2 / 3
Trigger Term Quality	Contains some relevant keywords ('asset file', 'assets-get-data', 'Packages/', 'Assets/') but relies on tool-internal names rather than natural user phrasing (e.g. 'asset', 'prefab', 'material'), missing common variations. Not score 3 because coverage of natural terms users would actually say is incomplete; not score 1 because several relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	Targets a clear Unity-asset niche with concrete folder constraints and a sibling-tool pairing (get-data vs modify), making it unlikely to trigger for the wrong skill. Matches the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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/assets-modify/SKILL.md
Commit: e0a24ef

Reviewed: about 13 hours 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.