unity-skill-generate

Regenerate every `SKILL.md` from the project's currently-registered MCP tools into the configured skills folder (or a project-relative override path). Writes the YAML `description:` from `[AiSkillDescription]` and the body from `[AiSkillBody]`.

Quality

73%

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/unity-skill-generate/SKILL.md

Quality

Content

68%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 skill body delivers fully executable CLI guidance with sensible troubleshooting, but the same input documentation is repeated in three places and the batch overwrite of all skill files has no verification step. Consolidating the input sections and adding a post-run check would raise both conciseness and workflow clarity.

Suggestions

Consolidate the three `path` documentation blocks (the "## Inputs" bullet, the "## Input" table, and the "### Input JSON Schema") into a single section.

Add a verification step after generation (e.g., list the regenerated SKILL.md files or preview one) since this batch operation overwrites every existing skill file.

Trim the generic multi-line/stdin CLI boilerplate to a brief pointer, keeping only the one invocation example plus a one-line fallback mention.

Dimension	Reasoning	Score
Conciseness	The `path` parameter is documented three separate times ("## Inputs" bullet, "## Input" table, "### Input JSON Schema"), and generic CLI boilerplate pads the body. Not 4 because the duplication is more than minor trimming; not 2 because there is no conceptual over-explanation Claude already knows.	3 / 5
Actionability	Fully executable, copy-paste ready commands are given ("unity-mcp-cli run-system-tool unity-skill-generate --input ..."), including --input-file and stdin variants plus troubleshooting fallbacks ("npm install -g unity-mcp-cli", "npx unity-mcp-cli"). Not 4 because the concrete examples cover the common invocation cases completely.	5 / 5
Workflow Clarity	The single CLI call is unambiguous, but the tool batch-overwrites every SKILL.md ("Regenerate every `SKILL.md`") with no validation or verification step, which caps workflow clarity at 3 under the batch-operation guideline. Not 4 because no checkpoint (e.g., verifying generated output) is described; not 2 because the Behavior section explains the mechanism coherently.	3 / 5
Progressive Disclosure	The body is well organized into Inputs, Behavior, How to Call, Troubleshooting, and Output sections with no unnecessary external references, and no content belongs in a separate file. Not 5 because the duplicate "Inputs"/"Input" sections and the interleaved JSON schema create a minor organization seam; not 3 because structure is clearly present and nothing is inlined that should be split out.	4 / 5
	Total	15 / 20 Passed

Description

63%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 excels at stating concretely what the tool does, including its data sources, but provides no guidance on when to invoke it and omits the most natural trigger term ("Unity"). Adding a "Use when..." clause and the Unity qualifier would resolve both weaknesses.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to regenerate or refresh Unity MCP skill files after tools change or the skills folder is out of date."

Include the term "Unity" and natural variations such as "generate skill files" or ".claude/skills" so the description matches what users would actually say.

State the effect on existing files (overwrite) in the description to sharpen distinctiveness from non-destructive skill tooling.

Dimension	Reasoning	Score
Specificity	"Regenerate every `SKILL.md` from the project's currently-registered MCP tools" and "Writes the YAML `description:` from `[AiSkillDescription]` and the body from `[AiSkillBody]`" name multiple concrete actions with explicit data sources, covering the tool's behavior comprehensively. Not 4 because there are no coverage gaps — inputs, destination, and both content sources are all specified.	5 / 5
Completeness	The "what" is clear and detailed (regenerates SKILL.md files, writes description and body from named attributes), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is wholly absent rather than weakly implied; not 2 because the "what" is concrete.	3 / 5
Trigger Term Quality	Relevant keywords appear ("SKILL.md", "MCP tools", "skills folder"), but the most natural trigger term a user would say — "Unity" — is absent, along with synonyms like "generate skill files" or ".claude/skills". Not 4 because key natural terms are missing; not 2 because several domain-relevant keywords are present.	3 / 5
Distinctiveness Conflict Risk	Regenerating skill files from registered MCP tools is a clear niche with mostly distinct triggers and low conflict risk. Not 5 because "Unity" is never mentioned, leaving minor overlap risk with generic skill-creation tooling; not 3 because the operation is far more specific than similar-sounding skills.	4 / 5
	Total	15 / 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/unity-skill-generate/SKILL.md
Commit: 4c8056f

Reviewed: 8 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.