Name: kotlin-tooling-kotlin-toolchain-plugin-authoring
Rating: 70.39999999999999 (1 reviews)
Author: Kotlin

kotlin-tooling-kotlin-toolchain-plugin-authoring

Load when authoring, writing, or designing a Kotlin Toolchain local plugin to extend the declarative build with code generation, build-time processing, custom verification, or packaging that module.yaml cannot express, or when referencing @TaskAction, @Configurable, plugin.yaml, or jvm/amper-plugin. Skip for porting an existing Gradle plugin.

Quality

85%

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

Quality

Content

82%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 tightly written, well-structured reference for Kotlin Toolchain plugin authoring with executable code patterns and a real external examples file. Its main gaps are template placeholders in code and the absence of an explicit validate-fix-retry loop in its workflows.

Suggestions

Replace placeholder code bodies (e.g. '// body' in the @TaskAction example, '<coordinate>:<version>') with a single fully concrete runnable snippet so the common case is copy-paste executable.

Add an explicit validate→fix→retry loop in the 'Validate against a consumer' section (run command → compare expected output → on mismatch, diagnose and re-run) to lift workflow clarity to 5.

Consider moving the inline API-reference table and the full plugin.yaml schema into references/examples.md or a separate reference file so SKILL.md reads more as an overview pointing to details.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean, assuming Claude's competence throughout — it never explains what Kotlin is or how builds work, and prose like 'There is no shared mutable build state — no project.version, no extension property maps' carries novel, high-value signal per token.	5 / 5
Actionability	Provides concrete, copy-paste-adaptable Kotlin and YAML for Settings, @TaskAction, execution avoidance, plugin.yaml, and env-var overrides, but template placeholders such as '<coordinate>:<version>', '<fully.qualified.foo>', and a '// body' stub leave minor execution gaps.	4 / 5
Workflow Clarity	Clear sequenced processes appear in 'File-based task communication' (producer→path-match→consumer) and 'Validate against a consumer' (3 numbered steps with a verification checkpoint), but there is no explicit validate→fix→retry feedback loop, keeping it below 5.	4 / 5
Progressive Disclosure	A single, well-signaled one-level reference ('Code patterns to adapt are in references/examples.md', verified to exist) plus a well-sectioned body gives good navigation, though the body itself carries substantial inline spec detail that keeps it just short of the ideal overview-points-to-details split.	4 / 5
	Total	17 / 20 Passed

Description

87%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 is specific, complete, and well-bounded: it names concrete plugin-authoring capabilities, gives explicit load triggers and an explicit skip condition, and stays in third-person voice. It is a strong trigger description with only minor room for more natural-surface synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'code generation, build-time processing, custom verification, or packaging' — tied to a named authoring task; these are slightly higher-level category labels than the fully concrete verbs in the anchor-5 example, so it sits at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what ('extend the declarative build with code generation, build-time processing, custom verification, or packaging that module.yaml cannot express') and when ('Load when authoring... or when referencing...'), with concrete trigger phrases and an explicit skip clause.	5 / 5
Trigger Term Quality	Good keyword coverage including concrete API tokens users would reference ('@TaskAction, @Configurable, plugin.yaml, or jvm/amper-plugin') and natural phrasings like 'authoring, writing, or designing', but a few common-surface synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Kotlin Toolchain local plugin authoring) with distinct API-token triggers, and the explicit 'Skip for porting an existing Gradle plugin' sharply bounds conflict risk.	5 / 5
	Total	18 / 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: Kotlin/kotlin-agent-skills
Path: skills/kotlin-tooling-kotlin-toolchain-plugin-authoring/SKILL.md
Commit: c2f9069

Reviewed: 5 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.