generate-classes

Generate bytecode classes from DSL scripts (MAL, OAL, LAL, Hierarchy). Runs the compiler and dumps .class files for inspection.

2.32x

Quality

66%

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/generate-classes/SKILL.md

Quality

Content

80%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 highly actionable and well-structured for a single-purpose skill, with copy-paste commands for every DSL. Its main weakness is the absence of validation/verification steps for a batch-generation operation, which caps workflow clarity at 3.

Suggestions

Add a verification checkpoint after generation, e.g. "Confirm the .class files exist at the expected location" with a quick `ls`/`find`, before running javap.

Add a brief error-recovery loop for when a test fails to emit classes (re-run the specific module, check the compiler log).

Trim the "After generation" prose that restates output locations already shown per section to lift conciseness to 5.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept re-explanation — just executable commands and output paths, assuming Claude's competence. Not 5 because the "After generation" prose ("Print the output location for the requested DSL so the user knows where to find the generated .class files") restates info already given per section; not 3 because padding is minor.	4 / 5
Actionability	Each DSL section gives a copy-paste ready "./mvnw test -Dtest=..." command with the exact module, test class, and output location, plus javap and clean commands covering all common cases. Not 4 because guidance is fully executable with no gaps.	5 / 5
Workflow Clarity	Per-argument commands are sequenced, but this batch operation (running tests that generate many .class files) has no validation checkpoint confirming files were generated and no fix-and-retry loop, so per the rubric workflow_clarity is capped at 3. Not 4 because checkpoints are missing; not 2 because a rough sequence does exist.	3 / 5
Progressive Disclosure	This single-purpose skill (~60 lines) is organized into clear sections (commands by argument, after generation, cleaning) with no need for external references, which scores 5 per the simple-skill exception. Not 4 because organization is clean and complete with no gaps.	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 is concise and concrete about what it does, but omits an explicit 'Use when...' trigger clause, which caps completeness at 3. Distinctiveness is strong thanks to the named DSLs, though trigger terms lean technical.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers, e.g. "Use when generating or inspecting bytecode classes from MAL/OAL/LAL/Hierarchy DSL scripts."

Include a couple of natural-language trigger phrases or file extensions users might say (e.g. "generated .class files", "DSL bytecode") to improve trigger-term quality.

Briefly note the per-DSL distinction in the description to lift specificity above 'minimal actions'.

Dimension	Reasoning	Score
Specificity	Quotes "Generate bytecode classes" and "Runs the compiler and dumps .class files for inspection" name the domain plus two concrete actions, but coverage is not comprehensive (no per-DSL behavior is described). Not 4 because it lists only minimal actions; not 2 because the actions are concrete, not generic.	3 / 5
Completeness	The "what" is clear ("Generate bytecode classes ... dumps .class files for inspection") but there is no "Use when..." trigger clause, so per the rubric completeness is capped at 3. Not 4 because 'when' is not explicitly stated; not 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Keywords like "DSL scripts (MAL, OAL, LAL, Hierarchy)", "bytecode classes", and ".class files" are relevant but technical jargon rather than natural user phrasing, with no synonyms or extensions. Not 4 because it lacks natural conversational terms; not 2 because the DSL acronyms are specific keywords rather than one-or-two generic terms.	3 / 5
Distinctiveness Conflict Risk	"bytecode classes from DSL scripts (MAL, OAL, LAL, Hierarchy)" carves a clear niche with distinct acronym triggers and minimal conflict risk. Not 5 because no explicit trigger phrase reinforces distinctiveness; not 3 because the DSL acronyms are highly specific rather than broad.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: apache/skywalking
Path: .claude/skills/generate-classes/SKILL.md
Commit: 521b2ab

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.