CtrlK
BlogDocsLog inGet started
Tessl Logo

generate-classes

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

91

2.32x
Quality

87%

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary lean command-reference: exact maven commands per DSL argument, exact output locations, a decompilation step, and a cleanup step, with no padding or concept explanation. Structure by argument makes both navigation and execution unambiguous.

DimensionReasoningScore

Conciseness

The body is lean command blocks with zero concept explanation: each section is a copy-paste maven command plus its output location, then a javap example and a clean command. Every token earns its place; it does not match anchor 4 because there is no over-explanation to trim.

5 / 5

Actionability

Quotes: "./mvnw test -pl oap-server/oal-rt -Dtest=RuntimeOALGenerationTest -DfailIfNoTests=false -Dcheckstyle.skip", "javap -c -p <path-to-class-file>" — fully executable, copy-paste-ready commands for every argument, with exact output paths. Coverage of all four DSLs plus 'all' makes this fully actionable; not 4 because there are no gaps in the common cases.

5 / 5

Workflow Clarity

This is a simple skill: each argument maps to one unambiguous command, with a follow-up step ("Print the output location for the requested DSL", then javap to decompile) and a cleanup section. The simple-skill exception applies — the single action per argument is unambiguous; the batch/destructive cap does not apply since mvn test generation is neither destructive nor batch-risky.

5 / 5

Progressive Disclosure

The skill is a short (~60 line) command reference with all content appropriately inline: sections organized per argument, output locations, inspection, and cleanup. There are no references to bury or nested files, and nothing that belongs in a separate file; structure is well-signaled and easy to navigate.

5 / 5

Total

20

/

20

Passed

Description

75%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, concrete, and distinctive: it names the exact DSLs, the actions (generate, compile, dump .class files), and the purpose (inspection). Its only real weakness is the complete absence of a "Use when..." trigger clause, which both caps completeness and leaves natural trigger phrasing underdeveloped.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to generate, compile, or inspect classes from MAL/OAL/LAL/Hierarchy DSL scripts."

Add natural trigger synonyms users might say, such as "compile DSL", "generated classes", or "inspect bytecode".

Optionally mention the decompilation/inspection angle as a trigger ("when the user wants to see the bytecode a DSL compiles to") to widen natural matching.

DimensionReasoningScore

Specificity

Quotes: "Generate bytecode classes from DSL scripts", "Runs the compiler and dumps .class files for inspection", with all four DSLs named (MAL, OAL, LAL, Hierarchy). Multiple concrete actions are listed and coverage of the skill's scope is comprehensive; it does not fit anchor 4 since there are no gaps in the action coverage.

5 / 5

Completeness

Quotes: "Generate bytecode classes from DSL scripts... Runs the compiler and dumps .class files for inspection" — a clear "what", but there is no "when" clause or equivalent explicit trigger guidance ("Use when..."). Per the guideline, a missing 'Use when...' clause caps completeness at 3; it is not 2 because the "what" is fully clear, and not 4 because no "when" is even implied.

3 / 5

Trigger Term Quality

Quotes: "bytecode classes", "DSL scripts (MAL, OAL, LAL, Hierarchy)", ".class files", "compiler" — good natural keyword coverage users would say (e.g. "generate MAL classes"). Not 5: missing common variations and an explicit trigger phrase like "Use when compiling MAL/OAL"; not 3 because the DSL acronyms and .class/bytecode terms go well beyond generic keywords.

4 / 5

Distinctiveness Conflict Risk

Quotes: "DSL scripts (MAL, OAL, LAL, Hierarchy)", "bytecode classes" — a clear niche (SkyWalking DSL compilation) with distinct trigger terms; minimal conflict risk with generic code-generation skills. Not 4 because the DSL acronyms provide distinct, unambiguous triggers.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
apache/skywalking
Reviewed

Table of Contents

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.