agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-benchmark-suite44
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 89%
↑ 2.17xAgent success when using this skill
Validation for skill structure
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is severely lacking in all key areas. It provides only a name and invocation command without explaining what the skill does, what actions it performs, or when it should be used. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what the benchmark suite does (e.g., 'Runs performance benchmarks, measures execution time, compares results across test runs')
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about performance testing, running benchmarks, measuring speed, or comparing execution times')
Remove the invocation command from the description and replace with capability-focused language that helps Claude understand the skill's purpose
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for benchmark-suite' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ($agent-benchmark-suite) with no explanation of purpose or triggers. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'benchmark-suite' which is technical jargon. No natural keywords a user would say like 'run benchmarks', 'performance testing', or 'measure speed' are included. | 1 / 3 |
Distinctiveness Conflict Risk | The specific name 'benchmark-suite' and invocation command provide some distinctiveness, but without knowing what it actually does, it's unclear if it would conflict with other testing or performance-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is severely bloated with framework-level pseudocode that describes what a benchmarking system could look like rather than providing actionable instructions Claude can execute. The content explains concepts Claude already understands and lacks the lean, executable guidance that makes skills effective. The CLI commands are the only actionable elements but lack context on expected outputs or validation.
Suggestions
Reduce content to ~50 lines focusing on: (1) the specific CLI commands available, (2) expected output formats, and (3) how to interpret results
Remove all class definitions and replace with actual executable examples showing real benchmark invocations and their outputs
Split detailed API reference and benchmark definitions into separate reference files, keeping SKILL.md as a quick-start overview
Add explicit validation steps: how to verify benchmarks ran correctly, what success/failure looks like, and recovery steps for common errors
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive code that explains concepts Claude already knows (what benchmarking is, how to structure test suites). The 500+ lines could be reduced to ~50 lines of actionable guidance. | 1 / 3 |
Actionability | Provides CLI commands that appear executable, but the extensive JavaScript code is pseudocode/framework design rather than copy-paste ready implementations. Classes reference undefined dependencies and methods. | 2 / 3 |
Workflow Clarity | Some workflow structure exists (warmup -> execute -> cooldown), but lacks explicit validation checkpoints and error recovery steps. The benchmark execution flow is described but not clearly sequenced with verification gates. | 2 / 3 |
Progressive Disclosure | Monolithic wall of code with no references to external files. All content is inline despite being far too long. No clear navigation structure or separation of overview from detailed reference material. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (670 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- 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.