CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-v3-performance-engineer

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

46

3.20x
Quality

17%

Does it follow best practices?

Impact

96%

3.20x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-v3-performance-engineer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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 verbose, monolithic spec that redundantly restates performance targets across ASCII art, pseudocode benchmark skeletons, and checklists. It conveys a measurement methodology and validation checklists, but the code is non-executable scaffolding with no progressive disclosure or tightly sequenced workflow.

Suggestions

State each performance target once and remove the redundant restatements across the ASCII boxes, hooks, benchmark arrays, and coordination sections.

Replace the pseudocode benchmark skeletons that call undefined methods with real executable commands/API calls, or explicitly justify the pseudocode as illustrative.

Add a clearly ordered optimization workflow with validation checkpoints (e.g., 1. measure baseline, 2. implement change, 3. validate improvement >= target, 4. revert on regression) instead of parallel benchmark classes.

DimensionReasoningScore

Conciseness

The ~395-line body restates the same performance targets redundantly across hooks, three ASCII boxes, benchmark targetRange arrays, checklists, and coordination sections, padding the context with unnecessary repetition rather than earning each token.

1 / 3

Actionability

The benchmark classes convey a concrete measurement methodology (baseline vs. optimized, improvement ratio), but every method calls undefined APIs like this.flashAttention(), this.sona.adapt(), and this.spawn15Agents(), making it pseudocode rather than the executable, copy-paste-ready code required for a 3.

2 / 3

Workflow Clarity

Validation checklists and a 5%-threshold regression detector exist, but the actual optimization work is presented as parallel benchmark classes rather than a clearly sequenced workflow with explicit checkpoints and fix-retry feedback loops.

2 / 3

Progressive Disclosure

There are no bundle files and the document is a single monolithic file with all benchmark, monitoring, and coordination content inline; section headers give some structure, but content that should be split into separate references is not.

2 / 3

Total

7

/

12

Passed

Description

0%

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 a boilerplate invocation stub that names no concrete capabilities, includes no natural user trigger terms, and lacks any explicit 'Use when' guidance. It is effectively indistinguishable from sibling templated agent skills.

Suggestions

Rewrite the description to name concrete actions, e.g. 'Benchmarks and optimizes Flash Attention speedup, AgentDB HNSW search latency, and memory usage for claude-flow v3.'

Add an explicit 'Use when...' trigger clause with natural phrasing, e.g. 'Use when optimizing claude-flow v3 performance, running benchmarks, or validating speedup targets.'

Replace the templated 'Agent skill for X - invoke with $X' form with a third-person capability statement that distinguishes this skill from sibling agent skills.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for v3-performance-engineer' only names a role label and names zero concrete actions, matching the 'vague or no actions; abstract language' anchor worse than 'Processes PDF files and extracts content'.

1 / 3

Completeness

It neither states concretely what the skill does nor provides any 'Use when...' trigger guidance; both the 'what' and 'when' are missing or very weak, so it cannot reach 2.

1 / 3

Trigger Term Quality

'invoke with $agent-v3-performance-engineer' is internal invocation jargon a user would never naturally say; there are no natural trigger keywords, only technical boilerplate.

1 / 3

Distinctiveness Conflict Risk

It is a generic 'Agent skill for X - invoke with $X' template applied identically across sibling agent skills, with no functional triggers to distinguish it, so it would conflict with many similar skills.

1 / 3

Total

4

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.