CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-performance-optimizer

Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

47

19.39x
Quality

19%

Does it follow best practices?

Impact

97%

19.39x

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-performance-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

21%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 verbose, largely aspirational capability catalog: mostly descriptive bullet lists plus non-executable code scaffolding, with no validation checkpoints and no reference files to offload detail. A stray embedded frontmatter block and reliance on unspecified MCP tools further reduce its usefulness.

Suggestions

Cut the body to a concise overview (~50 lines) and move detailed capability catalogs, neural-training configs, and integration patterns into separate reference files under references/, linked with clearly signaled 'See X' pointers.

Replace pseudocode with executable examples: either define or remove the undefined helper functions, and fix the Python example (import os, remove invalid top-level await) so it can run as written.

Add validation checkpoints to the workflows (e.g., verify optimization actually improved metrics via validateTemporalAdvantage, with a fix-and-retry loop) instead of one-directional 5-step checklists.

Remove the duplicate/malformed YAML frontmatter block embedded at the top of the body.

DimensionReasoningScore

Conciseness

The body is ~370 lines of padded bullet catalogs explaining concepts Claude already knows (throughput, latency, caching, Pareto optimization, load balancing) — matching the anchor 'Severely verbose; extensively explains concepts Claude already knows; heavily padded'. It is not a 2 because the padding is pervasive throughout the Metrics, Strategies, and Integration Patterns sections rather than confined to a few sections.

1 / 5

Actionability

The code examples are illustrative scaffolding rather than executable guidance: JavaScript blocks call undefined helpers (buildAllocationMatrix, extractLoadDistribution, calculateNodeUtilization), and the Python block is broken (missing 'import os', invalid top-level 'await' in what is passed as plain code, empty 'optimization logic' stubs). Combined with the majority of sections being purely descriptive bullet lists, this matches the anchor 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'.

2 / 5

Workflow Clarity

The 'Example Workflows' sections are generic 5-step lists ('Baseline Assessment', 'Bottleneck Identification', ... 'Monitoring') with no commands, no validation checkpoints, and no error-recovery loops for operations that continuously modify resource allocation — matching the anchor 'Rough sequence present but many gaps; steps poorly defined; validation absent'.

2 / 5

Progressive Disclosure

Section headers provide real structure and navigation, so it rises above the anchor-2 'no section headers' case, but ~370 lines of capability catalogs, neural-network configs, and integration details that clearly belong in separate reference files are inlined monolithically, and no bundle files exist. This matches the anchor 'Some structure but could be better organized; content that should be separate is inline' — additionally, a stray duplicate YAML frontmatter block sits malformed in the middle of the body.

3 / 5

Total

8

/

20

Passed

Description

17%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 a placeholder wrapper ('Agent skill for... invoke with $...') rather than a real skill description: it states no concrete capabilities, no natural trigger terms, and no 'when to use' guidance. It would almost never surface for a relevant user query.

Suggestions

State concrete capabilities in third person, e.g., 'Identifies system bottlenecks, optimizes resource allocation, and profiles CPU/memory/network utilization using sublinear-solver MCP tools'.

Add an explicit 'Use when...' trigger clause covering natural user phrases such as 'system is slow', 'optimize performance', 'profiling', or 'resource utilization is high'.

Remove the meta-invocation syntax ('$agent-performance-optimizer') from the description; it consumes trigger space without helping users discover the skill.

DimensionReasoningScore

Specificity

The description only names the domain ('Agent skill for performance-optimizer') with zero concrete actions — matching the anchor 'Names the domain but actions are minimal or generic'. It cannot score 3 because no specific capability (like 'identifies bottlenecks' or 'optimizes resource allocation') is stated.

2 / 5

Completeness

It has a vague 'what' ('Agent skill for performance-optimizer') and no 'when' clause at all, exactly matching the anchor 'Has a vague what and no when'. A 'when' clause is missing, so completeness is capped at 3 per guidelines, and it clearly falls below that cap.

2 / 5

Trigger Term Quality

The only content is the technical invocation identifier '$agent-performance-optimizer' — no natural keywords a user would actually say (e.g., 'slow', 'optimize performance', 'profiling'). This matches the anchor 'No natural keywords; only technical jargon or entirely generic language'; it is not a 2 because even generic keywords like 'performance' or 'optimization' never appear as usable trigger terms.

1 / 5

Distinctiveness Conflict Risk

'performance-optimizer' as a bare name is very broad and would overlap with any performance- or efficiency-related skill, with no distinct trigger phrases to disambiguate — matching the anchor 'Very broad; high overlap risk with many similar skills'. It is not a 3 because nothing in the description narrows the niche.

2 / 5

Total

7

/

20

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.

Validation — 16 / 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.