CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-performance-analyzer

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

47

1.00x
Quality

18%

Does it follow best practices?

Impact

99%

1.00x

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-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

20%

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 well-structured but generic conceptual taxonomy of performance analysis that largely restates knowledge Claude already has, with abstract steps and no executable or tool-specific guidance. It has a clear phased workflow but lacks validation checkpoints and any progressive file structure.

Suggestions

Cut generic concept lists (parallelization, caching, algorithm improvements) that Claude already knows and replace them with skill-specific, concrete analysis procedures or commands.

Make the workflow actionable by specifying actual tooling, metric formulas, or thresholds for each phase instead of abstract directives like 'Identify anomalies'.

Add validation/verification checkpoints in the workflow (e.g., confirm metrics captured before analysis, verify root-cause against baseline) and move advanced features/examples into separate reference files to reduce the monolithic body.

DimensionReasoningScore

Conciseness

The body enumerates generic concepts Claude already knows (parallelization, caching, resource reallocation, P95/P99) across ~170 lines without skill-specific novelty, matching the 'explains concepts Claude knows; padded' anchor for 1.

1 / 3

Actionability

Steps like 'Gather execution metrics', 'Identify anomalies', and 'Determine root causes' are abstract directives with no concrete tools, commands, or formulas; only the report template is semi-concrete, so it describes rather than instructs as in the score-1 anchor.

1 / 3

Workflow Clarity

The Data Collection, Analysis, and Recommendation phases give a clear numbered sequence, but there are no validation checkpoints or feedback loops, matching the 'steps listed but validation gaps' anchor for 2.

2 / 3

Progressive Disclosure

The document is well-organized into clearly headed sections, but at ~170 lines it is monolithic with content (advanced features, examples, report format) that could be split into references and no external files signaled, matching the score-2 anchor.

2 / 3

Total

6

/

12

Passed

Description

17%

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 auto-generated metadata that names the performance-analysis domain but conveys no real capabilities, natural trigger terms, or usage guidance. It reads as invocation boilerplate rather than a skill description.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Identifies and resolves performance bottlenecks in agent workflows by profiling execution time, resource usage, and coordination overhead.'

Add a 'Use when...' clause with natural trigger terms users would say, such as 'slow tasks', 'bottlenecks', 'latency', or 'resource contention'.

Replace the invocation-syntax phrasing ('$agent-performance-analyzer') with third-person capability language to improve specificity and distinctiveness.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for performance-analyzer' names a domain (performance analysis) but the only stated action is 'invoke with $agent-performance-analyzer', which is meta-invocation rather than a concrete capability, leaving it short of the comprehensive action list needed for a 3.

2 / 3

Completeness

It provides only a weak implied 'what' (via the name) and no 'Use when...' clause or equivalent trigger guidance, so both what and when are weak as in the score-1 anchor.

1 / 3

Trigger Term Quality

The description relies on the technical skill-name token 'performance-analyzer' and invocation syntax '$agent-performance-analyzer' rather than natural user phrasings like 'slow', 'bottleneck', or 'optimize', matching the jargon-heavy anchor for 1.

1 / 3

Distinctiveness Conflict Risk

The 'performance-analyzer' domain is somewhat specific and unlikely to broadly conflict, but the generic 'Agent skill for...' framing does not establish clear distinct triggers, matching the 'somewhat specific but could overlap' anchor.

2 / 3

Total

6

/

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/claude-flow
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.