agent-performance-optimizer

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

19.39x

Quality

17%

Does it follow best practices?

Impact

97%

19.39x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-performance-optimizer/SKILL.md

Quality

Content

35%Weight 40%Scale 1-3

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 monolithic, verbose document that lists capabilities and embeds large code scaffolding rather than giving lean, executable guidance. It has real MCP tool wiring and numbered workflows, but these are undercut by undefined helper functions, stub methods, duplicate sections, and a total absence of file-based progressive disclosure or validation checkpoints.

Suggestions

Trim the document drastically: delete the duplicate 'Optimization Strategies' section and the generic metric/capability bullets that restate what Claude already knows about throughput, latency, and caching.

Move large inline examples (the Flow Nexus sandbox block and the neural-training config) into reference files and link to them from a concise overview to enable one-level-deep progressive disclosure.

Replace stub methods (e.g. optimize_cpu_usage() that only prints) and undefined helpers (buildAllocationMatrix, extractAllocation) with complete, executable examples or explicitly justified pseudocode, and add validation/verification steps to the optimization workflows.

Dimension	Reasoning	Score
Conciseness	At ~370 lines the body is padded with redundant sections ('Optimization Strategies' appears twice), generic capability bullets restating concepts Claude already knows (throughput, latency, caching), and oversized inline blocks (an ~80-line sandbox example and a full neural-training config); this matches the 'verbose; padded with unnecessary context' anchor rather than the 'mostly efficient' score-2 level.	1 / 3
Actionability	Real MCP tool names and parameter structures (e.g. mcp__sublinear-time-solver__solve with matrix/vector/method) provide concrete guidance, but the examples are littered with undefined helpers (buildAllocationMatrix, extractAllocation, createLoadBalancingMatrix) and stub methods that only print('Optimizing CPU usage...'), so they are not fully executable or copy-paste ready.	2 / 3
Workflow Clarity	The 'Example Workflows' sections give numbered sequences (Baseline Assessment → Bottleneck Identification → Optimization Planning → Implementation → Monitoring), but there are no validation checkpoints, feedback loops, or error-recovery steps; per the rubric, missing validation for optimization/batch operations caps this at 2.	2 / 3
Progressive Disclosure	There are no bundle files and no external references at all — everything (giant code examples, full capability listings, neural configs) is inline in a single ~370-line document; section headers give 'some structure', but content that should be split into separate files is inline, so it does not reach the score-3 'well-signaled one-level-deep references' level, and the under-50-line exemption does not apply.	2 / 3
	Total	7 / 12 Passed

Description

0%Weight 40%Scale 1-3

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 frontmatter description is pure boilerplate ('Agent skill for X - invoke with $X') that describes no capabilities, no trigger terms, and no use conditions, making it indistinguishable from any other agent skill. It fails every dimension and is not usable as a skill description.

Suggestions

Replace the boilerplate with concrete capabilities, e.g. 'Identifies performance bottlenecks, optimizes resource allocation, and profiles CPU, memory, network, and storage utilization across distributed systems and cloud infrastructure.'

Add an explicit 'Use when...' trigger clause with natural user phrasing, e.g. 'Use when the user reports slow systems, high resource utilization, or asks to optimize performance, load balancing, caching, or resource allocation.'

Remove the generic 'Agent skill for X - invoke with $X' template and the duplicate frontmatter block so the skill has a single, distinctive description unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for performance-optimizer - invoke with $agent-performance-optimizer' names only the domain and an invocation token; it states zero concrete actions, matching the 'vague or no actions; abstract language' anchor rather than the score-2 anchor which requires named actions.	1 / 3
Completeness	It answers neither 'what does this do' (beyond boilerplate) nor 'when should Claude use it' — there is no 'Use when...' clause and no described capability, so both halves are missing/very weak; it cannot reach score 2, which already requires a stated 'what'.	1 / 3
Trigger Term Quality	The only terms are the skill's own name and the '$agent-performance-optimizer' invocation token — not phrases a user would naturally say (e.g., 'slow system', 'bottleneck', 'optimize performance'), so it sits at the 'no natural keywords; technical jargon or overly generic' level.	1 / 3
Distinctiveness Conflict Risk	The text is generic boilerplate that could prefix any agent skill, offering no distinctive niche or triggers, which is the 'very generic; would conflict with many skills' anchor.	1 / 3
	Total	4 / 12 Passed

Validation

100%

Warnings & errors only

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/claude-flow
Path: .agents/skills/agent-performance-optimizer/SKILL.md
Commit: 913f9ea

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.