CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-orchestration-multi-agent-optimize

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-orchestration-multi-agent-optimize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 over-padded with marketing fluff and buzzword bullets, and its code examples are non-executable pseudocode. Workflows are sequenced but lack concrete validation checkpoints, and no progressive disclosure to separate reference materials is used despite the volume of content.

Suggestions

Strip the marketing paragraph and buzzword-only bullet lists ('Core Capabilities', 'Optimization Spectrum'); keep only guidance Claude does not already know.

Replace pseudocode with executable snippets or explicitly justify the abstraction, defining or stubbing the referenced classes/functions so examples are copy-paste runnable.

Add concrete validation commands/checkpoints to the Instructions workflow (e.g. specific benchmark commands, pass/fail thresholds) and move the eight per-technique sections into separate reference files linked from the overview.

DimensionReasoningScore

Conciseness

The body is noticeably verbose with padded marketing prose ('advanced AI-driven framework designed to holistically improve system performance') and long bullet lists of buzzword concepts Claude already knows ('Intelligent multi-agent coordination', 'Adaptive optimization strategies'), fitting the score-2 anchor of several unnecessary padded sections; not severe enough for 1 because some code examples exist.

2 / 5

Actionability

Code blocks resemble real Python but are non-executable pseudocode relying on undefined names (DatabasePerformanceAgent, semantic_truncate, PerformanceTracker, PriorityQueue) and one method is just 'pass', matching the score-3 anchor of pseudocode instead of executable code with missing key details.

3 / 5

Workflow Clarity

The 4-step Instructions list provides a rough sequence and a validation step ('Validate improvements with repeatable tests and rollbacks'), but checkpoints are implicit and no concrete commands are given, matching the score-3 anchor; the batch/destructive context keeps it capped at 3 despite the Safety section.

3 / 5

Progressive Disclosure

The body has clear section structure (## 1-8) but is a ~240-line monolith with all content inlined and zero references to separate files, and no bundle files exist; much of the per-technique detail could live in reference files, fitting the score-3 anchor of some structure with content that should be separate kept inline.

3 / 5

Total

11

/

20

Passed

Description

83%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.

A strong, well-formed description that clearly states capability and explicit usage triggers in third person. The main weakness is mild buzzword-adjacent abstraction in the action list and some trigger-term synonym gaps.

DimensionReasoningScore

Specificity

Names the domain and several specific actions — 'coordinated profiling, workload distribution, and cost-aware orchestration' — matching the score-4 anchor of several specific actions with minor gaps, though the terms lean slightly abstract rather than fully concrete.

4 / 5

Completeness

It explicitly answers both 'what' ('Optimize multi-agent systems with...') and 'when' ('Use when improving agent performance, throughput, or reliability') with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

The 'Use when improving agent performance, throughput, or reliability' clause provides good, natural keyword coverage a user would actually say, missing only a few synonyms (e.g. latency, cost, bottlenecks) that would push it to 5.

4 / 5

Distinctiveness Conflict Risk

'Multi-agent systems' is a clear, fairly distinct niche, but the 'when' triggers (agent performance, throughput, reliability) could overlap with general single-agent optimization skills, so it sits at 4 rather than 5.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-skills
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.