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.

75

1.15x
Quality

62%

Does it follow best practices?

Impact

97%

1.15x

Average score across 3 eval scenarios

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

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 treatment of multi-agent optimization dominated by conceptual restating and non-executable skeleton code rather than lean, actionable guidance. Its clearest strengths are an organized section structure and a recognizable step sequence, but both need tightening and concrete validation.

Suggestions

Remove the 'Role/Context/Core Capabilities' framing and abstract capability bullets; lead with a concise procedure and keep only what Claude cannot infer.

Replace the skeleton code with runnable examples or clearly justified stubs, defining or importing the helpers they rely on (semantic_truncate, aggregate_performance_metrics, concurrent, etc.).

Make the orchestration-change workflow's validation explicit with concrete checkpoints and a validate-fix-retry loop given its destructive nature.

DimensionReasoningScore

Conciseness

The body is padded with role-play framing and conceptual fluff ('Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach...'), abstract capability bullets Claude already knows, and redundant vague four-step lists (Instructions, Key Considerations, Reference Workflows).

1 / 3

Actionability

Code blocks give structural guidance but are not executable: they call undefined helpers (semantic_truncate, aggregate_performance_metrics, PriorityQueue, PerformanceTracker) and select_optimal_model is just 'pass', matching the level-2 pseudocode/incomplete anchor.

2 / 3

Workflow Clarity

A four-step sequence exists and validation is mentioned ('Validate improvements with repeatable tests and rollbacks'), but checkpoints are implicit and lack concrete commands, and destructive orchestration changes warrant explicit validate-fix-retry loops that cap this at 2.

2 / 3

Progressive Disclosure

No bundle files exist and the 240-line body is monolithic with all technique sections and code inline; section headers give some structure but content that should be split into referenced files is not, matching the level-2 anchor.

2 / 3

Total

7

/

12

Passed

Description

90%

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 clear, well-structured description that covers what and when with natural trigger terms and a distinct multi-agent niche. The only weakness is that its named actions lean toward capability-bucket jargon rather than concrete operations.

DimensionReasoningScore

Specificity

Names the domain and several action areas ('coordinated profiling, workload distribution, and cost-aware orchestration'), but these are capability categories and light jargon rather than concrete verbs on concrete objects like the level-3 anchor.

2 / 3

Completeness

It states what the skill does ('Optimize multi-agent systems with...') and an explicit 'Use when...' clause for when to apply it, satisfying both halves at level 3.

3 / 3

Trigger Term Quality

'Use when improving agent performance, throughput, or reliability' supplies natural phrasings a user would actually say, matching the level-3 anchor's good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

The 'multi-agent systems' framing plus performance/throughput/reliability triggers carve a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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
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.