CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-orchestrator-task

Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

34

1.32x
Quality

3%

Does it follow best practices?

Impact

82%

1.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-orchestrator-task/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

78%

14%

User Notification System: Launch Orchestration

Feature development orchestration plan

Criteria
Without context
With context

Phase 1 sequential

0%

100%

Design+spec parallel

37%

25%

Impl+tests parallel

75%

100%

Integration+docs parallel

37%

50%

Final phase sequential

100%

100%

Dependency rationale

100%

100%

TodoWrite tracking

0%

100%

Parallelization maximized

100%

100%

No over-decomposition

50%

50%

Logical subtask grouping

100%

100%

5-phase structure

100%

0%

Clear task decomposition

100%

100%

78%

37%

Critical Payment Processing Bug: Orchestrated Response

Bug fix orchestration with memory and priority

Criteria
Without context
With context

Phase 1 sequential

25%

62%

Fix+test parallel

12%

100%

Verify+document parallel

25%

0%

Deploy+monitor sequential

100%

100%

memory_store usage

0%

100%

memory_search retrieval

0%

100%

Specific memory keys

100%

100%

Dynamic re-planning

90%

100%

Priority management

37%

100%

4-phase structure

37%

62%

No artificial constraints

83%

100%

TodoWrite mentioned

0%

0%

92%

11%

Legacy Codebase Modernization: Refactoring Coordination

Refactoring orchestration with adaptive strategy

Criteria
Without context
With context

Phase 1 sequential

100%

100%

Parallel refactoring phase

100%

100%

Parallel testing phase

75%

100%

Final integration sequential

87%

100%

4-phase structure

62%

100%

Multi-level orchestration discussed

100%

100%

Over-decomposition avoided

100%

100%

Adaptive strategy referenced

37%

50%

Balanced execution

100%

100%

Natural task boundaries

100%

100%

Sequencing rationale

100%

100%

TodoWrite tracking

0%

50%

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.