Agent skill for workflow - invoke with $agent-workflow
51
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 95%
↑ 2.43xAgent success when using this skill
Validation for skill structure
Workflow creation API usage
Correct create function
0%
100%
Step id field
100%
100%
Step action field
0%
100%
Step agent field
0%
100%
Triggers configured
100%
100%
Correct execute function
0%
100%
Async execution flag
0%
100%
Correct status function
0%
100%
Metrics included in status
0%
100%
Error handling present
100%
44%
Specialized agent types
0%
100%
Without context: $0.6483 · 2m 51s · 33 turns · 689 in / 9,935 out tokens
With context: $0.3787 · 1m 35s · 22 turns · 25 in / 5,019 out tokens
Workflow execution and monitoring
Correct create function
0%
70%
Steps with id/action/agent
12%
100%
Parallel extraction steps
100%
100%
Correct execute function
0%
75%
Async flag in execute
0%
100%
Input data passed
33%
100%
Correct status function
0%
75%
Metrics in status call
0%
100%
Rollback/error recovery
100%
100%
Logging/audit trail
100%
100%
Trigger configuration
0%
100%
Specialized agent types
87%
100%
Without context: $0.6832 · 2m 25s · 29 turns · 100 in / 8,456 out tokens
With context: $0.4150 · 1m 47s · 20 turns · 272 in / 5,908 out tokens
Agent assignment and workflow design approach
Requirements analysis section
75%
100%
Architecture section
100%
100%
Agent integration section
62%
100%
Trigger configuration section
100%
100%
Error handling section
0%
100%
Correct create function
100%
88%
Event-driven trigger
100%
100%
Correct agent assign function
0%
90%
Vector similarity flag
0%
100%
Specialized reviewer agent types
33%
100%
Steps with id/action/agent
25%
100%
Audit trail or logging
100%
100%
Without context: $0.9128 · 3m 39s · 41 turns · 1,162 in / 12,426 out tokens
With context: $0.4336 · 1m 47s · 22 turns · 182 in / 6,495 out tokens
Table of Contents
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.