Use when creating multi-step execution plans or processes — designs reusable, efficient workflows that coordinate agents, skills, tools, and external systems into reliable execution pipelines. Default skill for Starlight Orchestrator.
Scanned 6/11/2026
Install via CLI
openskills install frankxai/Starlight-Intelligence-System---
name: orchestration/workflow-design
description: Use when creating multi-step execution plans or processes — designs reusable, efficient workflows that coordinate agents, skills, tools, and external systems into reliable execution pipelines. Default skill for Starlight Orchestrator.
type: agent-orchestration
---
# Workflow Design
> *"A workflow is a promise: do these steps, get this result."*
## When This Skill Activates
- Creating multi-step execution plans or processes
- Keywords: "workflow", "process", "pipeline", "steps", "sequence", "automate"
- Default for: Starlight Orchestrator
## What This Skill Does
Designs reusable, efficient workflows that coordinate agents, skills, tools, and external systems into reliable execution pipelines.
## Procedures
### Procedure 1: Workflow Creation
1. Define the workflow's purpose and expected outcome
2. Identify all steps required
3. For each step: define input, action, output, owner
4. Identify dependencies between steps
5. Add error handling for each step
6. Add checkpoints for user verification (if needed)
7. Define success criteria for the workflow
### Procedure 2: Workflow Optimization
1. Map the current workflow
2. Identify bottlenecks (slowest steps)
3. Find parallelization opportunities
4. Remove unnecessary steps
5. Consolidate similar steps
6. Measure estimated vs actual execution time
7. Store optimization as pattern in Operational Vault
### Procedure 3: Workflow Template Creation
1. Identify a recurring workflow pattern
2. Abstract specific details into parameters
3. Document the template with clear parameter descriptions
4. Store in Operational Vault for reuse
5. Add to Orchestration Engine workflow templates
## Integration Points
- **Vault:** Operational Vault (workflow templates and patterns)
- **Agents:** Orchestrator (primary), all agents (as workflow participants)
- **Engine:** Orchestration Engine (execution)
## Quality Criteria
- Does each step have clear input, action, and output?
- Are dependencies explicit?
- Is error handling included?
- Is the workflow reusable?
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.