Agent Workflow Controller
by Roy Yuen
Design and audit complex multi-agent workflows with rigorous ownership, evidence gates, and failure recovery policies.
- Structure complex coding tasks into implementation and verification phases.
- Design approval-gated workflows for destructive production operations.
- Audit existing agent prompts to identify gaps in logic and ownership.
Free
Sample input
Design a workflow for fixing the JWT leak in /src/auth/ that separates implementation from security review and requires passing test logs for verification.
Sample output
Workflow Type: Implementation -> Review -> Verify
Roles
| Role | Owns | Must Not Do | |---|---|---| | Implementer | /src/auth/ | Edit /tests/ | | Reviewer | Security Audit | Modify code |
Verification Plan
| Claim | Method | Evidence |
|---|---|---|
| JWT fix | npm test | Test pass logs |
Agent Workflow Controller
by Roy Yuen
Design and audit complex multi-agent workflows with rigorous ownership, evidence gates, and failure recovery policies.
Free
Included in download
- Downloadable skill package
- Works with Claude Code, OpenClaw
- Instant install
Sample input
Design a workflow for fixing the JWT leak in /src/auth/ that separates implementation from security review and requires passing test logs for verification.
Sample output
Workflow Type: Implementation -> Review -> Verify
Roles
| Role | Owns | Must Not Do | |---|---|---| | Implementer | /src/auth/ | Edit /tests/ | | Reviewer | Security Audit | Modify code |
Verification Plan
| Claim | Method | Evidence |
|---|---|---|
| JWT fix | npm test | Test pass logs |
Screenshots
About This Skill
What it does
The Agent Workflow Controller is a sophisticated architectural skill designed for developers and AI orchestrators who need to manage complex, multi-step, or multi-agent tasks. It acts as the "operating system" for your agent's logic, transforming vague requests into structured execution plans with defined phases, roles, and boundaries.
Problem it solves
Standard LLM prompts often struggle with "agentic drift," where agents duplicate work, provide unverifiable outputs, or fail during handoffs. This skill prevents collaboration breakdown by enforcing ownership, explicit exit gates, and evidence-based verification. It moves beyond simple prompting by introducing professional workflow engineering—ensuring your agents act with the precision of a coordinated team rather than a single black box.
Supported Workflows
- Discovery-Execute-Verify: For tasks where the state is unknown.
- Approval-Gated: For high-risk, destructive, or financial operations.
- Parallel Slice: For independent sub-tasks requiring disjoint ownership.
- Failure-Repair Loop: For systematic debugging when a process fails.
The Output
The skill produces a comprehensive Workflow Plan. This includes a mission statement, complexity classification, a role/purpose matrix, ownership maps for files and decisions, and concrete verification plans that tie every claim to specific evidence (logs, diffs, or citations).
Use Cases
- Structure complex coding tasks into implementation and verification phases.
- Design approval-gated workflows for destructive production operations.
- Audit existing agent prompts to identify gaps in logic and ownership.
- Coordinate multi-agent research tasks to prevent duplicated effort.
Known Limitations
- Planning only; does not execute code or launch sub-agents.
- Best suited for complex logic; adds unnecessary overhead to simple tasks.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/agent-workflow-controller -o /tmp/agent-workflow-controller.zip && unzip -o /tmp/agent-workflow-controller.zip -d ~/.claude/skills && rm /tmp/agent-workflow-controller.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Claude Code, OpenClaw, and SKILL.md-compatible agents.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
cinematic-sites
Turn any basic business URL into a high-end cinematic landing page with AI-generated 4K assets and GSAP animations.
Multi-Agent Orchestration Master Library
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.
endless-loop
Autonomous research and task loop that builds on previous findings to solve complex objectives while you sleep.
skill-router-2
Automatically detect, load, and stack the perfect skills combo for any user request.