What types of decisions can I record?

The skill supports three primary decision states: 'approved', 'denied', and 'needs-review'.

Can I include comments or feedback with my decision?

Yes, there are optional fields for 'notes' and 'responded_by' to provide additional context or specific conditions regarding the decision.

What is the primary purpose of the Workflow Approval Responder skill?

It is designed to record formal decisions on approval requests, ensuring accountability and providing a clear audit trail for automated or semi-automated workflows.

Where are the approval records stored?

Responses are saved as Markdown files within the 'runtime/contexts/' directory, organized by context and session ID for easy retrieval.

Does this skill support human-in-the-loop workflows?

Yes, it is specifically built to capture human or supervisor decisions that gate automated processes, providing a bridge between AI execution and strategic oversight.

Workflow Approval Responder

Name: Workflow Approval Responder
Author: venikman

byvenikman

Productivity & Workflow

Records and audits formal approval decisions for session-based workflows to ensure governance and traceability.

About

The workflow-respond-to-approval skill provides a standardized mechanism for capturing decision-making logic within complex AI-driven workflows. By linking specific decisions—such as approved, denied, or needs-review—to unique session and approval identifiers, it ensures a high degree of auditability and gating. This skill is essential for maintaining a clear paper trail of strategic decisions, allowing teams to review the rationale and timing of every project milestone within the FPF Foundry ecosystem.

Key Features

Standardized decision recording (Approved, Denied, Needs-Review)
0 GitHub stars
Audit-ready Markdown response generation for documentation
Integration with U.Work logging for telemetry and reporting
Session-specific context tracking and identifier mapping
Deterministic output paths for predictable file management

Use Cases

Tracking human-in-the-loop decisions for AI-generated code modifications
Implementing formal sign-off stages in automated deployment pipelines
Maintaining compliance audit trails in highly regulated software environments

About

Key Features

Standardized decision recording (Approved, Denied, Needs-Review)
0 GitHub stars
Audit-ready Markdown response generation for documentation
Integration with U.Work logging for telemetry and reporting
Session-specific context tracking and identifier mapping
Deterministic output paths for predictable file management

Use Cases

Tracking human-in-the-loop decisions for AI-generated code modifications
Implementing formal sign-off stages in automated deployment pipelines
Maintaining compliance audit trails in highly regulated software environments