Agentic Workflow Automation

Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff arti...

Security Scan

The skill's code, instructions, and file list are consistent with its stated purpose of generating workflow blueprints and do not request extra credentials, network access, or surprising installs.

Purpose & Capability

Name/description match the included assets: a workflow guide, an OpenAI agent manifest, and a small Python script that normalizes and exports workflow blueprints. Nothing in the files suggests functionality beyond blueprint generation and export.

Instruction Scope

SKILL.md simply directs the agent to read the guide and run the bundled script. The script only reads a user-supplied input file (if provided), enforces a 1MB input size limit, normalizes step data, and writes an output artifact in json/md/csv. There are no instructions to access unrelated system files, network endpoints, or secrets.

Install Mechanism

There is no install spec; this is instruction-only plus a small Python script using only standard library modules. No external downloads, package installs, or archive extraction are present.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. The code does not read environment variables or attempt to access credentials.

Persistence & Privilege

The skill is not 'always' enabled and does not modify other skills. Model invocation is allowed (platform default), which means an agent could call this skill autonomously — this is normal for skills and not by itself problematic.

Assessment

This skill appears coherent and low-risk: it only processes an input JSON you provide and writes a chosen output file. Before running: (1) review the output path you supply to avoid overwriting sensitive files, (2) only feed trusted input files (script will read whatever path you give it up to 1MB), and (3) if you prefer to prevent autonomous agent use, restrict model-invocation or only call the skill manually. If you need higher assurance, run the Python script in an isolated environment and inspect its output.

Overview

Build workflow blueprints that can be translated into automation platforms such as n8n or internal orchestrators.

Workflow

1. Define workflow name, trigger, and ordered steps.
2. Normalize each step into a simple execution contract.
3. Build a blueprint with dependencies and execution order.
4. Export JSON/markdown artifacts for implementation.

Use Bundled Resources

• Run scripts/generate_workflow_blueprint.py for deterministic workflow output.
• Read references/workflow-blueprint-guide.md for step design guidance.

Guardrails

• Keep each step single-purpose.
• Include clear fallback behavior for failed steps.