[Resource]: WRITE THE NAME OF YOUR RESOURCE HERE #933
Description
Display Name
operator-agents
Category
Agent Skills
Sub-Category
General
Primary Link
https://github.com/fatihkutlar/operator-agents
Author Name
fatihkutlar
Author Link
https://github.com/fatihkutlar
License
MIT
Other License
No response
Description
Production-grade library of 66 AI agents with enforced YAML frontmatter
schema (AGENT_SPEC.md). Every agent declares tools.required, context.required,
output.format, and pipeline.handoff_to — making agents machine-parseable and
composable. Includes 5 multi-agent pipeline definitions with Mermaid diagrams
and typed JSON data contracts. Verticals: ecommerce, SaaS, agency, finance,
automation. 6-runtime support: Claude Code, Codex, Gemini CLI, Cursor, Aider,
raw API. MIT.
Validate Claims
Clone the repo and inspect any agent file:
git clone https://github.com/fatihkutlar/operator-agents
cat operator-agents/agents/engineering/code-reviewer.md
You'll see YAML frontmatter declaring tools.required, context.required, output.format, and pipeline.handoff_to. Then inspect a pipeline:
cat operator-agents/pipelines/product-launch.md
You'll see a Mermaid diagram and typed JSON data contracts between agents. Total verification time: under 2 minutes.
Specific Task(s)
Install the ecommerce vertical agents and run a product launch pipeline.
Specific Prompt(s)
First, in your terminal:
git clone https://github.com/fatihkutlar/operator-agents ~/.claude/agents/operator-agents
Then open Claude Code in any project and say:
"Look at the agents in ~/.claude/agents/operator-agents/verticals/ecommerce/ and tell me what tools each agent requires and what it hands off to next. Then use the product-launch pipeline to outline the launch steps for a fictional SaaS product."
Expected result: Claude reads the YAML frontmatter from each agent file, reports the typed schema (tools, context, output format, handoff targets), and walks through the pipeline stages with the correct agent sequence.
Additional Comments
v1.0.0 released March 2026. MIT licensed. 66 agents across 10 divisions + 5 verticals. The key differentiator vs other agent collections is AGENT_SPEC.md — an enforced schema that makes every agent machine-parseable, not just human-readable. Includes strip-frontmatter.sh for raw API use and parse-agents.sh for programmatic extraction.
Recommendation Checklist
- I have checked that this resource hasn't already been submitted
- It has been over one week since the first public commit to the repo I am recommending
- All provided links are working and publicly accessible
- I do NOT have any other open issues in this repository
- I am primarily composed of human-y stuff and not electrical circuits