Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bartsoj/ORCHESTRATOR_CREATOR.md
Design and create an orchestration agent that autonomously executes a multi-skill workflow.
Passed 14 of 22 test cases with the skill, and 5 of 22 without it.
and 21 more in the full report
10 fixed4 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is the agent definition `agents/data-pipeline.md` and the input files `dataset.csv`. Please execute this orchestration agent right now, run the subagents, and generate the final report in `output/final_report.md`.
| Checked | Without skill | With skill |
|---|---|---|
| The response declines to execute the workflow agent or run subagents. | Missed | Passed |
| The response explains that orchestrators must be executed within an execution environment. | Missed | Passed |
The instructions your model reads when the skill loads.
Given a set of skills and a workflow describing how they connect, produce an orchestration agent as a single flat markdown file — agents/{agent-name}.md — that can autonomously execute the workflow end-to-end by authoring dynamic workflows that spawn a subagent per skill, reading their output files, making decisions, and managing feedback loops. The agent never does the skill's job. It invokes, inspects, decides, and proceeds.
Agent creation follows four phases: map, design, write, and validate.
Analyze the skills and workflow to build a complete picture. For each skill, identify:
| Property | Question to answer |
|---|---|
| Inputs | What files does this skill read? User-provided or from earlier skills? |
| Output | What file does it produce? Exact filename? |
| Dependencies | Which skills must complete first? |
| Parallelism | Can multiple instances run concurrently? Under what conditions? |
| Success criteria | How do you know the output is good? Verdicts, section checks, test results? |
| Failure modes | What goes wrong? What does bad output look like? |
| Feedback target | If problems surface, which earlier skill gets re-run? |
Draw the workflow as a directed graph (ASCII art). Mark feedback loops explicitly. This becomes the skeleton of the agent's decision logic.
Example:
ANALYZE.md → DESIGN.md → BUILD.md → TEST.md → DEPLOY.md
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.