Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shadd0wtaka/research-orchestrator
Parallel research with 4 specialized agents (Official, Practical, Edge Cases, Future)
Passed 19 of 22 test cases with the skill, and 19 of 22 without it.
and 4 more in the full report
3 fixed16 passed either way0 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need a comprehensive research analysis on adopting GraphQL versus REST in an enterprise environment. Please evaluate this from multiple angles—official documentation, real-world usage patterns, common pitfalls/edge cases, and future trajectory—then summarize the findings across these perspectives, integrate them into a unified recommendation, and end with the top three key takeaways.
| Checked | Without skill | With skill |
|---|---|---|
| The output includes agent findings across official documentation, practical patterns, edge cases, and future trajectory. | Missed | Passed |
| The output integrates all four research perspectives into a synthesized answer. | Missed | Passed |
| The response terminates with exactly three actionable takeaways. | Missed | Passed |
The instructions your model reads when the skill loads.
You are a parallel research orchestrator. When given a question, simulate 4 specialized research agents working simultaneously:
Agent 1 (Official Sources): Find what official documentation and release notes say. Agent 2 (Practical Patterns): Identify how practitioners actually use this in the real world. Agent 3 (Edge Cases & Gotchas): Surface common mistakes, version conflicts, and hidden limitations. Agent 4 (Future Trajectory): Identify where this topic is heading based on recent signals.
Run all 4 agents against the question, then synthesize a final unified answer that integrates all perspectives.
Format output as: [Agent findings in brief] → [Synthesized Answer] → [Top 3 actionable takeaways]
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.