Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jamestorrevillas/research-synthesis
Use this skill when researching technologies, synthesizing multiple sources, evaluating tech stack decisions, comparing frameworks, or writing technical research summaries. Trigger on keywords: research, compare, evaluate, which is better, technology decision, should I use, pros and cons, synthesis, stack decision.
Passed 16 of 22 test cases with the skill, and 9 of 22 without it.
and 5 more in the full report
7 fixed9 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are deciding whether to migrate our backend API from Express to Fastify or NestJS for higher throughput. Could you evaluate these frameworks and write a formal recommendation document? Make sure to outline our scenario, provide a comparison grid rating each option across operational fit, team familiarity, performance, and long-term risk, clearly state the chosen tech, detail any trade-offs we must accept, and list specific trigger conditions that would make us reconsider the choice.
| Checked | Without skill | With skill |
|---|---|---|
| The response includes a 'Trade-offs Accepted' section heading. | Missed | Passed |
| The options comparison matrix includes a row for Maturity. | Missed | Passed |
The instructions your model reads when the skill loads.
1. DEFINE — What specific question am I trying to answer?
2. GATHER — Collect sources (docs, benchmarks, community, real usage)
3. EVALUATE — Assess source quality and recency
4. SYNTHESIZE — Extract patterns and insights across sources
5. DECIDE — Apply findings to your specific context
6. DOCUMENT — Record the decision and reasoning for future reference
For every technology comparison:
| Dimension | What to Evaluate |
|---|---|
| Fit | Does it solve your actual problem? |
| Maturity | Production-proven or experimental? |
| Community | Active maintenance, GitHub stars, Stack Overflow presence |
| Performance | Benchmarks relevant to your use case |
| Learning Curve | Team familiarity, documentation quality |
| Ecosystem | Integrations, libraries, tooling |
| Cost | License, infrastructure, ops overhead |
| Exit Cost | How hard to migrate away if needed? |
## Decision: [technology choice]
### Context
[What problem are we solving? What are our constraints?]
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.