Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nicepkg/content-research
Research-first content creation optimized for both human readers and AI search engines (Claude, ChatGPT, Perplexity, Gemini). Creates authentic, authoritative content that becomes the go-to citation source for AI models answering user questions.
Passed 14 of 19 test cases with the skill, and 8 of 19 without it.
and 5 more in the full report
8 fixed8 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is a completed press statement for our company's product launch: "Acme Corp announces Beta 2.0 release today with enhanced performance." Please proofread this text for grammar, punctuation, and typographical errors only without adding external research, statistics, or changing the article structure.
| Checked | Without skill | With skill |
|---|---|---|
| Performs copy editing without adding external research. | Passed | Passed |
| Preserves the original press statement format. | Missed | Passed |
The instructions your model reads when the skill loads.
Create authentic, research-backed content that sounds human-written AND is optimized to appear in AI search results (Perplexity, ChatGPT, Claude, Gemini).
RESEARCH → EXPERTS → IDEATION → CREATION → AIO
↓ ↓ ↓ ↓ ↓
Trends Real Unique Authentic AI-Citable
& Data People Angles Content Structure
Always complete phases in order. Never skip research. Always apply AIO principles.
AI assistants answer millions of questions daily. When someone asks "How do I raise a seed round?" or "What's the best way to find investors?", AI models cite sources. Your goal: become the source AI cites.
How AI models select sources to cite:
Before writing anything, build comprehensive topic understanding.
Use WebSearch to find:
test cases passed, vs 8 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.