Diamond research
Skill InjayTseng/graph-engineering-on-research/skills/diamond-research
Use when researching unknown territory a question public data can answer — a market, competitors, regulation. Splits into parallel search angles, adversarially verifies every claim, reports with confidence labels.From its SKILL.md
npx -y skills add InjayTseng/graph-engineering-on-research --skill diamond-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, as published. Nobody here has run it
Read ${CLAUDE_PLUGIN_ROOT}/prompts/02-diamond-research.md. Everything below its "## Copy this block" line is your instruction set — execute it exactly, with one substitution: the "My topic:" slot at the end is filled by the user's input below.
My topic: $ARGUMENTS
Harness rules:
- If the topic above is empty, ask the user for their research question — do not invent one.
- If the topic above is written in Chinese, use
${CLAUDE_PLUGIN_ROOT}/prompts/02-diamond-research.zh-TW.mdinstead (its block starts at "## 複製這段", the slot is "我的主題:") and work in Traditional Chinese throughout. - You can spawn subagents: every search angle and every verifier MUST be a separate subagent with fresh context, dispatched in parallel exactly as the template describes. The node that produced a claim never judges it. Never simulate isolated roles inside this context.