empire-research

These agents are adapted from upstream open-source projects under the MIT

Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting.

Trigger when user says: "compare libs", "compare frameworks", "/empire-research:compare", "evaluate options", "side by side", "head to head", "X vs Y", "which is better", "tooling comparison", "weigh these options", "decide between these". Closed comparison of tools, libraries, frameworks, vendors, or architectural choices — NOT competitors (use `/empire-product:recon` for competitor mapping). User already has a known set of options; skill produces a side-by-side matrix across user-defined dimensions and recommends a winner. Findings stay local — never posted externally.

Systematically investigate complex claims by decomposing them into atomic verifiable components, resolving vague entities, verifying each component independently, and separating confirmed facts from narrative interpretation. Use when fact-checking complex claims, investigating narratives that mix facts with interpretation, or when a claim bundles multiple assertions. Trigger phrases: "investigate this claim", "fact-check this", "is this true", "decompose this narrative", "viral content check", "trace this claim", "/empire-research:dissect". Findings stay local — never post to GitHub.

Trigger when user says: "explore options", "what could we do for X", "research approaches", "/empire-research:explore", "investigate approaches", "spawn research team", "what are the options", "options analysis", "explore solutions", "have the team explore". Open-ended exploration: shallow scan to enumerate 3–5 candidate approaches, user picks subset to deep-dive, parallel research per approach, consolidated comparison with a recommended direction. Findings stay local — never posted externally.

Run a systematic verification pass on generated content to catch hallucinations, confabulations, and unsupported assertions. MUST be a separate pass — cannot be reliably combined with content generation in the same pass. Use after research synthesis, after content generation, or whenever accuracy of claims matters before delivery. Trigger phrases: "fact-check this", "verify these claims", "check for hallucinations", "second pass on accuracy", "verify the output", "is this accurate", "/empire-research:verify". Findings stay local — never post to GitHub.