From empire-research
Decomposes complex claims into atomic verifiable components, resolves vague entities, verifies each independently, and separates facts from narrative interpretation. For fact-checking mixed-fact narratives.
npx claudepluginhub marcoskichel/empire --plugin empire-researchThis skill uses the workspace's default tool permissions.
<section id="core">
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Explores codebases via GitNexus: discover repos, query execution flows, trace processes, inspect symbol callers/callees, and review architecture.
Share bugs, ideas, or general feedback.
Complex claims combine verifiable facts with unverifiable interpretations. Effective investigation decomposes claims into atomic components, verifies each independently, and clearly distinguishes confirmed facts from narrative framing.
Difference from /empire-research:verify: dissect investigates external claims (social media, sources). verify checks AI-generated output for hallucinations.
Break the statement into individual verifiable claims. Each MUST be:
Example: Original: "The House Leader refusing to seat the newly-elected AZ-07 special election winner because she'd vote to release the Epstein files"
Atomic claims:
| Type | Description | Verifiability |
|---|---|---|
| ENTITY | Person, organization, place | Usually verifiable |
| EVENT | Something that allegedly happened | Often verifiable |
| STATE | Current condition or status | Usually verifiable |
| PROCESS | Official procedure or mechanism | Verifiable |
| CAUSATION | Claimed reason or motivation | Rarely verifiable |
| NARRATIVE | Interpretive framing | Not directly verifiable |
Note what's conspicuously absent: unnamed entities, unspecified dates, missing procedural context, absent opposing perspectives.
Convert vague references to specific, searchable terms before searching.
For each event: when did it allegedly occur? What is normal timeline for this type of event? Are there procedural deadlines?
Identify: primary actors (taking alleged actions), secondary actors (affected), official bodies with relevant authority, potential verification sources.
Start with most basic, verifiable claims:
Search strategy: official sources first (.gov, electoral bodies) → cross-reference multiple news sources → look for primary documents.
For any claimed action/inaction:
Causation requires direct evidence — "X happened" + "Y exists" does not confirm "X because Y."
Direct evidence: quoted statements from alleged actor, official statements or press releases, video/audio of relevant statements.
Indirect evidence: other explanations for observed facts, standard reasons for similar situations, procedural explanations.
Context: previous positions by involved parties, historical precedents, timeline compatibility.
Priority order:
For each source, note: type (official / news / advocacy / social media), date relative to events, whether claims are attributed, presence of supporting documentation, corrections or updates issued.
Document bias without dismissing: source's typical alignment, stakeholder relationships, pattern of coverage, language choices (neutral vs. charged).
Patterns indicating narrative rather than fact:
For each narrative: what facts support it? What facts complicate it? What alternative narratives explain the same facts? What facts are excluded?
VERIFIED FACTS:
- [Fact] (Source: [citation], Confidence: Certain/Probable/Possible)
DISPUTED / UNCLEAR:
- [Claim]:
- Supporting: [source]
- Contradicting: [source]
- Unable to verify: [what's missing]
CONTEXT NEEDED:
- [Procedural context]
- [Historical precedent]
NARRATIVE ELEMENTS (not directly verifiable):
- [Claim]
- Facts that support: [list]
- Facts that complicate: [list]
- Alternative explanations: [list]
Confidence levels:
| Level | Meaning |
|---|---|
| Certain | Multiple primary sources confirm |
| Probable | Multiple credible sources align, no contradictions |
| Possible | Some evidence supports, gaps remain |
| Unclear | Contradictory evidence or insufficient info |
| False | Contradicted by authoritative sources |
Confirmation Rush — finding one source that matches the claim and declaring it verified. Fix: require 2-3 independent sources. Trace claims back to primary sources. Check if "multiple sources" are repeating the same original.
Causation Collapse — accepting "X happened because Y" when only "X happened" and "Y exists" are verified. Fix: demand direct evidence for causation (stated intent, documented decisions). Report as "alleged motivation" when causation can't be verified.
Premature Debunking — finding one fact wrong and dismissing the entire claim. Complex claims often mix true and false elements. Fix: decompose fully, verify each component independently.
Authority Fallacy — accepting official sources uncritically. Official sources can be wrong, incomplete, outdated, or misleading. Fix: cross-reference official sources; distinguish "official position" from "verified fact."
Narrative Anchoring — starting with a hypothesis and investigating to prove it. Fix: start with specific claims as stated. Investigate each on its own terms. Actively seek disconfirming evidence.