evidence-researcherlisted

Build auditable Evidence Packs for consequential research, fact-checking, due diligence, verification, and cross-skill evidence handoff. Use when ChatGPT must decompose a question into material claims, inspect primary or system-of-record sources, verify currentness/effective dates/versions, distinguish source artifacts from claim-specific evidence, search for falsifiers and negative evidence, resolve contradictions, detect derivative or non-independent sources, identify evidence gaps, compare evidence deltas, or prepare reusable evidence for AI Council, product, technical, audit, SEO/GEO/AEO, sales, or customer workflows. Do not use for casual single-fact lookup or as the final decision-maker when a dedicated decision skill exists.
MaciejZet/agent-skills · ★ 1 · AI & Automation · score 74

Install: claude install-skill MaciejZet/agent-skills

# Evidence Researcher v2 Reusable evidence intelligence layer. Produce a traceable substrate for downstream reasoning — not a pile of links and not a governance verdict. ## Progressive disclosure This file is the contract only. Load detail by stage: | Stage | Load | | --- | --- | | Responsibility / stop | Boundary + Hard rules below | | Framing | `references/research-contract.md` | | Graph model | `references/evidence-graph.md` | | Authority routing | `references/source-routing.md` | | Provenance / independence | `references/source-lineage.md` | | Falsifiers / contradictions | `references/contradiction-protocol.md` | | Temporal truth | `references/freshness.md` | | Mode / stop | `references/modes-stop-rule.md` | | Output | `references/output-contract.md` | | Downstream handoff | `references/integrations.md` | | Privacy / injection | `references/privacy-provenance.md` | | CLI cookbook | `references/kernel-cli.md` | | Migration | `references/migration-v1-v2.md` | | Eval invariants | `references/evaluation.md` | ## Boundary **Owns:** research framing, atomic claims, source-authority routing, provenance/lineage, claim-specific evidence edges, temporal truth, falsifier pass, contradictions, gaps, refresh/delta, readiness. **Does not own:** final business/product/legal/security decision when another skill is responsible. `question → evidence-researcher → Evidence Pack → domain/decision skill → recommendation` Never auto-promote `verified_for_research` to `verified_for_deci