Evidence and source evaluation
Digital Research Skills: Evidence-Led Research and Source Evaluation
A public research operating system for investigations, OSINT, due diligence, source verification, analysis, synthesis, and decision-ready outputs.
Inspect on GitHub Digital Research SkillsRepository facts verified locally on 22 August 2026
Direct answer
Digital Research Skills helps a researcher move from a question to a defensible output without allowing unsupported names, statistics, quotes, laws, or URLs into the final work. It separates discovery, targeted gap-filling, verification, peer review, synthesis, and product mapping.
Who it serves
Researchers, analysts, consultants, journalists, academics, policy teams, due-diligence teams, and organisations that need traceable evidence.
60
Local SKILL.md files verified
Evidence
Primary discipline
Decision-ready
Core output
main
Repository branch
Non-negotiable operating rule
Human in the middle. Every time.
Nothing is considered finished merely because an AI tool or skills engine produced it. A responsible person reviews the facts, logic, sources, calculations, code, security, privacy, context, and quality of the output before it is published, deployed, submitted, or used to make a decision. For some actions, the engine must stop until the user explicitly types that they approve the action; approval must never be inferred from silence or a vague request.
Human responsibility: approve, correct, escalate, reject, stop, or roll back the work.
Engine responsibility: make the method, evidence, limits, review points, and approval pauses visible.
In practice
A second view of the work this engine supports
The visuals illustrate the domain; they do not replace evidence, controls, or the human review required before a consequential decision or action.
Capability map
What this engine covers
The list below is a plain-language summary of the repository's verified capability surface. It is not a promise that every project needs every skill.
- Wave-based research orchestration: broad sweep, targeted gaps, verification, peer review, synthesis, and product mapping.
- Source evaluation, currentness checks, URL liveness, statistic re-checking, quote confirmation, and uncertainty handling.
- OSINT, due diligence, primary research, research design, data-quality work, web research, and scraping foundations.
- Executive, academic, consulting, and client-facing outputs with source and evidence discipline.
How to use it
A repeatable route from request to evidence
Define the question
State the decision, audience, scope, time window, jurisdiction, source needs, and what would count as a useful answer.
Sweep and gap-fill
Run a broad source sweep, then target the gaps rather than collecting links without a decision purpose.
Verify claims
Check source quality, currency, URL liveness, figures, quotations, and uncertainty before synthesis.
Synthesize honestly
Separate facts, inferences, hypotheses, and unknowns in a structured output that a reviewer can audit.
Good fit
When to use this engine
- You are preparing a due-diligence, OSINT, market, policy, literature, or competitor research product.
- An AI-assisted report needs a stronger anti-hallucination and source-evaluation workflow.
- A decision depends on current laws, standards, market facts, platform claims, or other changing evidence.
- A client needs a concise evidence pack rather than a link dump or generic AI summary.
Boundaries
What it does not replace
- It does not replace legal, accounting, tax, medical, security, or other qualified professional review.
- A source that is unavailable, stale, unattributable, or unverified is recorded as a gap, not silently treated as fact.
- It does not create evidence merely by writing confidently; source claims and project facts still need verification.
- It does not remove accountable human review, specialist judgement, approval authority, or professional sign-off.
- It does not authorise live account changes, client communications, production changes, or submissions without explicit permission.
Continue the route
Related first-party guidance
Chwezi Dev Engine
Use the engineering engine when research turns into software, AI, data, or infrastructure implementation.
Business Plan Skills
Use the planning engine when verified research must become a feasibility, investment, or implementation plan.
Research and source discipline
Inspect the public repository for the source-evaluation and research-orchestration skills.
Frequently asked
Questions about Digital Research Skills
How does Digital Research Skills reduce hallucinations?
It requires claims, names, URLs, figures, and quotations to be traceable to verified sources, and it distinguishes unavailable evidence from confirmed evidence.
What are the research waves?
The documented flow is broad sweep, targeted gap-fill, verification, peer review or structured analytic technique, synthesis, and product mapping.
Can this engine produce a bankable or legal conclusion?
It can organise evidence and uncertainty, but professional finance, legal, tax, regulatory, or other specialist review remains necessary.
Ready to discuss your project?
Every engagement begins with a conversation. Book a consultation to explore how Peter's experience can serve your organisation.