# Source Evaluation

> Judge whether a source is credible and relevant: authority, evidence, bias, and recency. Use when deciding whether to trust and cite a source, in any research.

- Skill: `amey-thakur/source-evaluation` (Agent Skill)
- Install (CLI): `npx skillmds@latest add amey-thakur/source-evaluation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/amey-thakur/source-evaluation/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: Amey-Thakur (https://skillmd.com/u/amey-thakur)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/amey-thakur/source-evaluation

---


# Source evaluation

Not all sources deserve equal trust, and the credible-looking ones are
often the trap. Source evaluation is the habit of asking, before you rely
on anything, who is behind it, what backs their claim, what they want you
to believe, and whether it is current, so your conclusions rest on solid
ground.

## Method

1. **Identify the author and their authority.** Who produced this, and are
   they in a position to know? Expertise, credentials, and a track record
   in the specific domain matter; a confident stranger and a domain expert
   are not equal. Anonymous or unattributed claims start at low trust (see
   web-research's lateral reading to check them).
2. **Check the evidence behind the claim.** Does the source show its work
   (data, citations, methodology, primary references) or just assert? A
   claim with checkable evidence beats an eloquent one without. Follow the
   citations: a source citing strong primary evidence is stronger than one
   citing nothing or citing other opinions (see reading-papers,
   writing-with-evidence).
3. **Assess bias and motivation.** What does the source want, and how might
   that shape what they say? A vendor on their own product, an advocate for
   their cause, an outlet with a known slant: bias does not make a source
   wrong, but it tells you what to scrutinize and where to seek a
   counter-source. Follow the incentives (see mental-models' incentives).
4. **Weigh source type by the claim.** Peer-reviewed research and official
   primary data for facts; reputable journalism for events; practitioner
   accounts for real-world experience; forums and social media for leads,
   not conclusions. Match the source's authority to the weight of the
   claim you are hanging on it.
5. **Check recency and currency.** Is it current enough for a claim that
   changes over time (technology, prices, best practices, contested
   science)? An authoritative source from years ago can be authoritatively
   outdated. Note the date and whether newer work supersedes it.
6. **Prefer the primary and corroborated.** Trace claims to their origin
   rather than trusting the retelling (see web-research), and for important
   or contested claims, require independent corroboration (see
   fact-checking). A single source, however credible, is a single point of
   failure.

## Boundaries

- Evaluation manages risk; it does not make any source certain. Even good
  sources err, so keep your confidence proportional to the evidence and
  flag uncertainty (see the honesty ethic throughout).
- Credibility is domain-specific: a source authoritative on one topic is a
  layperson on another. Evaluate per claim, not by the source's general
  reputation.
- Speed-versus-rigor scales with stakes: a low-stakes fact needs a quick
  check; a decision-shaping or public claim needs full evaluation and
  corroboration (see fact-checking).