Skip to content
Skills Library
Science & research · Analysis

source-evaluation

/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.

Repository
AI-SKILLS ↗
Licence
MIT
Last repository change
05.09.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 05.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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.

Original author description

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.

How it works

  1. Method
  2. Boundaries
Original SKILL.md headings · 54 lines, 434 words
SKILL.md preview
---
name: source-evaluation
description: "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."
---

# 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).

Versions

RepositoryScoreLicence
This page · Amey-Thakur/AI-SKILLS90MIT
oborchers/fractional-cto100MIT

Database snapshot: 13.11.2026 · package version 2ed2184817a7 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95BiasCheck
    Three-layer bias analysis of any URL, file, or text: fetches the content and cited studies, then audits data bias, source conflicts, and journalism distortions. USE WHEN bias analysis, analyze bias, bias check, check this study, who funded this, is this source biased, fact-check…
  • 100source-credibility-assessment
    Evaluates how much weight a source deserves before a claim from it is used. Applies SIFT lateral reading (Stop, Investigate the source, Find better coverage, Trace to the original), checks fitness with CRAAP criteria (currency, relevance, authority, accuracy, purpose), traces…
  • 100source-research
    Fast topic research with source discovery, source quality evaluation, and concise synthesis. Use when looking up recent information, comparing sources, or producing a quick/detailed summary with citations.
  • 100research-methodology
    Plan, conduct, evaluate, and synthesize rigorous research investigations with credible evidence and a traceable method, including source-to-claim closure for media evidence. Do not use this skill for repeated source extraction and durable note orchestration; use…
  • 95BiasCheck
    Three-layer bias analysis on any URL, file, or text — auto-fetches the content and any cited study, then audits data-level biases, source conflicts of interest, and journalism-added distortions, separating what the data supports from what's editorialized. USE WHEN bias analysis,…
  • 100source-evaluation-bibliography
    Evaluate source quality, build annotated bibliographies, and maintain curated reference collections. Covers the CRAAP test, source classification, citation management, and research documentation patterns. Triggers on source evaluation, bibliography creation, or research documentation requests.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.