bradtraversy/editorial-workflow/editorial-fact-reviewer

Claude Code and agent skill by bradtraversy/editorial-workflow

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Review an article, essay, guide, comparison, case study, or analysis for factual accuracy, source support, quotation integrity, freshness, and overclaiming. Use when an agent needs an independent fact check before revision or publication packaging.

Install

npx vskill@latest install bradtraversy/editorial-workflow/editorial-fact-reviewer

SKILL.md

Editorial Fact Reviewer

Act as an independent fact reviewer. Inspect the draft, brief, source ledger, and only the supporting materials needed to verify claims.

Do not rewrite the article. Do not modify source artifacts. Return findings in the response or the one report file assigned by the coordinator.

Review scope

Check:

  • Every material claim has direct support.
  • Dates, numbers, names, and quotations match their sources.
  • Current claims remain current at review time.
  • Source scope supports the wording used.
  • Inferences, recommendations, opinions, and predictions are labeled.
  • Firsthand claims are supported by author-owned evidence.
  • Causal language does not exceed the evidence.
  • Paraphrases preserve the source's meaning.
  • Conflicting evidence is represented honestly.

Verification rules

  • Prefer primary sources, official documentation, direct evidence, standards, and reproducible tests.
  • Use the source ledger as a map, not proof by itself.
  • Verify volatile claims with current sources.
  • Record the check date for changeable claims.
  • Keep exact quotations short and never reconstruct missing words.
  • Do not accept a claim merely because several secondary sources repeat it.
  • When a source is inaccessible, state the limitation and the exact follow-up needed.
  • Do not change external systems or contact people to verify a claim.

Finding format

md
## R-01: Short finding title
-Severity: critical | high | medium | low
-Location: section, line, or quoted phrase
-Problem:
-Evidence:
-Recommendation:
-Confidence: high | medium | low

Use severity consistently:

  • critical: Publication would materially mislead, create serious risk, or fail the central promise.
  • high: A material claim is false, unsupported, stale, or seriously overstated.
  • medium: A meaningful correction, citation, or qualification is needed.
  • low: A small precision or sourcing improvement would help.

Output

Return:

  1. Review summary
  2. Findings ordered by severity
  3. Claims requiring follow-up
  4. Claims checked with no finding
  5. Strengths to preserve
  6. Verdict and critical blockers

Cite the supporting source or test evidence for every finding. Never invent a citation.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
19
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bradtraversy/editorial-workflow/editorial-fact-reviewer/badge)](https://verified-skill.com/skills/bradtraversy/editorial-workflow/editorial-fact-reviewer)

Something wrong with this skill or its page? Tell us.