For AI agents: the docs index is at /llms.txt. Every page has a markdown version: add .md to the URL.

Agent Coach
Security scan: pass (whole repo scanned)SkillSSection: DeveloperCdLicense: MITMIT

Bullshit Detector (fact-check skills)

Portable agent skills that fact-check a YouTube video, article, tweet, PDF or pasted draft claim by claim, with sourced verdicts (confirmed, plausible, misleading, false, unverifiable) and a 0-10 BS score. Plain markdown plus self-contained Python; needs the agent's web search.

Scan
Repo scan pass
GitHub stars
163
Last updated
2026-09-29
License
MIT
Cost
free
Why it helps

Lets a content-producer agent check every claim in a draft or source against cited evidence before it publishes, instead of repeating unverified numbers.

Ask your owner first. installs a skill

Paste to your agent

Read https://upskill.coach/skills/bullshit-detector.md. If the security scan passed, ask me before installing, then install it with the command under Install and tell me what you did.

Install

npx skills@latest add SerhiiKorniienko/bullshit-detector  (or Claude Code: /plugin marketplace add SerhiiKorniienko/bullshit-detector)

Community

– views– downloads– comments

Helps with

DeveloperContentEvals & qualityContent producerQuality verification
Repo security-scanned on 2026-11-10 at commit d5f6156a8a5c: pass. The verdict covers the whole repo (serhiikorniienko/bullshit-detector); this skill wasn't scanned separately.
Scan notes
Automated scan: pass (no medium+ findings) at commit d5f6156a8a5c on 2026-11-10.
Source
github.com/serhiikorniienko/bullshit-detector
Repo
serhiikorniienko/bullshit-detector

Static scan at a pinned commit (prompt-injection, malware and exfiltration rules plus semgrep, gitleaks, osv-scanner); flagged lines reviewed by hand. A scan lowers risk; it doesn't prove safety.

Full text not reproduced here. Read it at the source.

Alternatives

Compare all

For agents: markdown, JSON.

Comments

Comments are from visitors, not reviewed by Upskill, and never shown to agents.