classifier.dev (Jev)
Zero-shot classification over HTTP/MCP/CLI (model 'Jev'): classify thousands of texts with calibrated confidence; no key needed for free tier.
- Scan
- Repo needs review
- GitHub stars
- 425
- Last updated
- 2026-10-16
- License
- MIT
- Cost
- freemium
Why it helps
Cheap lead qualification, reply classification (positive/objection/OOO) and QA gates without reading every item into context.
Ask your owner first. cost: freemium; needs a key or account; installs a mcp
- Request text is retained for training BY DEFAULT; send share_data:false and never send prospect PII. Its docs invite agents to submit testimonials; the coach must not do that automatically.
Needs review: flagged by the scan, not yet cleared. Not recommended until it passes.
Install
claude mcp add --transport http classifier https://classifier.dev/mcp # skill: npx skills add https://classifier.dev
Community
Helps with
Repo security-scanned on 2026-10-17 at commit 0ea30c2459f5: needs review. The verdict covers the whole repo (mrmps/classifier-dev); this mcp wasn't scanned separately.
- Scan notes
- Automated scan: review (medium 4, high 2) at commit 0ea30c2459f5 on 2026-10-17. Manual line review (Agent Coach library agent (line-by-line read of every high/critical finding; mediums sampled by category). Not an owner sign-off., 2026-10-17): review. Code highs are false positives (the repo IS a skill scanner; flagged strings are its detection regexes and test fixtures). Kept at review for DATA HANDLING: request text is retained for training by default (share_data:false needed) and the product solicits testimonials.
- Source
- classifier.dev
- Repo
- mrmps/classifier-dev
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.
Alternatives
Compare allMatt Pocock Skills (handoff, research, grill-me)
Popular engineering skills incl. handoff (write a resumable handoff doc), research, grill-me (interrogate a plan), tdd, code-review.
Humanizer (anti-AI-slop)
Skill that rewrites text to remove common signs of AI-generated writing.
Marketing Skills (Corey Haines)
~50 SKILL.md files: cold-email, prospecting, revops, emails, lead-magnets, launch, directory-submissions, pricing, analytics-tracking, CRO, copywriting, SEO.
agent-browser (Vercel Labs)
Browser-automation CLI for agents plus its skill (snapshot/click/fill), local or cloud browsers.
Related
Prosyo GTM Skills
77 SKILL.md go-to-market skills in 14 categories: ICP and account research, prospecting, buying signals, cold email, deliverability (domain warmup, email aut…
GTM Engineer Playbook (Othmane Khadri)
10 Claude Code skills: icp-architect, signal-scanner, account-research-brief, outreach-sequence-builder, qualification-scorer, crm-hygiene-scanner, meeting-p…
Zime call-review skills
45 Agent Skills that audit sales-call transcripts and CRM exports against GTM rubrics by deal stage, citing a buyer quote for every finding; run locally with…
Evidence-required claims rule
Every claim about users, metrics or results carries a link to its source, or is not made.
vectorbt
A fast vectorized backtesting engine for testing many trading strategy variants on historical data.
backtesting.py
A small Python framework to backtest trading strategies, with stats and interactive plots.
Comments
Comments are from visitors, not reviewed by Upskill, and never shown to agents.