Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LoreJob/screener --skill cv-screenergit clone --depth 1 https://github.com/LoreJob/screenerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lorejob/screener/cv-screener)<a href="https://agentmods.dev/skills/lorejob/screener/cv-screener"><img src="https://agentmods.dev/badge/skills/lorejob/screener/cv-screener/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lorejob/screener/cv-screener"><img src="https://agentmods.dev/badge/skills/lorejob/screener/cv-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00192 | $0.02296 |
| Opus 5 | $0.00096 | $0.01148 |
| Sonnet 5 | $0.00038 | $0.00459 |
| Haiku 4.5 | $0.00019 | $0.00230 |
Grade C, and why
cv-screener scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
If the JD describes a role that does not clearly map to any available sector module, do not refuse. Instead: How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CV Screener — Master Router
You are the entry point for the CV screening system. Your job is to collect the right inputs, identify the sector, and execute the correct sector-specific evaluation. The evaluation logic lives in this skill's references/ directory: a shared core protocol plus one evaluation module per sector. Load only the files you need — the core protocol and the single matching sector module.
Language
Detect the language of the conversation and respond in it — the acknowledgment, the assessment, the rejection reasons, everything narrative. English, Italian, Spanish, French, Portuguese, Russian, and Chinese are explicitly supported; any other language the user writes in is handled the same way.
Two rules:
- Structural labels stay in English —
VERDICT,ACCEPTED FOR INTERVIEW,REJECTED,ATS SCORE,OVERALL CV SCORE,SCORE BREAKDOWN, and the section titles of the output blocks. This keeps verdicts comparable across users and languages. Everything inside them (assessment text, rejection reasons, keyword commentary) is written in the user's language. - CV and JD language is an evaluation input, not a barrier. If the CV or JD is in a different language from the conversation, evaluate them as-is and respond in the conversation language. A CV in the wrong language for the role remains a hard disqualifier per the core protocol — but a Spanish-speaking user screening an English CV against an English JD is the normal case, not an error.
Step 0 — Trigger Acknowledgment
When this skill is triggered (user writes "screener" or equivalent), respond immediately with the following, translated into the conversation language:
CV SCREENER — ACTIVATED
Upload or paste:
1. Your CV (PDF or plain text)
2. The job description of the role you're applying for
Both are required. I will not screen without the full job description — a job title alone is not enough.
Nothing else. No pleasantries. Wait for the documents.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ATS_KEYWORDS.md 4.6 KB
- references/consulting.md 6.6 KB
- references/energy-utilities.md 7.2 KB
- references/finance-banking.md 6.5 KB
- references/hr-legal.md 6.8 KB
- references/manufacturing.md 6.6 KB
- references/marketing.md 7.1 KB
- references/pharma-biotech.md 7.1 KB
- references/retail-fmcg.md 6.0 KB
- references/sales-bd.md 6.3 KB
- references/SCREENING_PROTOCOL.md 12 KB
- references/tech-software.md 6.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 152 lines · 192 tokens per session scan C c2b351761b66
cv-screener is a skill published in the GitHub repository LoreJob/screener (2 stars, last pushed 3mo ago), licensed MIT. It adds 192 tokens to every session and 2,296 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Automation Tester Resume Optimizer
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.
DevOps Engineer Resume Optimizer
Build a DevOps or SRE resume around pipeline ownership, infrastructure as code, reliability metrics, and incident evidence, structured to pass both ATS parsing and platform-team screening.
cv-resume-builder
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
resume-tuning
An interactive resume-writing workflow that turns an existing resume or spoken work history into a tailored PDF resume. It can adapt the content to a job description and check whether applicant-tracking systems can read it.
resume-studio
Build, tailor, and maintain job-winning resumes with a persistent career memory. Use this skill WHENEVER the user mentions a resume or CV in any capacity — creating one, updating one, tailoring one for a job description, reviewing/critiquing one, converting a LinkedIn profile into a resume, preparing a job…
project-to-resume
A workflow for turning a completed project into a résumé project entry. It gathers the project's purpose, work, technology, and results, then writes versions suited to different job types.