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 LiuMengxuan04/vibe-resume --skill vibe-resume-editorgit clone --depth 1 https://github.com/LiuMengxuan04/vibe-resumeWrote 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/liumengxuan04/vibe-resume/vibe-resume-editor)<a href="https://agentmods.dev/skills/liumengxuan04/vibe-resume/vibe-resume-editor"><img src="https://agentmods.dev/badge/skills/liumengxuan04/vibe-resume/vibe-resume-editor/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/liumengxuan04/vibe-resume/vibe-resume-editor"><img src="https://agentmods.dev/badge/skills/liumengxuan04/vibe-resume/vibe-resume-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01702 |
| Opus 5 | $0.00018 | $0.00851 |
| Sonnet 5 | $0.00007 | $0.00340 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
vibe-resume-editor scanned grade A with 0 findings 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeResume Editor
Purpose
Use this skill to help a user maintain a resume in the VibeResume templates. The PDF is generated by scripts/export-pdf.mjs.
Template sources:
- Standard one-page template:
templates/internship-employment/standard-one-page/index.html+styles.css - Dense one/two-page technical template:
templates/internship-employment/dense-two-page/index.html+templates/internship-employment/dense-two-page/styles.css - Research application template:
templates/research-application/research-classic/index.html+templates/research-application/research-classic/styles.css
Core Rules
- Keep the resume credible and specific. Do not invent degrees, employers, dates, awards, metrics, or project claims when editing a real resume.
- Use
templates/internship-employment/standard-one-page/by default when the user does not specify length. - When the user explicitly asks for two pages, a dense resume, or has substantial technical experience that clearly needs two pages, default to
templates/internship-employment/dense-two-page/. - When the user is applying for a PhD, research internship, research assistant role, or needs to foreground publications and a representative research contribution, use
templates/research-application/research-classic/. - The dense template is backward compatible: keep one
.resume-pagefor a one-page version, or two.resume-pageelements for a two-page version. - The research template intentionally exports as a continuous long page. Do not force it into A4 unless the user explicitly requires A4.
- Prefer concise, formal resume wording with strong verbs, concrete scope, and measurable outcomes.
- Keep the selected template's semantic HTML structure unless a section truly needs to be added or removed.
- Keep visual edits scoped to
styles.css, and preserve the screen-to-PDF export mechanism. - Treat company/project logos as optional. Use SVG/vector icons when useful, but keep text-only names when no suitable asset is available.
- When a company logo is needed, proactively ask the user to manually search and download an SVG from
https://www.iconfont.cn/, verify that it is the intended company mark, and attach it for the Agent to copy intoassets/logos/. An official company brand/media library is also preferred. For AI model/product/provider icons, readhttps://lobehub.com/icons/skill.md, inspect@lobehub/iconstoc, and usegetLobeIconCDN. Production resumes must reference local files and never hotlink.
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.
- 9d ago Changed · +9 lines a20bf2def420
- 13d ago First seen · 108 lines · 36 tokens per session scan A 34b8f5f9bd37
vibe-resume-editor is a skill published in the GitHub repository LiuMengxuan04/vibe-resume (565 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 1,702 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.