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 hevangel/dvcon_ai_library --skill dvcon-submitgit clone --depth 1 https://github.com/hevangel/dvcon_ai_libraryWrote 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/hevangel/dvcon_ai_library/dvcon-submit)<a href="https://agentmods.dev/skills/hevangel/dvcon_ai_library/dvcon-submit"><img src="https://agentmods.dev/badge/skills/hevangel/dvcon_ai_library/dvcon-submit/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/hevangel/dvcon_ai_library/dvcon-submit"><img src="https://agentmods.dev/badge/skills/hevangel/dvcon_ai_library/dvcon-submit.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 | $0.00196 | $0.05561 |
| Opus 5.5 | $0.00078 | $0.02224 |
| Sonnet 5.5 | $0.00039 | $0.01112 |
| Haiku 4.5 | $0.00020 | $0.00556 |
Grade A, and why
dvcon-submit 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 2mo 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DVCon Submit
This skill does three things for DVCon U.S. paper submissions:
- Convert a paper written in Markdown into a
.docx(and optionally.pdf) that matches the IEEE-style DVCon abstract template, via MS Word COM. The output uses the template's named IEEE styles so it inherits the right fonts, sizes, margins, and US Letter paper size automatically. - Fill the Accellera/DVCon copyright permission + speaker-consent PDF (title, all author names, company, paper ID, dates). Signature widgets stay blank unless the user supplies a signature image — the skill never forges a handwritten signature.
- Submit the resulting PDF (or the user's existing PDF) to the DVCon U.S.
call for papers on Oxford Abstracts, by driving a real browser with the
playwright-clicommand-line tool — including the file upload, which the ZCode in-app browser cannot do butplaywright-cli uploadcan.
It handles both stages of the DVCon lifecycle:
- Extended Abstracts (the initial submission, double-blind, 600–1200 words)
- Full Paper (the later stage, after preliminary acceptance, 6–8 pages, author info included)
When to use
Trigger this skill when the user wants to:
- submit an extended abstract or a full paper to DVCon (U.S.)
- fill out the DVCon submission form on Oxford Abstracts
- upload a paper PDF to the DVCon / Oxford Abstracts submission system
- enter authors, affiliations, or topics into the DVCon submission form
- convert a markdown paper to the DVCon Word template / PDF
- fill the DVCon / Accellera copyright form (and speaker-consent page)
- prepare a DVCon abstract or full paper for submission
Do not trigger this for tutorials/workshops or panel submissions — those are separate Oxford Abstracts stages with different forms.
Three tools, two stages
| Task | Stage | Tool |
|---|---|---|
Convert markdown → .docx + .pdf (template-styled) |
either | scripts/convert_md_to_docx.ps1 (PowerShell, MS Word COM) or scripts/convert_md_to_docx.sh (bash twin; delegates to the .ps1 on Windows, else fill_ieee_docx.py + LibreOffice) |
| Fill the copyright + speaker-consent PDF | full paper | scripts/fill_copyright_form.py (PyMuPDF; bundled references/dvcon-copyright-form-2027.pdf) |
| Drive the submission form (fill fields, upload PDF, click Submit) | either | playwright-cli (real browser) |
What ships with it
10 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/conversion_reference.md 13 KB
- references/copyright_reference.md 5.7 KB
- references/dvcon_abstract_template.doc 47 KB
- references/dvcon_abstract_template.pdf 278 KB
- references/dvcon-copyright-form-2027.pdf 148 KB
- references/submission_reference.md 13 KB
- scripts/convert_md_to_docx.ps1 16 KB runs code
- scripts/convert_md_to_docx.sh 7.8 KB runs code
- scripts/fill_copyright_form.py 16 KB runs code
- scripts/fill_ieee_docx.py 11 KB runs code
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.
- 2mo ago Changed · +87 lines · +27 tokens per session cb170d0d0c6d
- 2mo ago First seen · 332 lines · 169 tokens per session scan A eec12c3dfdf3
dvcon-submit is a skill published in the GitHub repository hevangel/dvcon_ai_library (11 stars, last pushed 2mo ago), licensed MIT. It adds 196 tokens to every session and 5,561 once invoked, about $0.0008 per session on Opus 5.5. 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.
dvcon-submit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dvcon-submithevangel/dvcon_ai_library | Skill | 11 | 2mo ago | MIT | A | 196 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| foundry-hosted-agent-validationmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 82 | Claude Code, Codex |
| skill-doc-deliverynyldn/claude-octopus | Skill | 4.4k | yesterday | MIT | A | 29 | Claude Code |
| meta-web-to-pdf-briefingopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| paper-readerhuangkiki/dailypaper-skills | Skill | 1.3k | 4d ago | Apache-2.0 | A | 135 | Claude Code, Codex |
| chat-complex-documentsvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 90 | Claude Code, Codex |