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 nanoAgentTeam/research-claw --skill cvpr-iccv-eccvgit clone --depth 1 https://github.com/nanoAgentTeam/research-clawWrote 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/nanoagentteam/research-claw/cvpr-iccv-eccv)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/cvpr-iccv-eccv"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/cvpr-iccv-eccv/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/nanoagentteam/research-claw/cvpr-iccv-eccv"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/cvpr-iccv-eccv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 26 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00052 | $0.03377 |
| Opus 5 | $0.00026 | $0.01688 |
| Sonnet 5 | $0.00010 | $0.00675 |
| Haiku 4.5 | $0.00005 | $0.00338 |
Grade A, and why
cvpr-iccv-eccv 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[SKILL: CVPR / ICCV / ECCV PAPER FORMAT]
Activate when: user mentions CVPR, ICCV, ECCV, Computer Vision and Pattern Recognition, International Conference on Computer Vision, or European Conference on Computer Vision.
⚠️ Reference only — always verify: The rules below reflect common patterns from recent years. Conference requirements (page limits, required sections, package restrictions, submission options, etc.) can change each year. Before making any formatting changes, verify all requirements against the current year's official CFP and the author kit files (sample
.tex, README, formatting guide PDF) bundled in the template download.
Note: CVPR and ICCV share nearly identical templates (both use IEEE CVPR-style). ECCV uses a different Springer LNCS-based template. Instructions are split below — read the section matching the target venue.
Execution Protocol
After this skill is activated, select the matching scenario based on user intent.
Shared Common Workflow
Before venue-specific template steps, also load and follow:
config/.skills/ml-paper-writing/SKILL.md
At minimum, apply these shared references:
writing-guide.md(narrative and clarity)citation-workflow.md(verified citations; no hallucinations)reviewer-guidelines.md(reviewer-facing quality checks)checklists.md(pre-submission gates)
Built-in template: None — this skill does not bundle templates. Templates must always be downloaded from official sources (see Template Download below).
Pre-step: Year Confirmation & Template Acquisition
This step MUST be completed before any scenario below.
- Confirm the target year and venue (CVPR, ICCV, or ECCV) with the user. Default to latest available year if user does not specify.
- Confirm the stage:
submission(blind review) orcamera-ready(final). - Download the official template — this skill has no built-in template; always download from:
- CVPR: https://cvpr.thecvf.com → "Author Guidelines" or "Paper Submission" → download Author Kit
.zip - ICCV: https://iccv.thecvf.com → "Author Guidelines" → download Author Kit
.zip - ECCV: https://eccv.ecva.net → "Author Guidelines" → download from the ECCV site or https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines
- Overleaf fallback: search the venue name on https://www.overleaf.com/latex/templates
- CVPR: https://cvpr.thecvf.com → "Author Guidelines" or "Paper Submission" → download Author Kit
- Unzip downloaded files directly into <PROJECT_CORE>.
- Read the sample
.texfile from the downloaded kit to confirm preamble structure, package requirements, and author block format. - Confirm page limit and supplementary material policy from the current year's CFP.
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 First seen · 298 lines · 52 tokens per session scan A ede22967df21
cvpr-iccv-eccv is a skill published in the GitHub repository nanoAgentTeam/research-claw (293 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 3,377 once invoked, about $0.0003 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
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
latex-fmt
Reformat LaTeX papers for target journals and conferences. Handles document class changes, margin/page adjustments, citation style conversion, figure/table reformatting, and compliance checking against venue-specific requirements.
latex-polish
Polish academic writing in LaTeX files. Enhances clarity, fixes grammar, improves academic style, and eliminates Chinglish patterns. Operates on text content while preserving LaTeX commands, math, citations, and references.
latex-rescue
Diagnose and fix LaTeX compilation errors. Handles undefined control sequences, missing brackets, math mode violations, package conflicts, undefined references, and environment mismatches.
pdf2tex
Convert PDF documents back into editable LaTeX source code. Extracts text, math, tables, figures, and structure. Uses pymupdf + AI for intelligent reconstruction.
paper-verify-webchat
Use when the user asks to fact-check, verify, or score the citations/sources/references in a document from a chat (no terminal) — extracts citations with bundled code, fetches and judges each source with web tools, then scores through paper-verify's standard 100-point rubric via --from-evidence.