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 Rheinmir/setup --skill dym-arex-skill-creator-paper-to-skillsgit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-arex-skill-creator-paper-to-skills)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-arex-skill-creator-paper-to-skills"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-creator-paper-to-skills/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/rheinmir/setup/dym-arex-skill-creator-paper-to-skills"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-arex-skill-creator-paper-to-skills.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 | $0.00057 | $0.01470 |
| Opus 5.5 | $0.00023 | $0.00588 |
| Sonnet 5.5 | $0.00011 | $0.00294 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
dym-arex-skill-creator-paper-to-skills 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 yesterday.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-arex-skill-creator-paper-to-skills — Creator: paper → skill tái lập được (Distiller)
Vì sao dùng: Có một bài báo cần tái lập, và muốn kết quả là skill module hoá đã verify chứ không phải một bản tóm tắt.
Sinh ra cái gì: <workspace_root>/<paper_slug>/skills/ (skill sinh ra, còn là staging cho tới khi được duyệt import) và <workspace_root>/<paper_slug>/distillation/reports/final/ (báo cáo cuối).
1. Chuẩn bị file config
Có hai file TOML trong repo, cùng schema:
| File | Vai trò |
|---|---|
examples/creator/paper-to-skills/distiller-run-config.toml |
Starter đã chú thích kỹ — dùng cái này |
cli/packages/coding-agent/src/disco/skills/create-paper-skills/assets/distiller-run-config-template.toml |
Template canonical do skill giữ |
Từ gốc checkout AREX-Skill:
cp examples/creator/paper-to-skills/distiller-run-config.toml \
/absolute/path/to/distiller-run-config.toml
2. Điền tối thiểu 3 trường
schema_version = 1
[defaults]
workspace_root = "/absolute/path/to/paper2skills-workspace" # ① BẮT BUỘC sửa
[[runs]]
paper_slug = "my_paper_slug" # ② BẮT BUỘC sửa
paper_source = "/path/to/paper.pdf" # ③ BẮT BUỘC sửa
original_repo_source = "unknown"
paper_source nhận: đường dẫn PDF/text local · URL PDF trực tiếp · URL hoặc mã arXiv · tên bài báo.
original_repo_source nhận: đường dẫn repo local · URL Git/GitHub · "none" · "unknown".
Thêm bài thứ hai = thêm một khối [[runs]] nữa.
3. Các knob nên hiểu trước khi chạy (không phải mặc định nào cũng vô hại)
| Trường | Mặc định | Ý nghĩa |
|---|---|---|
recovery_mode |
"hard" |
hard: các lần chạy reduced/proxy/toy/fallback chỉ được ghi làm chẩn đoán, không tính là recovery thành công. Muốn chấp nhận chúng thì phải chọn soft một cách tường minh |
ask_before_expensive_recovery |
true |
Dừng hỏi trước khi đốt tài nguyên |
repo_discovery_mode |
"ask" |
ask dừng hỏi trước khi đi tìm repo cài đặt · auto tự tìm GitHub và clone ứng viên đầu · disabled không bao giờ tự tìm |
allow_title_top_hit |
false |
Không tự nhận kết quả đầu tiên khi tra bằng tên bài báo |
iteration_budget |
10 |
Số vòng refine tối đa |
network_timeout_seconds |
120 |
|
command_timeout_seconds |
20 |
|
runtime_constraints |
(chuỗi) | Mặc định starter cấm động vào conda env dùng chung, bắt dùng env cô lập |
test_root / skills_root / generated_skills_root / distiller_skills_root / attempt_dir |
"" |
Để trống là dùng layout mặc định dưới workspace_root |
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.
- yesterday First seen · 108 lines · 57 tokens per session scan A c9c82ed50435
dym-arex-skill-creator-paper-to-skills is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 57 tokens to every session and 1,470 once invoked, about $0.0002 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 2026-11-07.
dym-arex-skill-creator-paper-to-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-arex-skill-creator-paper-to-skillsRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 57 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |