Vibe-Skills is a collection and routing system that helps AI agents discover, select, and coordinate specialized skills for completing tasks. It is intended for agents that need to organize workflows across many installed capabilities. The catalogue entries are skills and an agent belonging to this system.
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 foryourhealth111-pixel/Vibe-Skills --skill manuscript-as-codegit clone --depth 1 https://github.com/foryourhealth111-pixel/Vibe-SkillsWrote 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/foryourhealth111-pixel/vibe-skills/manuscript-as-code)<a href="https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/manuscript-as-code"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/manuscript-as-code/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/foryourhealth111-pixel/vibe-skills/manuscript-as-code"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/manuscript-as-code.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 | $0.00043 | $0.00527 |
| Opus 5 | $0.00022 | $0.00264 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
manuscript-as-code 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 8d 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.
What it actually says
Manuscript as Code（论文工程化）
目标
把“写论文”升级成“交付可复现的出版工程”：
- 结构清晰：任何人进仓库都知道哪里改正文、哪里改图、哪里改引用
- 可复现：一条命令能构建 PDF/HTML；CI 自动验证
- 可审计：每张图/每个结果都有来源（代码/数据/参数）
适用：
- 多人协作写作（导师/合作者/跨机构）
- 反复投稿/返修（需要明确改动轨迹）
- 图表多、实验多、容易“找不到版本”的项目
推荐仓库结构（最小可行）
见 templates/repo-structure.md。核心思想：
manuscript/：只放正文与引用（source-of-truth）figures/：每张图一个目录（source + out）build/：所有生成物（可删除，可再生）submission/与revision/：投稿与返修阶段产物
元规则（工程化的关键）
1) 生成物与源文件分离
- 源：
figures/fig-02/src/plot.py - 产物：
figures/fig-02/out/fig-02.pdf - 禁止把产物当源文件编辑（比如在 PDF 上涂改）
2) 每张图都要能“重生成”
最少要求：
- 一条命令 + 固定参数能导出最终图（PDF/TIFF）
- 记录依赖版本与随机种子（如果有）
3) 把“投稿约束”写成配置
推荐维护：
submission/submission-manifest.yml（统一记录规格与完成度）
案例（推荐学习）
- Manubot：
manubot/rootstock（论文的 CI/协作写作范式） - Deep review：
greenelab/deep-review（评审/返修视角）
What ships with it
1 file 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.
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.
- 8d ago First seen · 59 lines · 43 tokens per session scan A 81de88373ee7
manuscript-as-code is a skill published in the GitHub repository foryourhealth111-pixel/Vibe-Skills (3,235 stars, last pushed 11d ago), licensed Apache-2.0. It adds 43 tokens to every session and 527 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 2026-09-03.
Other skills, from other repositories
shared-tooling-git-hooks
Husky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8.
changelog-generator
Generate changelogs and release notes from Conventional Commits with semver bump detection, Keep a Changelog formatting, and monorepo scopes. Use when preparing releases, enforcing commit standards, or automating release notes.
agent-commit
Analyze changes and create a meaningful commit with agent authorship. Internal skill for evolveloop.
commit-and-push
Create a well-formatted git commit and push to remote repository.
commit
Creates Conventional Commits with pre-commit validation. Triggers: commit, conventional commit, git commit, message.
latex-diff
Compare two LaTeX files, project directories, or Git revisions and produce human-readable plus machine-readable severity-graded semantic changes. Use when determining what changed between manuscript versions or preparing a revision audit bundle. Not for proofreading one version; use $proofread.