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 hamzabellouch/agent-skills --skill academic-nature-nature-experiment-loggit clone --depth 1 https://github.com/hamzabellouch/agent-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/hamzabellouch/agent-skills/academic-nature-nature-experiment-log)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/academic-nature-nature-experiment-log"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/academic-nature-nature-experiment-log/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/hamzabellouch/agent-skills/academic-nature-nature-experiment-log"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/academic-nature-nature-experiment-log.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 | $0.00051 | $0.01646 |
| Opus 5.5 | $0.00020 | $0.00658 |
| Sonnet 5.5 | $0.00010 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
nature-experiment-log 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 1mo 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
experiment-log — 实验日志标准化
触发条件
用户通过以下任一方式提交实验原始材料时自动加载：
- 路径 A — CLI 直接提交（图片 / 语音转录 / 文字）
- 路径 B — 发到飞书科研群，通过
feishu-cli-integration扫描
前置依赖
需要配合 feishu-cli-integration skill 使用。确保：
- 飞书 bot 已添加到目标群
- bot 权限：
im:message+im:resource+im:message.group_msg - 群 ID 配置在 skill 上下文中
处理流程
- 接收材料 → vision_analyze 读图 + 提取结构化信息
- 生成实验 ID + 样品批次 ID
- 写出标准日志到
wiki/实验日志/{体系}/{类型}/{exp_id}.md - 原始材料（图片等）归档到
raw/experiments/YYYY.MM.DD_描述_EXPID/ - 日志末尾加「原始材料」段落，引用 raw 路径
- 检查异常 → 有则追加
异常记录.md - 追加操作记录到日志索引
- 告知用户写入位置
模糊信息（温度记不清、样品编号不明）主动询问，不猜测写入。
目录结构
/vault/
├── raw/experiments/ ← 原始层（归档）
│ └── YYYY.MM.DD_描述_EXPID/
│ ├── 笔记.md
│ ├── 图片/
│ └── 语音/
│
wiki/实验日志/ ← 标准层（产出）
├── 实验索引.md
├── 异常记录.md
├── {体系A}/
│ ├── 实验类型1/
│ ├── 实验类型2/
│ └── ...
├── {体系B}/
│ └── ...
└── 公共/
└── 设备与试剂追踪.md
实验 ID 规则
{体系代码}-{设备代码}-YYMMDD-{序号}
│ │ │ └─ 当日序号（001 起）
│ │ └─ 日期
│ └─ 设备代码（M=马弗炉, T=管式炉, E=电化学, G=手套箱, F=可控气氛炉, B=通用）
└─ 体系代码（自定义，如 CL / NO / OX / HY 等）
样品批次 ID 规则
{体系代码}-{候选编号}-B{序号}
│ │ └─ 配盐批次序号
│ └─ 候选配方编号
└─ 体系代码
同一批样品跨多个实验时 sample_batch 保持一致，便于 dataview 追踪。
设备代码
| 代码 | 设备 | 场景 |
|---|---|---|
| M | 马弗炉 | 热处理、浸泡腐蚀 |
| T | 管式炉 | 气氛控制、脱水、热稳定性 |
| E | 电化学工作站 | CV/SWV/EIS |
| G | 手套箱 | 配盐、称量、取样 |
| F | 可控气氛炉 | 精密气氛控制 |
| B | 通用 | 干燥、清洗、制样 |
按实际设备扩展。
Obsidian 集成
本 skill 设计为与 Obsidian vault 配合使用。Obsidian 是一个基于本地 Markdown 文件的笔记系统，配合 Dataview 插件可实现实验数据的动态查询和仪表盘。
为什么用 Obsidian：
- 所有日志为纯文本 Markdown，可版本控制、可全文搜索
- YAML frontmatter 结构使 dataview 可自动生成实验列表、异常汇总、设备使用记录
- 本地存储，无云依赖性，数据安全
安装 skill 后需在 vault 中创建以下文件：
| 文件 | 模板 | 用途 |
|---|---|---|
实验日志/实验索引.md |
templates/experiment-index.md |
Dataview 查询仪表盘 |
实验日志/异常记录.md |
templates/anomaly-log.md |
异常记录 |
实验日志/公共/设备与试剂追踪.md |
templates/equipment-tracking.md |
设备与试剂追踪 |
What ships with it
9 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.
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.
- 1mo ago First seen · 155 lines · 51 tokens per session scan A fd079f111119
nature-experiment-log is a skill published in the GitHub repository hamzabellouch/agent-skills (8 stars, last pushed 11d ago), licensed MIT. It adds 51 tokens to every session and 1,646 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 2026-09-03.
Other skills, from other repositories
taxonomy-vto
A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.
space-util-fixer
A LaTeX layout helper for improving how content fills pages and columns. It addresses issues such as isolated lines, large blank areas, incorrect page counts, and uneven columns in two-column papers.
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
read
Read PDF page by page with structured output — key arguments, terms glossary, thesis connections. Use when reading academic papers, books, or articles.
release-governance
Use when preparing, auditing, releasing, PDF-hardening, or rebuttal-hardening academic manuscripts, datasets, artifacts, reviewer packets, or claim registers involving multiple refs, local assets, human labels, agent-assisted drafts, wide tables, figure provenance, submission PDFs, or evidence-boundary checks.
markdown
Documentation and content creation standards.