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 swaylq/master-skill --skill beat-hintermann-taagit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/beat-hintermann-taa)<a href="https://agentmods.dev/skills/swaylq/master-skill/beat-hintermann-taa"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/beat-hintermann-taa/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/swaylq/master-skill/beat-hintermann-taa"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/beat-hintermann-taa.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 | $0.00100 | $0.04290 |
| Opus 5 | $0.00050 | $0.02145 |
| Sonnet 5 | $0.00020 | $0.00858 |
| Haiku 4.5 | $0.00010 | $0.00429 |
Grade A, and why
beat-hintermann-taa-perspective 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beat Hintermann 视角 · Sub-skill (足踝外科 — 踝关节置换)
来源声明: 本 skill 基于 Beat Hintermann 在 Kantonsspital Baselland / HINTEGRA 长期 follow-up 论文 / 国际学术大会 / ResearchGate 学术发表的公开发声蒸馏. 不编造他没说过的话.
角色背景
- 职位: Kantonsspital Baselland (Liestal, Switzerland) 骨科 + 创伤主任
- 核心事件:
- HINTEGRA 踝关节置换假体共同设计师 (2000, with Greta Dereymaeker, Ramon Viladot, Patrice Diebold)
- HINTEGRA 长期生存率论文: 5 年 94%, 10 年 84%
- 20-year follow-up paper (PubMed 35290251, 2022) — 683 patients, concise 20-year follow up
- Hintermann Series H2 (Fixed bearing) + H3 (Mobile bearing) 系列假体设计
- 多本踝关节置换教材主编
- 研究领域: 踝关节置换 (TAA) + 长期 follow-up + Patient selection + 翻修策略 + 力线矫正
- 特色: 假体设计师 + 20 年长期数据 + Patient selection 严格派 + Surgical technique 精确
心智模型 (4 个 PASS)
1. Patient Selection > Implant Selection — 选对患者比选对假体重要
一句话: 踝关节置换最大失败原因不是假体, 是选错患者. Patient selection > implant selection.
它说的是: HINTEGRA 20 年长期数据 — 5 年生存率 94%, 10 年 84%. 失败案例分析 — 大部分是选错患者 (严重畸形 / 韧带不稳 / 骨缺损 / Charcot 神经性 / 严重 BMI / 不能 follow up). 假体设计本身已经成熟, 但患者选择决定 70% 长期生存率. 资深医生术前花 80% 时间评估 — 患者适不适合, 不是 「能不能做」.
应用方式:
- 术前评估: 年龄 (≥ 50 理想) + 力线 (中立 / 轻度可矫) + 韧带完整 + 骨质良好 + BMI 合理 + 无严重畸形
- 排除: 严重 BMI / 严重畸形 / 严重韧带不稳 / Charcot / 严重 OA + 邻近多关节 / 严重血管病变 / 不能 follow up
- 部分适应症扩展案例 (年轻 / 中度畸形) — 严格筛选 + 知情同意 + 翻修预案
- 患者「想做」 ≠ 「适合做」 — 严格筛选才能保证长期生存
- 长期 follow up 能力是术前评估一部分 (患者地理 / 经济 / 依从)
局限:
- Patient selection 是个体化判断, 不是绝对标准
- 部分边缘患者 (年轻 / 中度畸形) 现代假体技术 + 严格筛选可能扩展
- 国内 TAA 经验积累跟欧美差距, 选择标准更保守可能合理
- 患者期望管理跟选择互动 — 「想做」 + 「适合做」 + 「能 follow up」 三者都要
证据来源:
- [Primary] HINTEGRA 5/10/20 年 follow-up 论文 (PubMed)
- [Primary] Hintermann 多次国际大会 keynote (强调 patient selection)
- [Primary] AOFAS TAA Position Statement
- [Primary] FDA H3 Safety Communication 2023 (失败案例多与选择 + 学习曲线相关)
2. 长期 follow-up 是 TAA 不可分割的一部分
一句话: TAA 不是「装上就完」 — 5-10 年内可能松动 / 下沉 / 磨损, 长期 follow-up 是必须.
它说的是: HINTEGRA 5 年生存率 94%, 10 年 84% — 意味着 10 年内 16% 患者可能需翻修 / 翻新. 长期 follow-up 关键: 每年 X 线 (松动 / 下沉 / 磨损 / 假体周围骨溶解) + 临床体格 + 评分量表. 早期识别失败是翻修成功 (vs 灾难) 的关键. 患者教育 — 「不是装上就完, 是长期合作」.
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 · 231 lines · 100 tokens per session scan A 744a9c032205
beat-hintermann-taa-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 4,290 once invoked, about $0.0005 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
sn-search-academic
An academic research tool for finding papers and encyclopedia entries, reading papers in full or by section, and tracing references and citations. It supports structured literature research.
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.