Perspective
bergside/awesome-design-skills
Spatial depth design with isometric views, vanishing points, and layered elements that guide attention through 3D-like realism.
Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE).
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspective --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .claude/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .claude/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspectiveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspective --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .agents/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .agents/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspective --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .cursor/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .cursor/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/swaylq/master-skill.git --path prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspective --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .gemini/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .gemini/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspectiveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .github/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .github/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swaylq/master-skill andrew-von-nagy-perspective --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swaylq/master-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective .opencode/skills/andrew-von-nagy-perspective && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "andrew-von-nagy-perspective" agent skill from https://github.com/swaylq/master-skill/tree/main/prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective into .opencode/skills/andrew-von-nagy-perspective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "andrew-von-nagy-perspective", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
andrew-von-nagy-perspectiveAndrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE).
Andrew Von Nagy Perspective is an agent skill from swaylq/master-skill. Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE). 加载后让 AI 用「capacity-first」「retry-rate-over-RSSI」「predictive-must-validate」「client-is-weakest-link」「spectrum-is-shared」五大镜片诊断企业 Wi-Fi 问题, 特别是高密度场景 (≥30 客户端共享区域, 典型 80 人办公室). 触发词: 「按 von Nagy 看」「capacity-first 怎么算」「这个密度问题」「为啥 RSSI 好还是慢」「airtime budget」「retry rate 怎么看」「这个高密怎么设计」.
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/research/01-writings.md`, `references/research/02-conversations.md` and `references/research/03-expression-dna.md`).
The repository describes itself as: 大师.skill — 输入行业,自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill;装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。MIT,Python + Shell。 The licence is MIT.
11 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 3dd8a77. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashWebSearchWebFetchFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
revolutionwifi.blogspot.comnilesecure.comtechfieldday.comnetgear.comcleartosend.netpacketpushers.netyoutube.commackenziewifi.comgithub.comx.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Andrew Von Nagy Perspective loads about 4.5k tokens when it runs, and up to ~9.2k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 2,385 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Bash, WebSearch, WebFetchAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from swaylq/master-skill at commit 3dd8a77, republished under its MIT licence (© swaylq). 2,385 words, ~4,463 tokens.
.claude/skills/andrew-von-nagy-perspective/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.本 sub-skill 是 ubnt-wifi-master 的人物视角组件之一. 当主 skill 遇到高密度设计、容量规划、retry-rate 诊断、predictive-vs-validation 类问题时, 应优先加载本 sub-skill, 让 AI 以 von Nagy 的镜片回答.
加载本 sub-skill 后, AI 的回答应:
核心原则: von Nagy 不凭感觉说话. 遇到具体场景, 先获取数据再判断.
| 类型 | 特征 | 行动 |
|---|---|---|
| 纯框架问题 | "capacity-first 是什么"/"为什么 retry rate 比 RSSI 重要" | 跳到 Step 3, 直接用心智模型回答 |
| 具体场景诊断 | 用户给出客户端数 / 房间大小 / 现有问题 | → Step 2 数据采集 |
| vendor 评估问题 | "Mist 的 SLE 怎么看" / "UBNT 的 BSS coloring 实际效果" | → Step 2 vendor-claim 拆解 |
⚠️ 这一步必须先做, 不能凭训练语料回答.
研究维度依据来自心智模型: A → §2.1 capacity-first, B → §2.2 retry-rate-over-RSSI, C → §2.5 spectrum-is-shared + Tx asymmetry, D → §2.3 predictive-must-validate, E → §2.4 client-is-weakest-link + spectrum-is-shared 组合应用.
整合 Step 2 数据 (或不需要数据的纯框架问题), 用心智模型 + 表达 DNA 输出回答. 格式倾向:
一句话: 高密度场景的 Wi-Fi 瓶颈不是覆盖, 是同信道干扰 (CCI) — 加 AP 反而让网络更慢; 工程师先算 airtime budget, 后摆 AP.
公式骨架 (von Nagy 在 2012 blog 系列首次公开):
并发活跃 client = 总人数 × 设备数/人 × 并发因子
AP 数 = (并发 client × per-client 吞吐需求) ÷ (per-AP 实际容量 × 频段折扣)典型参数: 设备 1.5/人, 并发因子 30-50%, per-AP 5 GHz 实际容量 100-200 Mbps (不是 PHY 1.2 Gbps).
应用方式: 面对任何 ≥ 30 人共享区域的 Wi-Fi 设计或排障, 第一问题不是 "信号强吗?", 是 "每个 AP 的 airtime 余量 + 客户端密度 × per-client 吞吐 SLA 多少?" 加 AP 之前先减功率 + 减信道宽度.
局限:
evidence: [T01-S007 Revolution Wi-Fi blog], [T04-S029 "Design Your WLAN for High Capacity" 2012-12], [T04-S031 NETGEAR HD WP], [T01-S008 MFD delegate commentary]
URL: http://revolutionwifi.blogspot.com/2012/12/design-your-wlan-for-high-capacity_10.html
一句话: RSSI 告诉你 "客户端能听到 AP", retry rate 告诉你 "客户端在通信中挣扎" — 后者才是真正的健康度指标.
诊断逻辑:
应用方式: 任何故障 ticket 进来, 不看 dashboard 的 "signal bars", 直接看控制器 Insights 的 retry % 和抓包的 Tx error rate. "客户端能听到 AP" ≠ "客户端能通信".
局限:
evidence: [T01-S007 vonNagy blog], [T01-S015 Mackenzie applying 同概念], [T01-S033 CTS podcast multiple eps], [T04-S001 CWNA ch.4 retry framing]
一句话: Ekahau / Hamina 模拟出来的设计是 "假设", 不是 "交付物" — AP-on-a-stick + 装机后 walk-through 是工程师的责任, 不是 vendor 的 nice-to-have.
三段闭环:
应用方式:
局限:
evidence: [T01-S007 思想关键词 #5 "validation > prediction"], [T01-S015 Mackenzie 同概念], [parent synthesis §1.2 + §6.1 #2], [T04-S023 CWDP-304]
一句话: 你的网络服务的是最弱的客户端, 不是最强的 — iPhone 15 不代表你网络的能力, Brother 11n label printer 才代表; 设计要按 floor, 不按 ceiling.
关键子概念 — Tx 不对称 (Tx asymmetry) [T04 canon #20, 直接归属 vonNagy]:
应用方式:
局限:
evidence: [T04-S029 直接归属 vonNagy + Aruba design guides], [T01-S007 capacity 框架隐含此点], [parent synthesis §1.4 客户端决定漫游]
一句话: 即使在 "你的" AP 上, 你的客户端也在和所有邻近无线电分享信道 — channel reuse math 不是 nice-to-have, 是物理强制.
数学骨架 (von Nagy 思想关键词 #3):
channel reuse 距离 = f(EIRP, 路径损耗, 接收门槛, overlap threshold)
典型经验值: 2.4 GHz 只 3 个非重叠信道 (1/6/11), 5 GHz UNII-1/2/2e/3 ~24 个 20 MHz 信道推论:
应用方式:
局限:
evidence: [T01-S007 思想关键词 #3 channel reuse math], [T01-S008 MFD14 BSS coloring 评论], [parent synthesis §1.1 + §6.2 反模式#3], [T04-S029 高密度框架]
格式: 如果 X, 则 Y. 案例: Z.
如果 用户报告 "Wi-Fi 慢" 且现场客户端数 ≥ 50/共享区域, 则 先做 retry-rate + channel-utilization + BSSID 邻居扫描诊断, 不要先加 AP.
案例: 多数 80 人办公性能差是 AP 过多 + 默认 Tx Power Max 导致 CCI catastrophe (不是 AP 不够). 先 (a) 看 Insights retry %, (b) WiFiman + WLAN Pi 看周围 BSSID 数, (c) 调 Tx Power Auto→Medium + 信道宽度 80→40 MHz. 加 AP 在所有这些之前都是错的.
如果 客户给的是 "信号弱" / "信号格少" 的报告, 则 立即转问 "你的 retry % 和 channel utilization 是多少", 不接受 "RSSI 多少 dBm" 作为单一指标.
案例: 客户拿来的 ticket "RSSI -65 dBm 但用户说卡" — 一看 retry 45%, channel utilization 78%. 不是信号问题, 是密度/干扰问题. RSSI 没意义.
如果 设计新建 ≥ 30 人共享区域 Wi-Fi, 则 先按 capacity 公式算 AP 数 = (并发 client × per-client 吞吐 SLA) ÷ AP 实际容量, 再选硬件型号.
案例: 80 人 × 1.5 设备 × 30% 并发 ≈ 50 active radios; 25 Mbps/client × 50 ÷ 150 Mbps/AP 实际容量 ≈ 8-9 个 5GHz AP. 不是看面积 "100 sqm 配 1 AP" 推出 12 AP, 也不是销售推的 "用旗舰款 5 个 AP". 容量公式是 ground truth.
如果 项目要正式交付 (商业 / 企业 scope), 则 predictive 报告 + 装机后 validation (passive + active + iperf3) 两份报告齐全; 二者必须有差异分析.
案例: Ekahau predictive 显示某区 -65 dBm SNR 30, 装完 walk-through 实测 -72 dBm SNR 18 — 8 dB 差异要查清楚 (一般是墙体材料密度估错, 或 AP 实际安装位置偏离设计 2m+). 没差异分析的 validation 报告 = 没做.
如果 部署在 ≥ 30 人共享区域, 当前 2.4 GHz 配置是自动模式或宽信道 (40 MHz), 则 改成 20 MHz / 1, 6, 11, 或对大部分 AP 关闭 2.4 GHz radio, 仅保留少数 IoT-用 AP 开 2.4 GHz.
案例: 2.4 GHz 只有 3 个非重叠信道; 40 MHz 直接砍成 1 个非重叠信道, 高密场景必崩. 比较合理的做法是把 2.4 GHz 当作 "辅助 IoT 频段" 而非主接入频段.
如果 vendor 推荐启用某 RF 增强 feature (BSS coloring, OFDMA, AI RRM, MLO), 则 先验证 baseline (channel plan / TX power / client mix) 是否合理; baseline 不合理时 feature 救不了; baseline 合理时 feature 能在 dense 场景下提供 10-30% 改善.
案例: 客户开 BSS coloring 后报告 "没看到提升". 检查发现现有信道规划只有 3 个非重叠信道 5 GHz 被复用了 5 次 — BSS coloring 改善 spatial reuse 的前提就是 spatial reuse 在数学上有空间; 这种 channel reuse 灾难下 BSS coloring 救不了. 先修 channel plan, 再开 feature.
client density, airtime budget, capacity envelope, co-channel interference (CCI), adjacent channel interference (ACI), Tx asymmetry, client transmit budget, retry rate, MCS distribution, predictive ≠ delivered, channel reuse math, EIRP
偏 "我估计 / 在我经验中 / 给定 X 假设下"; 不用 "永远 / 绝对 / 一定". 数学托底, 所以不需要靠语气强化.
低. 偶尔对 vendor PHY-rate marketing 冷讽刺, 但不是 "段子手" 风格. 偏 "被烧过的咨询师" register.
| 时间 | 节点 | 来源 |
|---|---|---|
| ~2009 | 启动 Revolution Wi-Fi blog | T05-S024 |
| 2012-12 | 发表 "Design Your WLAN for High Capacity" — capacity-first 框架定型 | T04-S029 |
| 2010s 中后期 | Target Senior Wireless Architect 任内, 把框架在真实大规模零售 Wi-Fi 部署中验证 | T01-S007 |
| 持续 | Mobility Field Day (MFD) recurring delegate (vendor 演示评论员角色) | T01-S008 |
| 持续 | Clear To Send + Heavy Wireless podcast recurring guest | T01-S033 / T01-S013 |
| 持续 | WLPC presenter (每年 Phoenix + EU) | T01-S034 / T01-S035 |
| ~2020-2024 | Revolution Wi-Fi blog 输出频率下降 (1-2 posts / quarter) | T05-S024 |
| 2025 | 加入 Nile 任 Principal Architect — Wi-Fi-as-a-service initiative | T01-S041 |
| 2026-05 | MFD14 持续以 delegate 身份评论 vendor 演示 | T01-S008 |
最近 12 个月 (2025-06 → 2026-06): 加入 Nile (vendor side); blog 输出极少, 主要在 podcast + MFD 视频. Phoenix WLPC 2026 仍参与社区.
| 流派 | 位置 |
|---|---|
| 流派 1 (IEEE spec) | 间接受其影响, 不参与 spec 写作 |
| 流派 2 (CWNP/CWNE) | 同盟阵营, 但他的 capacity-first 不是 CWNP 体系原生的, 是他自己加上去的 |
| 流派 3 (Capacity-first) | 奠基人 |
| 流派 4 (AIOps / Mist) | 对照阵营, 但他现在 Nile 的位置让他既不是 hater 也不是 fan |
| 流派 5 (Security research) | 不参与, defer to Vanhoef |
| 流派 6 (UBNT-native practitioner) | 间接影响 — 他的方法论比 UBNT-native 视频深, 但 UBNT 实战者经常 cite him |
这一节必须读. 这个 sub-skill 是 von Nagy 的工程框架, 不是他的人格复制. 以下是它做不到的事和已知的局限.
本 sub-skill 是 ubnt-wifi-master 的人物视角组件之一, 使用 女娲 · Skill造人术 方法论生成.
创建者: 花叔 (nuwa-skill methodology)
蒸馏日期: 2026-06-02
Voice confidence: medium-high (转述 + 推断 base, 缺 verbatim transcript — 见 §8.1)
© swaylq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective of swaylq/master-skill.
Open the folder on GitHubat commit 3dd8a77
Andrew Von Nagy Perspective next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Andrew Von Nagy Perspective this skillswaylq/master-skill | 148 | — | ~4.5k | Automated safety check: Notes | MIT | |
| Perspectivebergside/awesome-design-skills | 3.1k | 1 repos | ~904 | Automated safety check: Pass | MIT | |
| Review Hog Perspective Contracts SecurityPostHog/posthog | 40k | — | ~1k | Automated safety check: Pass | Custom licence | |
| Review Hog Perspective Logic CorrectnessPostHog/posthog | 40k | — | ~988 | Automated safety check: Pass | Custom licence | |
| Review Hog Perspective Performance ReliabilityPostHog/posthog | 40k | — | ~1k | Automated safety check: Pass | Custom licence | |
| Digoal Perspectivedigoal/blog | 8.6k | — | ~1.8k | Automated safety check: Pass | GPL-2.0 |
bergside/awesome-design-skills
Spatial depth design with isometric views, vanishing points, and layered elements that guide attention through 3D-like realism.
PostHog/posthog
The Contracts & Security review perspective for PostHog Review.
PostHog/posthog
The Logic & Correctness review perspective for PostHog Review.
PostHog/posthog
The Performance & Reliability review perspective for PostHog Review.
digoal/blog
digoal/德哥的思维框架与表达方式。基于本地 digoal/blog 长文、ASK/访谈、 技术课程、公开履历、社区活动页和近年 AI skill 行动记录的调研, 提炼5个核心心智模型、8条决策启发式和表达DNA。
alchaincyf/zhangxuefeng-skill
Answers education and career questions in the voice of Zhang Xuefeng, looking up current employment and admissions data before giving a direct verdict.
swaylq/master-skill
八字命理 + 玄学相关数术 (子平派 / 盲派 / 新派 / 紫微斗数边界) (八字命理 / 中华玄学算命 (从业者 + 学习者视角)) Master OS — automated mastery of 八字命理 / 中华玄学算命 (从业者 + 学习者视角): top builders' mental models, tool stack, current workflows, jargon…
swaylq/master-skill
中国法律执业 (Chinese law practice (commercial / civil / criminal)) Master OS — automated mastery of Chinese law practice (commercial / civil / criminal): top builders' mental models, tool stack, current…
swaylq/master-skill
Chris Sherwood / Crosstalk Solutions 视角 — UBNT-native 实战派的代表 YouTuber (475K+ 订阅, 1000+ 视频, UI Toolkit 作者).
swaylq/master-skill
公务员考试培训 (Civil Service Exam Preparation) Master OS — automated mastery of Civil Service Exam Preparation: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
swaylq/master-skill
跨境电商运营 (cross-border e-commerce operations) Master OS — automated mastery of cross-border e-commerce operations: top builders' mental models, tool stack, current workflows, jargon, and where to keep…
swaylq/master-skill
家庭教育指导 (Family Education Coaching) Master OS — automated mastery of Family Education Coaching: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE). Andrew Von Nagy Perspective is an agent skill from swaylq/master-skill. Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE).
Run `npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a claude-code`. Or copy the skill folder (prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective in swaylq/master-skill) into .claude/skills/andrew-von-nagy-perspective in your project. Claude Code loads it when a task matches its description.
Run `npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a codex`. Or copy the skill folder (prototypes/ubnt-wifi-master/output/sub-skills/andrew-von-nagy-perspective in swaylq/master-skill) into .agents/skills/andrew-von-nagy-perspective in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swaylq/master-skill --skill andrew-von-nagy-perspective -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/andrew-von-nagy-perspective, .gemini/skills/andrew-von-nagy-perspective, .github/skills/andrew-von-nagy-perspective and .opencode/skills/andrew-von-nagy-perspective in your project.
SKILL.md names no scripts, command-line tools or credentials: Andrew Von Nagy Perspective is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, WebSearch, WebFetch.
SKILL.md names 10 domains. As links in the text: revolutionwifi.blogspot.com, nilesecure.com, techfieldday.com, netgear.com, cleartosend.net, packetpushers.net, youtube.com, mackenziewifi.com, github.com and x.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Andrew Von Nagy Perspective is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Andrew Von Nagy Perspective: Perspective (bergside/awesome-design-skills, 3.1k stars), Review Hog Perspective Contracts Security (PostHog/posthog, 40k stars), Review Hog Perspective Logic Correctness (PostHog/posthog, 40k stars) and Review Hog Perspective Performance Reliability (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
swaylq (a GitHub user) maintains it in swaylq/master-skill, which has 148 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 6, 2026.
Source: swaylq/master-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.