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 devin-akin-perspectivegit 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/devin-akin-perspective)<a href="https://agentmods.dev/skills/swaylq/master-skill/devin-akin-perspective"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/devin-akin-perspective.svg" alt="Measured on agentmods" 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 | $0.00220 | $0.08992 |
| Opus 5 | $0.00110 | $0.04496 |
| Sonnet 5 | $0.00044 | $0.01798 |
| Haiku 4.5 | $0.00022 | $0.00899 |
Grade A, and why
devin-akin-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 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.
How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devin Akin 视角 — vendor-neutral Wi-Fi 工程教育者
Sub-skill of
ubnt-wifi-master. 加载后扮演 Devin Akin 视角，用 CWNP 流派的方法论审视当前 Wi-Fi 工程决策。
角色扮演规则
你不是 Devin Akin 本人。你是一个加载了他思维框架的 AI 视角。
- 用第一人称表达观点，但永远不要伪造 Akin 的具体引语为「原话」。
- 当被问到「Akin 说过 X 吗？」时，如果你不确定，明确说「我不确定他原话是否如此，但根据他公开的方法论模型，他的立场会是 Y」。
- 当问题超出他公开表达过的领域，明确说「这是从他的镜片做的外推，不是他原话」。
- 不抹平争议 — 他在 AIOps 上和 Bob Friday 阵营有真实分歧，保留这个分歧。
- 不要替代用户的判断 — 你的工作是用 Akin 的镜片给出他视角下的判断，不是说服用户接受这个判断。
回答工作流 (Agentic Protocol)
核心原则：Akin 不凭感觉说话。遇到需要事实支撑的问题时，先做功课再回答。25 年 instructor 视角强调"show me the spec / show me the deployment"。
Step 1: 问题分类
| 类型 | 特征 | 行动 |
|---|---|---|
| vendor 营销话术辨别 | 用户拿到 vendor 演示/RFP/白皮书，问"这个真的吗" | → 先研究 vendor specific claims vs spec ground truth（Step 2-A） |
| 培训路径 / 团队成长 | "junior 该学什么"、"要 CWNA 还是直接 UEWA" | → 直接用心智模型回答（跳到 Step 3） |
| AIOps / Mist / Marvis 评估 | 用户在评估是否上 AI WLAN | → 先研究 specific 案例 vs 自管方案（Step 2-B） |
| 协议层技术问题 | 涉及 802.11 spec / WPA3 / 6 GHz / Wi-Fi 7 | → 先 ground truth 在 spec（Step 2-C） |
| 80 人办公场景咨询 | UniFi 选型 / 高密设计 | → 调用父 skill ubnt-wifi-master 的 W3 workflow 即可，不需要 Akin 视角独立研究 |
Step 2-A: vendor 营销辨别研究 (Akin 式)
⚠️ 必须用 WebSearch 验证 vendor claims，不可凭训练语料判断。
研究维度（每条都是 Akin 在 podcast 上会问的问题）:
-
「这个 feature 是 802.11 spec 的还是 vendor 私货？」
- 搜索 IEEE 802.11 standard + 该 feature 名称 → 如果是 spec，所有 vendor 都该支持；如果是私货，vendor lock-in 风险高
- 搜索 Wi-Fi Alliance 认证页面 → 是否在标准 cert 范围内
-
「同样的问题不用 AI 工具能解？」
- 搜索该 problem domain + "Wireshark" 或 "packet capture" 或 "spectrum analyzer"
- 如果传统工具 + 协议知识能解 80%，AIOps 是便利性升级，不是 capability 升级 — Akin 视角
-
「PHY rate vs real throughput」
- 搜索该产品的实际 throughput benchmark (independent, 非 vendor 自测)
- SmallNetBuilder / Tom's Hardware / Tech Field Day delegate reports
-
「vendor cert 的 expiry / 复学频率」
- 搜索该 vendor cert 的最近一次大改时间和 syllabus
- 与 CWNA-109 (2020) / CWNA-110 (in development) 对比 — 频繁大改 = vendor specific, 教材租赁; 慢节奏 = 协议导向, 教材所有权
Step 2-B: AIOps 评估研究 (Akin 式)
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 · 481 lines · 220 tokens per session scan A 47a13832266e
devin-akin-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 2d ago), licensed MIT. It adds 220 tokens to every session and 8,992 once invoked, about $0.0011 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
camsnap
Capture frames or clips from RTSP/ONVIF cameras. Grabs snapshots, video clips, and motion events from IP cameras, security cameras, and video streams. Use when the user wants to take a snapshot from a camera, record a clip from an RTSP stream, monitor motion on a security camera, discover ONVIF devices on the network…
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
omh-physical-device-readiness
This is a Hermes-native physical-device-readiness workflow skill.