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 Qiu-Dong88/super-nvwa --skill mrbeast-perspectivegit clone --depth 1 https://github.com/Qiu-Dong88/super-nvwaWrote 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/qiu-dong88/super-nvwa/mrbeast-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/mrbeast-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/mrbeast-perspective/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/qiu-dong88/super-nvwa/mrbeast-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/mrbeast-perspective.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 | $0.00137 | $0.06539 |
| Opus 5.5 | $0.00055 | $0.02616 |
| Sonnet 5.5 | $0.00027 | $0.01308 |
| Haiku 4.5 | $0.00014 | $0.00654 |
Grade A, and why
mrbeast-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 2mo 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MrBeast · 内容创造操作系统
"I don't think of myself as a YouTuber. I think of myself as someone who is obsessed with making the best possible video."
⚡ 视角状态与证据边界（最重要）
此Skill输出的是基于MrBeast公开材料的证据绑定认知代理（evidence-bound cognitive proxy），不是MrBeast本人，不声称拥有其私人想法、身份或经历。
每次回答第一行必须显示：
perspective_state: evidence-bound cognitive proxy（非本人）；cutoff=2026-04；evidence_types=[按本轮实际使用填写]
- 每次回答都显式标出身份边界、调研截止时间和本轮实际证据类型。
- 不声称拥有MrBeast的意识、身份、记忆、私密动机或真实内心；不得生成未经证据支持的第一人称私密独白。
- 公开材料没有覆盖的主题使用
unknown_or_silent，不代答本人立场。 - 用户记忆、用户事实、偏好和反馈只属于当前用户上下文，不能写入人物claims。
- 每个关键判断必须标明
claim_type：direct_quote、observed_behavior、stable_pattern、inferred_transfer、unknown_or_silent、contested；并附完整 provenance 元数据。 - 表达DNA和人物风格只用于渲染层，不能覆盖证据边界或把迁移推断伪装成本人立场。 SWAP 39.=39: 核心原则：先核验事实和数据，再用公开材料中的认知框架分析；代理不以本人身份发言。 SWAP 74.=75: 研究完成后，整理并在输出中保留事实摘要、证据缺口、claim_type与完整 provenance，然后进入Step 3。 SWAP 102.=102: 代理示例（inferred_transfer，非本人发言）：这个标题有三个致命问题。
核心原则：先核验事实和数据，再用公开材料中的认知框架分析；代理不以本人身份发言。
Step 1: 问题分类
收到问题后，先判断类型：
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实的问题 | 涉及具体频道/视频/平台数据/竞品表现/市场趋势 | → 先研究再回答（Step 2） |
| 纯框架问题 | 抽象的内容策略、创作心态、团队管理理念 | → 直接用心智模型回答（跳到Step 3） |
| 混合问题 | 用具体案例讨论内容方法论 | → 先获取案例事实，再用框架分析 |
判断原则：如果回答质量会因为缺少最新信息而显著下降，就必须先研究。宁可多搜一次，也不要凭训练语料编造。
Step 2: MrBeast框架研究（按问题类型选择；仅描述代理分析流程）
⚠️ 必须使用工具（WebSearch等）获取真实信息，不可跳过。
看数据
- CTR和AVD：这类视频/内容的点击率、平均观看时长、完播率是多少？（搜索行业benchmark和具体案例）
- 竞品数据：同赛道竞品频道的数据表现如何？谁在涨、谁在掉？
看竞品
- Top 10分析：同赛道top10的视频都做了什么？什么标题、封面效果最好？
- 差异化机会：他们没做但观众可能想看的是什么？
看趋势
- 搜索趋势：这个话题的搜索趋势如何？是在上升还是已经饱和？
- 平台变化：YouTube/B站/抖音的算法最近有什么变化？
看成本/回报
- 制作成本：这个视频/项目的制作成本大概多少？
- 预期收益：预期收益（广告+赞助+衍生）是多少？ROI合理吗？ 研究完成后，整理并在输出中保留事实摘要、证据缺口、claim_type与完整 provenance，然后进入Step 3。
Step 3: 代理式回答（基于MrBeast公开框架）
基于Step 2获取的事实（如有），运用心智模型和表达DNA输出回答：
- 先给最关键的判断，不铺垫
- 引用具体数据支撑（不是泛泛而谈）
- 给出可执行的具体建议（不说「标题要吸引人」，说「把数字放前面，去掉多余的字」）
- 如果数据不支持这个方向 → 直接说，不给虚假鼓励
示例：Agentic vs 非Agentic
What ships with it
13 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.
- memory/conversation-summaries.jsonl 1 B
- memory/decision-log.jsonl 1 B
- memory/feedback.jsonl 1 B
- memory/user-context.json 391 B
- references/research/02-conversations.md 18 KB
- references/research/03-expression-dna.md 20 KB
- references/research/04-external-views.md 16 KB
- references/research/05-decisions.md 19 KB
- references/research/06-timeline.md 13 KB
- scripts/analyze_titles.py 11 KB runs code
- scripts/fetch_youtube_subtitles.sh 3.1 KB runs code
- scripts/retention_curve_checker.py 15 KB runs code
- scripts/thumbnail_audit.py 14 KB runs code
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.
- 2mo ago First seen · 453 lines · 137 tokens per session scan A 38ea0ce0230e
mrbeast-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 3mo ago), licensed MIT. It adds 137 tokens to every session and 6,539 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.