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 | $0.00068 | $0.03270 |
| Sonnet 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 11d 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.
- 11d 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 1mo ago), licensed MIT. It adds 137 tokens to every session and 6,539 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
creative-completion-and-renewal
Addresses the hardest creative act -- finishing and releasing work -- covering the tension between experimenter and finisher mindsets, making choices when everything feels possible, accepting shades rather than absolutes, ending projects to begin anew, approaching new work with a clean slate, knowing when to stop…
s4h-creativity
Entry point for the creativity toolkit. Routes to the right creative thinking technique based on your situation. Use when you say 'creativity', 'think creatively', 'I need fresh ideas', 'help me think differently', 'I'm stuck', or want creative help without knowing which specific tool applies. For comprehensive…
s4h-writing-arc-design
Maps and repairs character arcs and thematic arcs by aligning external plot events with internal change. Use when an arc feels unearned, a change feels sudden, or the ending doesn't land. Triggers: 'the arc feels unearned', 'arc design', 'the ending doesn't land', 'character arc', 'thematic arc', 'the change feels…
s4h-aesthetic-pattern-detection
Identifies the underlying formal pattern at work — because most successful designs, arguments, and solutions share deep structural patterns, and naming the pattern unlocks the playbook. TRIGGERS: 'what pattern is this', 'pattern recognition', 'why does this work', 'identify the form', 'what structure is at play'…
s4h-creativity-alternatives
Apply Edward de Bono's APC (Alternatives, Possibilities, Choices) tool to deliberately generate options before evaluating any of them. Use when the user is about to make a decision, wants more options before choosing, feels like they only see two paths, is planning something and wants to make sure they've considered…
s4h-creativity-brainstorm
Run an orchestrated multi-method creative thinking sprint on a challenge. Use when the user wants to make real progress on a hard problem, says 'I need to think through this properly', wants a thorough creative exploration rather than a single technique, has a big decision or challenge and wants the full toolkit…