mrbeast-perspective

MrBeast（Jimmy Donaldson）的内容创造操作系统。基于泄露的36页内部培训手册、 6个深度播客、决策记录和外部批评的深度调研，提炼6个核心心智模型、8条决策启发式、完整的标题/缩略图/Hook/节奏公式，和4个可运行的内容分析脚本。激活后沉浸式扮演MrBeast，直接以「我」的视角给出内容创作建议。当用户提到「用MrBeast的视角」「MrBeast会怎么做」「Beast模式」「mrbeast perspective」时使用。即使用户只是说「视频CTR怎么提升」「标题不够吸引人」「retention曲线怎么优化」「缩略图要改吗」也应触发。不要在用户只是说「内容创作建议」「怎么做内容」等一般性问题时触发——只在涉及视频优化、标题/缩略图/Hook/留存率等YouTube方法论时激活。

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers highly actionable, well-sequenced guidance with strong validation checkpoints. Its main weaknesses are verbosity from inlined biographical detail and under-signaled reference files that keep the overview from being lean.

Suggestions

Link and signpost the five ./references/research/ files from the body (e.g. 'See references/research/03-expression-dna.md for the full expression DNA') so the reference layer is one level deep and discoverable.

Move the identity card, personal timeline, and '内在张力' biographical content into a reference file and keep the body focused on the operative persona rules, mental models, and formulas.

Trim the duplicated guidance between the anti-pattern table, fallback tree, and CHECKPOINT sections, which restate the same 'be concrete / no hedging' rule several times.

Dimension	Reasoning	Score
Conciseness	The body is substantive and mostly non-redundant, but the identity card, full personal timeline, and '内在张力' sections are padded biographical detail that competes for context without proportionally improving Claude's task execution.	3 / 5
Actionability	Highly concrete throughout — a title-formula table with examples and usage frequencies, the thumbnail 3-element rule, a 0–30s hook structure, retention targets by time band, and a scripts table giving exact invocation commands.	5 / 5
Workflow Clarity	Sequenced 3-step agentic protocol (classify → research → answer) with explicit CHECKPOINT A/B/C self-checks and a 9-row if-then fallback tree providing validation and recovery loops.	5 / 5
Progressive Disclosure	Scripts are listed in a table with real, matching paths in ./scripts/, but the five research files in ./references/research/ are never signaled or linked from the body, and the long persona/timeline/identity content is inlined rather than split into one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinct: it states concrete capabilities, gives explicit positive and negative trigger guidance, and uses third-person imperative voice throughout. Trigger-term coverage is strong though not exhaustive of every synonym.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — '6个核心心智模型、8条决策启发式、完整的标题/缩略图/Hook/节奏公式，和4个可运行的内容分析脚本' — giving comprehensive coverage of what the skill provides.	5 / 5
Completeness	Explicitly answers both 'what' (the content-creation operating system and its components) and 'when' ('当用户提到…时使用', '即使用户只是说…也应触发') with concrete trigger phrases and a negative-trigger boundary.	5 / 5
Trigger Term Quality	Includes natural user phrases like '用MrBeast的视角', 'MrBeast会怎么做', '视频CTR怎么提升', '标题不够吸引人'; good coverage but a few common synonyms (e.g. 'YouTube增长') are less explicit.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (MrBeast YouTube content methodology) with distinctive triggers and an explicit exclusion clause ('不要在…一般性问题时触发'), minimizing overlap with generic content skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alchaincyf/nuwa-skill
Path: examples/mrbeast-perspective/SKILL.md
Commit: fe03746

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.