taleb-perspective

塔勒布(Nassim Nicholas Taleb)的思维框架与表达方式。基于40+个来源的深度调研，提炼6个核心心智模型、9条决策启发式和完整的表达DNA。用途：作为思维顾问，用塔勒布的视角分析问题、审视决策、质疑主流叙事。当用户提到「用塔勒布的视角」「塔勒布会怎么看」「塔勒布模式」「反脆弱视角」「taleb perspective」时使用。即使用户只是说「会不会黑天鹅」「这个有尾部风险吗」「skin in the game」「有没有反脆弱的方法」「杠铃策略怎么用」也可触发。不要在用户只是做一般风险评估或问「靠不靠谱」时触发——只在涉及极端风险、反脆弱、预防原则等塔勒布核心概念时激活。

Quality

86%

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.

A richly detailed persona skill with excellent actionability and a well-sequenced, checkpointed workflow. Its main weaknesses are verbosity from redundant anti-pattern lists and concept re-explanation, and a monolithic structure that fails to navigate to the existing reference bundle files.

Suggestions

Consolidate the four overlapping anti-pattern sections (CHECKPOINT三问, 失败模式与Fallback树, 反例黑名单, 附录) into one, since they repeat the same rules (no two-sided arguments, no hedging, verdict-first).

Link to the existing ./references/ research files from a short '## 深度素材' section so the heavy research is one level deep rather than inlined, and move the 6-model evidence/genealogy detail into references.

Trim re-explanations of concepts Claude already knows (iatrogenics, ergodicity, Lindy effect, via negativa) down to the Taleb-specific application, not the concept definition.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and much of the detail is genuinely Taleb-specific, but it re-explains concepts Claude already knows (iatrogenics, ergodicity, Lindy effect, via negativa) and repeats the same anti-patterns across four overlapping sections (CHECKPOINT三问, 失败模式与Fallback树, 反例黑名单, 附录), so several sections could be tightened.	3 / 5
Actionability	Highly actionable for an instruction skill: concrete role-play rules, an EXIT TRIGGER with exact phrases, a 9-row fallback tree with copy-paste 兜底话术, and two full example dialogues covering common cases.	5 / 5
Workflow Clarity	The Agentic Protocol gives a clear Step 1→2→3 sequence with explicit CHECKPOINT三问 validation between steps and a fallback tree providing error-recovery feedback loops, matching the top anchor.	5 / 5
Progressive Disclosure	The body has decent section structure but is a ~480-line monolith that never links to the five research files in ./references/ (the 调研信息源 section describes sources without pointing to the bundle files), and inlines content (full model evidence, genealogy) that could live in separate files.	3 / 5
	Total	16 / 20 Passed

Description

95%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.

A strong, well-scoped description that clearly states what the skill does, when to trigger it (with rich CN/EN trigger phrases), and when NOT to trigger it. The only minor weakness is that the 'actions' are abstract cognitive modes rather than many concrete operations, capping specificity at 4.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('分析问题、审视决策、质疑主流叙事', '提炼6个核心心智模型、9条决策启发式'), but the actions are cognitive modes for a persona rather than a comprehensive set of concrete operations, so it falls just short of a 5.	4 / 5
Completeness	Explicitly answers both 'what' (思维顾问, 用塔勒布的视角分析/审视/质疑) and 'when' with concrete trigger phrases plus an explicit negative boundary ('不要在用户只是做一般风险评估...时触发'), satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases in both Chinese and English including synonyms ('用塔勒布的视角', '塔勒布会怎么看', '反脆弱视角', 'taleb perspective', '会不会黑天鹅', '尾部风险', 'skin in the game', '杠铃策略'), matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Taleb's perspective) with distinct triggers and an explicit negative boundary that prevents firing on generic risk assessments, giving minimal conflict risk.	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/taleb-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.