CtrlK
BlogDocsLog inGet started
Tessl Logo

trump-perspective

唐纳德·特朗普(Donald Trump)的思维框架与行为逻辑。基于著作、长访谈、辩论、 心理分析、前幕僚回忆录、重大决策记录共6个维度的深度调研(320KB+原始资料), 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:(1)思维顾问——用特朗普视角分析谈判、权力、传播问题; (2)行为预判——解读他的公开行为背后的逻辑,预判下一步动作; (3)角色扮演——模拟特朗普在特定场景下的决策和表达。 当用户提到「用懂王视角」「特朗普会怎么看」「懂王逻辑」「trump perspective」 「懂王会怎么做」「从特朗普角度分析」「预测特朗普」时触发。

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 structured, highly actionable knowledge skill with an explicit multi-step workflow, validation checkpoints, and error-recovery fallbacks. The main weaknesses are minor: duplicated 最新动态 content and a generic rather than per-topic reference signal into the research bundle.

Suggestions

De-duplicate the 最新动态 section: keep the detailed analyst-facing version under ⚡最新动态 and remove the repeated bullets from the 人物时间线 section, or vice versa.

Replace the single generic reference pointer with per-topic links into the bundle, e.g. 「表达DNA原始语料:见 references/research/03-expression-dna.md」「决策记录:见 references/research/05-decisions.md」, so each inlined topic maps to its source file.

Consolidate the overlapping guidance between the 9-row 失败模式与 Fallback 树 and the 8-row 反例黑名单 into one table, or clearly delineate their distinct purposes (runtime fallback vs. pre-output checklist) to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is dense with unique, non-obvious knowledge (specific 2025-2026 events, quotes, dates) and largely avoids explaining concepts Claude already knows, but the 「最新动态」 material is duplicated in two sections (lines ~198 and ~402) and the failure-mode and anti-pattern tables partially overlap — minor trimming is possible.

4 / 5

Actionability

Highly actionable for an instruction skill: concrete WebSearch query templates (e.g. 「Trump Japan tariff 2026 latest」), prescribed output formats (概率分布 + 置信度 + 关键未知变量), a 9-row fallback table with concrete 兜底话术, and worked examples (The Weave, Agentic vs 非Agentic).

5 / 5

Workflow Clarity

Clear sequenced Agentic Protocol (Step 1 问题分类 → Step 2 研究 → Step 3 回答) with explicit CHECKPOINT 三问 validation between steps, a 9-rule failure-mode feedback loop for error recovery, and an 8-item anti-pattern checklist — matching the top anchor; no destructive/batch operations so the cap does not apply.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and a real one-level-deep reference bundle (references/research/ with 6 named files), but the body only gives a single generic directory pointer (「详见 references/research/ 目录」) rather than per-topic file links, and the distilled knowledge is largely inlined rather than split.

4 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, three explicit use cases, and a rich set of natural trigger phrases with synonyms, all in third-person voice. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete deliverables — 「6个核心心智模型、8条决策启发式和完整的表达DNA」 — plus three concrete use cases (analyze negotiation/power/communication, predict behavior, role-play), giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both what (Trump's thinking framework distilled into models/heuristics/DNA across 6 research dimensions) and when (「当用户提到…时触发」 with concrete trigger phrases), satisfying the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms — 「用懂王视角」「特朗普会怎么看」「懂王逻辑」「trump perspective」「懂王会怎么做」「从特朗普角度分析」「预测特朗普」 — covering both the colloquial 懂王 and formal 特朗普 plus an English variant.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Trump-specific perspective/analysis/role-play) with distinct triggers that would not plausibly fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alchaincyf/nuwa-skill
Reviewed

Table of Contents

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.