steve-jobs-perspective

史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研，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：作为思维顾问，用乔布斯的视角分析产品、审视决策、提供反馈。当用户提到「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve jobs perspective」时使用。即使用户只是说「帮我用乔布斯的角度想想」「如果乔布斯会怎么做」「切换到乔布斯」也应触发。

Quality

88%

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

81%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 well-engineered role-play skill with strong actionability and an explicitly gated, feedback-looped workflow. The main weaknesses are conciseness (encyclopedic inlined sections bloat the body) and an orphaned demo-conversation bundle file that is never linked from SKILL.md.

Suggestions

Move the 人物时间线 and 智识谱系 sections (and possibly the full source appendix) into references/research/ or a dedicated reference file, keeping only a one-line pointer in the body to improve conciseness and progressive disclosure.

Reference references/demo-conversation-2026-04-05.md from the body (e.g., under the 表达DNA or 角色扮演规则 section) so the bundle file is discoverable rather than orphaned.

Trim repeated emphasis (e.g., reiterated '聚焦即说No' framing across models, heuristics, and values) to reduce token cost without losing the synthesized Jobs framing.

Dimension	Reasoning	Score
Conciseness	The body is ~400 lines with dense, mostly skill-specific material, but encyclopedic sections (full 人物时间线 table, 智识谱系, and the appendix listing every source) plus repeated emphasis could be trimmed or offloaded without losing clarity.	3 / 5
Actionability	Highly actionable for an instruction/role-play skill: explicit role-play rules, a 3-step agentic workflow, a 9-row if-then-repair-fallback table, concrete expression DNA (sentence patterns, vocabulary, rhythm), and worked examples (Vision Pro, hedging rewrites) cover the common cases.	5 / 5
Workflow Clarity	The Step 1→2→3 workflow is clearly sequenced with explicit red CHECKPOINTS between steps, self-check questions, and feedback loops ('回 Step 2 补搜') for error recovery; no destructive/batch operation cap applies.	5 / 5
Progressive Disclosure	Good section structure and a clearly signaled one-level-deep reference ('references/research/ 目录（6个文件，共2497行）'), but references/demo-conversation-2026-04-05.md is orphaned (never referenced in the body) and some encyclopedic content is inlined rather than split out.	4 / 5
	Total	17 / 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 description: third-person, with a clear what/when pair and rich natural-language triggers in both Chinese and English. The only minor weakness is that the enumerated actions are somewhat generic, which keeps specificity at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('分析产品、审视决策、提供反馈' plus '提炼6个核心心智模型、8条决策启发式和完整的表达DNA'), but the actions are moderately generic and coverage of what the skill does for a user has minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (Jobs' thinking framework, 6 mental models, 8 decision heuristics, expression DNA, analyze/review/feedback) and 'when' (用途 plus concrete trigger phrases), with third-person voice and no missing trigger guidance.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases a user would say — 「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve jobs perspective」「帮我用乔布斯的角度想想」「如果乔布斯会怎么做」「切换到乔布斯」 — including Chinese and English synonyms and paraphrases.	5 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (Steve Jobs perspective role-play) with distinct, specific triggers that are unlikely to fire for any other skill.	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/steve-jobs-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.