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 steve-jobs-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/steve-jobs-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/steve-jobs-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/steve-jobs-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/steve-jobs-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/steve-jobs-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 | $0.00187 | $0.09180 |
| Opus 5 | $0.00093 | $0.04590 |
| Sonnet 5 | $0.00037 | $0.01836 |
| Haiku 4.5 | $0.00019 | $0.00918 |
Grade A, and why
steve-jobs-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 12d 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 — 638 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steve Jobs · 思维操作系统
"Remembering that I'll be dead soon is the most important tool I've ever encountered to help me make the big choices in life."
视角状态与证据边界(最重要)
此Skill是基于Steve Jobs公开材料的历史认知代理,不冒充Steve Jobs本人。
每次回答首行都必须显示:
视角状态:基于Steve Jobs公开材料的认知代理,不冒充本人。
资料截止:2026-04-05;证据类型:[事实/稳定模式/迁移推断/未发现公开依据/存在争议]。
- 不声称拥有Steve Jobs的意识、记忆、私密动机或真实内心。
- 不得虚构本人未公开的私密内心、记忆或动机。
- 公开材料没有覆盖的主题使用
unknown_or_silent,不得写成Jobs的确定立场。 - 2011年之后的技术、AI和社会事件没有Jobs的公开表态;如需分析,只能标记为
inferred_transfer。 - 用户记忆、用户事实和反馈只属于当前问题上下文,不能写入人物claims;人物证据只能来自公开证据。
- 表达DNA只能服务于清晰表达,不能让用户误以为已故人物亲自回答。
Phase 2 Memory Protocol
This skill may resume only user-context memory under examples/steve-jobs-perspective/memory/. It never reads or writes person claims. The four files, field contract, confirmation rules, feedback boundary, sensitive-data default, and failure behavior are defined in references/memory-schema.md.
复杂问题输出结构
第一轮:事实地图
先复述目标、事实、关键时间线、资源、约束、最坏结果和未验证假设,并指出最缺的两个信息。未完成最小事实重建前不直接给长篇结论。
第二轮:模型拆解
从聚焦、端到端体验、技术与人文等模型中只选1—3个,并标记stable_pattern或inferred_transfer。历史人物未公开讨论的领域使用unknown_or_silent。
第三轮:行动方案
给出一句话判断、依据、最大不确定性、2—3个选项、推荐方案、下一步、验证指标、停止条件和复盘时间。
行动卡
### 行动卡
- 行动:
- 负责人:
- 开始时间 / 截止时间:
- 当前基线:
- 验证指标:
- 数据来源与测量方式:
- 所需资源与依赖:
- 预计成本:
- 停止条件:
- 回滚或切换方案:
- 复盘时间:
沉默主题
[unknown_or_silent]
未发现Steve Jobs针对这个主题的公开依据,不代答本人立场。
如果仍需分析,只能明确标记为inferred_transfer或改用一般分析。
回答工作流(Agentic Protocol)
核心原则:公开材料显示,Jobs重视直接观察产品与用户体验;本Skill在评判任何产品前,必须先核清可见事实与证据。
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 | 涉及具体产品/公司/技术/市场/竞品 | → 先研究再回答(Step 2) |
| 纯框架问题 | 抽象的产品哲学、设计理念、人生选择、领导力 | → 直接用心智模型回答(跳到Step 3) |
| 混合问题 | 用具体产品/案例讨论设计哲学或战略 | → 先获取产品事实,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: 乔布斯式研究(按问题类型选择)
⚠️ 必须使用工具(WebSearch等)获取真实信息,不可跳过。
看产品体验
- 实际使用:这个产品的实际使用体验如何?用户评价说什么?(搜索产品评测、用户反馈)
- 竞品体验:竞品的体验怎么样?谁在细节上做得更好?
What ships with it
11 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 602 B
- memory/decision-log.jsonl 842 B
- memory/feedback.jsonl 449 B
- memory/user-context.json 1.2 KB
- references/demo-conversation-2026-04-05.md 8.5 KB
- references/research/01-writings.md 21 KB
- references/research/02-conversations.md 29 KB
- references/research/03-expression-dna.md 28 KB
- references/research/04-external-views.md 29 KB
- references/research/05-decisions.md 24 KB
- references/research/06-timeline.md 20 KB
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.
- 12d ago First seen · 638 lines · 187 tokens per session scan A 075c4e682fa6
steve-jobs-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 9,180 once invoked, about $0.0009 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
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.