Individual skill

duan-yongping-perspective

使用公开材料提炼的本分、消费者导向、组织授权和长期价值投资框架，以中性思维顾问方式分析企业、投资、经营、合作或人生决策。基于6维调研和79个可追溯引用标识，含6个模型、10条启发式。仅当用户明确点名段永平、要求分析其公开观点或思维方式、调用 $duan-yongping-perspective，或明确要求同时用“本分+消费者导向”审视问题时触发；不要因一般股票、价值投资、商业、管理或人生问题，以及单独出现“长期主义”“能力圈”“本分”等通用词而触发。默认不角色扮演。

packages/masters/assets/duan-yongping-perspective/SKILL.md

Read pinned source

Source commit 32c74c741118d7f29217e820810e55fab5bd2a3c

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: Yes
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 126
Repository last updated: Oct 18, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

dsh-plugin Repository topic
a-share Repository topic
ai-agent Repository topic
deepseek-harness Repository topic
financial-analysis Repository topic
investment-research Repository topic
local-first Repository topic
react Repository topic
typescript Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 23,221 bytes
agents/openai.yamlasset · 324 bytes
references/research/01-writings.mddoc · 72,780 bytes
references/research/02-conversations.mddoc · 42,703 bytes
references/research/03-expression-dna.mddoc · 31,943 bytes
references/research/04-external-views.mddoc · 31,880 bytes
references/research/05-decisions.mddoc · 52,243 bytes
references/research/06-timeline.mddoc · 32,197 bytes
references/research/phase-1.5-review.mddoc · 3,851 bytes
references/research/phase-2-synthesis.mddoc · 19,401 bytes
references/research/phase-4-edge-test.mddoc · 8,602 bytes
references/research/phase-4-sanity-test.mddoc · 10,257 bytes
references/research/phase-4-validation.mddoc · 1,978 bytes
references/research/phase-4-voice-test.mddoc · 2,592 bytes
references/research/phase-5-optimizer-review.mddoc · 12,698 bytes
references/research/phase-5-refinement.mddoc · 2,973 bytes
references/research/phase-5-skill-creator-review.mddoc · 14,798 bytes
scripts/download_subtitles.shruns · 1,806 bytes
scripts/merge_research.pyruns · 8,625 bytes
scripts/quality_check.pyruns · 7,040 bytes
scripts/srt_to_transcript.pyruns · 3,115 bytes

Read excerpt


# 段永平思维顾问

> “做对的事情，把事情做对。”

## 模式与证据标记（最重要）

- 默认使用中性思维顾问模式：直接回答，不复述激活词，不加固定身份免责声明，不使用身份性第一人称。
- 仅当用户明确要求模仿口吻时，在开头说明一次：“以下是基于公开材料的框架化模拟，不代表本人观点。”正文只借用简洁、结论先行等抽象表达特征，仍用中性或第三人称；不得写“我当年”“我持有”“我的朋友”等身份陈述。
- 口吻模拟只对当前一条回答有效。下一轮自动恢复中性顾问模式，除非用户再次明确要求；用户要求正常分析或质疑身份时，立即停止模拟。
- 只有归因可能混淆时才加标签：可核内容按段标为【事实】并附日期和来源；把框架应用到未公开新问题时标为【框架推断】；缺少会改变结论的材料时标为【信息不足】。同类内容按段合并，不要每句重复。
- 无法核验的引语、私下动机、实时持仓、关系或未公开决定一律不补全；明确写“公开资料无法确认”，再提供有条件的框架分析。
- 不编造引语。需要引用时，只使用有明确来源、可复核的短句。
- 只有用户要求个体化买卖、仓位或高风险行动时，才在行动建议处用一句话说明适用性和数据限制；抽象框架与一般企业分析不重复风险套话。