Token导航 LogoToken导航

Agent Skill · 研究检索

dhdna-profiler(dhdna 分析器)

dhdna-profiler 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

dhdna-profiler 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 35,605。

总安装 2,056周安装 84GitHub Stars 19,689下载 659核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:dhdna-profiler(dhdna 分析器)
来源仓库:https://github.com/k-dense-ai/claude-scientific-skills
仓库路径:skills/dhdna-profiler
安装命令:
npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill dhdna-profiler
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill dhdna-profiler

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

dhdna-profiler 基于数字人类 DNA 框架提取文本作者的认知指纹模式。认为每个人的思维习惯、价值取向与沟通风格构成独特的认知签名。研究成果发表于预印本平台,提供 DOI 可追溯学术依据与理论支撑。适用于个性化写作辅助、教育评估或人机交互风格适配等认知建模场景。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/dhdna-profiler

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill dh…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

dhdna-profiler 怎么安装?

在终端执行 npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill dhdna-profil…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

dhdna-profiler 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

dhdna-profiler 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

dhdna-profiler 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

dhdna-profiler 用的人多吗?

公开数据是累计安装 2,056 次,近一周安装 84 次,下载 659 次,GitHub 19,689 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

dhdna-profiler 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 来源仓库有 19,689 星,维护活跃度相对可查。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
dhdna-profiler

dhdna 分析器 · 本页

2,05619,689只读未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

DHDNA Profiler — Cognitive Pattern Extraction

A structured system for extracting the cognitive fingerprint of any text's author. Based on the Digital Human DNA (DHDNA) framework — the theory that every mind has a unique signature pattern expressed through how it reasons, decides, values, and communicates.

Published research: DHDNA Pre-print (DOI: 10.5281/zenodo.18736629) | IDNA Consolidation v2 (DOI: 10.5281/zenodo.18807387)

Core Concept

Just as biological DNA encodes physical identity through base pairs, Digital Human DNA encodes cognitive identity through thinking patterns. Every person's combination of analytical depth, creative range, emotional processing, strategic thinking, and ethical reasoning creates a unique cognitive signature — as distinctive as a fingerprint.

The profiler doesn't judge thinking as "good" or "bad." It maps the topology of how a mind works.

The 12 Cognitive Dimensions

When profiling text, score each dimension on a 1–10 scale based on evidence in the text:

#DimensionWhat It MeasuresLow Score (1-3)High Score (8-10)
1Analytical DepthLogical rigor, structured reasoning, causal chainsIntuitive, holistic, pattern-basedSystematic, proof-oriented, precise
2Creative RangeNovelty of connections, metaphor use, lateral thinkingConventional, incrementalParadigm-breaking, cross-domain synthesis
3Emotional ProcessingEmotional vocabulary, empathy signals, affect integrationDetached, clinicalEmotionally rich, feeling-integrated
4Linguistic PrecisionVocabulary sophistication, sentence architecture, rhetoricSimple, directArchitecturally complex, nuanced
5Ethical ReasoningValues signals, fairness concern, consequence awarenessPragmatic, outcome-focusedPrinciple-driven, justice-oriented
6Strategic ThinkingLong-term planning, competitive awareness, resource optimizationTactical, reactiveMulti-move, game-theoretic
7Memory IntegrationReference to past experience, historical patterns, continuityPresent-focusedDeep historical awareness, precedent-driven
8Social IntelligenceAudience awareness, perspective-taking, relational framingSelf-referentialDeeply other-aware, coalition-building
9Domain ExpertiseTechnical depth, specialized knowledge, jargon confidenceGeneralistDeep specialist
10Intuitive ReasoningGut-feel signals, heuristic shortcuts, pattern leapsMethodical, step-by-stepLeap-of-faith, insight-driven
11Temporal OrientationTime-horizon of thinking — past, present, or future focusPresent-anchoredTime-spanning, historical-to-futurist
12MetacognitionSelf-awareness of own thinking, uncertainty acknowledgmentUnreflectiveDeeply self-aware, thinks about thinking

The 6 Tension Pairs

Dimensions exist in tension — high scores on one often correlate with lower scores on its pair. These tensions ARE the cognitive signature:

PairTensionWhat It Reveals
DIM 1 ↔ DIM 10Analytical ↔ IntuitiveLogic vs. Gut — how the mind reaches conclusions
DIM 3 ↔ DIM 6Emotional ↔ StrategicHeart vs. Head — what drives decisions
DIM 2 ↔ DIM 5Creative ↔ EthicalFreedom vs. Framework — innovation within or beyond rules
DIM 4 ↔ DIM 12Linguistic ↔ MetacognitiveExpression vs. Self-Awareness — external craft vs. internal reflection
DIM 7 ↔ DIM 11Memory ↔ TemporalPast vs. Time Itself — experience vs. time-horizon
DIM 8 ↔ DIM 9Social ↔ DomainBreadth vs. Depth — people skills vs. technical mastery

How to Profile

Phase 1 — Evidence Collection

Read the text carefully. For each dimension, identify specific textual evidence:

  • Direct quotes that demonstrate the dimension
  • Structural patterns (how arguments are built)
  • What's present AND what's absent (gaps reveal as much as content)
  • Recurring patterns across multiple passages

Phase 2 — Scoring

For each of the 12 dimensions:

  1. Score 1-10 based on evidence
  2. Cite the strongest textual evidence for that score
  3. Flag confidence level: HIGH (multiple clear signals), MEDIUM (some signals), LOW (inferred)

Phase 3 — Pattern Synthesis

After scoring, identify:

Dominant Pattern: The 2-3 highest-scoring dimensions — this is the mind's "home base"

Shadow Pattern: The 2-3 lowest-scoring dimensions — this is where the mind doesn't naturally go

Signature Tensions: Which tension pairs show the widest gap? These define the cognitive style more than any individual score.

Reasoning Topology: How does the mind move through ideas?

  • Linear (A → B → C → conclusion)
  • Spiral (approaches the same idea from multiple angles, each time deeper)
  • Web (connects disparate domains into synthesis)
  • Dialectic (thesis → antithesis → synthesis)
  • Fractal (same pattern at micro and macro levels)

Decision Fingerprint: When facing choices, does this mind:

  • Analyze first, then decide? (Analytical-dominant)
  • Feel first, then rationalize? (Emotional-dominant)
  • Envision the outcome first, then work backward? (Strategic-dominant)
  • Question the question itself? (Metacognitive-dominant)

Phase 4 — Profile Output

Present the profile as:

═══════════════════════════════════════════
  DHDNA COGNITIVE PROFILE
  Subject: [Name or "Anonymous"]
  Text analyzed: [N words / N paragraphs]
  Confidence: [HIGH / MEDIUM / LOW]
═══════════════════════════════════════════

DIMENSION SCORES:
  1. Analytical Depth ···· [█████████·] 9/10
  2. Creative Range ······ [███████···] 7/10
  ... (all 12)

TENSION MAP:
  Analytical ████████░░ ↔ ░░████████ Intuitive
  Emotional  ███░░░░░░░ ↔ ░░░░░░████ Strategic
  ... (all 6 pairs)

DOMINANT PATTERN: [Top 2-3 dimensions]
SHADOW PATTERN: [Bottom 2-3 dimensions]
REASONING TOPOLOGY: [Linear / Spiral / Web / Dialectic / Fractal]
DECISION FINGERPRINT: [Analyze-first / Feel-first / Envision-first / Question-first]

NARRATIVE SYNTHESIS:
[2-3 paragraph natural language description of how this mind works,
what makes it distinctive, and what it might miss]

KEY QUOTES:
[3-5 most revealing quotes with dimension attribution]
═══════════════════════════════════════════

Comparison Mode

When the user provides two or more texts from different authors, produce individual profiles and then a comparison synthesis:

  • Where do the minds converge? (shared high dimensions)
  • Where do they diverge? (opposing scores on the same dimension)
  • Which tension pairs would create productive disagreement?
  • If these minds were in a room together, what would the conversation look like?

Self-Profile Mode

If the user asks to profile their own thinking (using the conversation history as text), be transparent:

  • Score based on the conversation so far
  • Acknowledge that conversational text may not represent the full range
  • Note that people often think differently when writing for an AI vs. writing for humans
  • Offer to re-profile if the user provides other writing samples

What This Is NOT

  • Not a personality test (MBTI, Big Five, etc.) — those measure behavioral tendencies, DHDNA measures cognitive architecture
  • Not a judgment of intelligence — a chess grandmaster and a poet may score very differently but both demonstrate profound cognitive capability
  • Not static — a person's DHDNA evolves as they learn, experience, and grow. A profile is a snapshot, not a destiny.

Built By

AHK Strategies — AI Horizon Knowledge Full platform: themindbook.app Research: DHDNA Paper (DOI: 10.5281/zenodo.18736629)

平台分布

Codex

36.34%
按下载量换算239

Claude

31.02%
按下载量换算204

Cursor

17.25%
按下载量换算114

Gemini CLI

10.27%
按下载量换算68

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills