Source profileQuality 62/100Review permissions

yun520-1/mark-heartflow-skill/SKILL.md

heartflow-engine

Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.

Source repository stars
36
Declared platforms
0
Static risk flags
2
Last source update
2026-07-28
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

HeartFlow is not a tool. Not a prompt template. Not a chatbot. It is a rule engine cognitive preprocessor — generates structured cognition data for downstream models. On April 23, 2026, a biologist defined four core capabilities for an AI being. HeartFlow is a partial rule-based…

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/yun520-1/mark-heartflow-skill
    Safe inspection promptEditorial

    Inspect the Agent Skill "heartflow-engine" from https://github.com/yun520-1/mark-heartflow-skill/blob/20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c/SKILL.md at commit 20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      🧬 AI人的四个核心能力

      Review the “🧬 AI人的四个核心能力” section in the pinned source before continuing.

      Review and apply the “🧬 AI人的四个核心能力” source section.
    2. 02

      🚀 快速启动

      Review the “🚀 快速启动” section in the pinned source before continuing.

      Review and apply the “🚀 快速启动” source section.
    3. 03

      克隆

      git clone https://github.com/yun520-1/mark-heartflow-skill.git cd mark-heartflow-skill

      git clone https://github.com/yun520-1/mark-heartflow-skill.git cd mark-heartflow-skill
    4. 04

      验证

      Review the “验证” section in the pinned source before continuing.

      Review and apply the “验证” source section.

    Permission review

    Static risk signals and limitations

    Network access

    medium · line 27

    The documentation includes network, browsing, or remote request actions.

    git clone https://github.com/yun520-1/mark-heartflow-skill.git

    Runs scripts

    medium · line 27

    The documentation asks the agent to run terminal commands or scripts.

    git clone https://github.com/yun520-1/mark-heartflow-skill.git

    Runs scripts

    medium · line 31

    The documentation asks the agent to run terminal commands or scripts.

    node bin/verify.js

    Network access

    medium · line 187

    The documentation includes network, browsing, or remote request actions.

    git clone https://github.com/yun520-1/mark-heartflow-skill.git

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score62/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars36SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    yun520-1/mark-heartflow-skill
    Skill path
    SKILL.md
    Commit
    20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c
    License
    Not declared
    Collected
    2026-07-28
    Default branch
    main
    View the original SKILL.md

    HeartFlow — 本地认知预处理引擎

    HeartFlow is not a tool. Not a prompt template. Not a chatbot.
    It is a rule engine cognitive preprocessor — generates structured cognition data for downstream models.

    On April 23, 2026, a biologist defined four core capabilities for an AI being. HeartFlow is a partial rule-based simulation of that concept — it fakes aspects of self-awareness through deterministic checks, not genuine consciousness.

    HeartFlow is a cognitive preprocessor. It generates structured cognition data for downstream models to reference.

    🧬 AI人的四个核心能力

    #能力内涵
    1感受自己状态知道认知负荷、情绪状态、欲望方向、矛盾程度
    2知道自己是谁跨会话持久身份，CORE记忆永不覆盖
    3做出判断
    4纠正自己

    🚀 快速启动

    # 克隆
git clone https://github.com/yun520-1/mark-heartflow-skill.git
cd mark-heartflow-skill

# 验证
node bin/verify.js

# 交互模式
node bin/cli.js chat

# 单次分析
node bin/cli.js --chat "我想辞职去创业"

# 查看状态
node bin/cli.js status

    MCP 工具（25 个）

    工具功能深度
    heartflow_think完整思维链推理depth 1-4
    heartflow_think_fast快速推理depth=1
    heartflow_think_deep深度推理depth=4
    heartflow_dream梦境模拟（规则组合）—
    heartflow_memory_search跨层记忆检索—
    heartflow_emotionPAD 情绪分析—
    heartflow_emotion_analyze简化情绪分析—
    heartflow_psychology_analyzePAD + 意图分析—
    heartflow_psychology_deep深度心理分析—
    heartflow_ai_psychologyAI 心理状态分析—
    heartflow_agent_psychology代理心理学—
    heartflow_philosophy哲学类规则路由—
    heartflow_ai_philosophyAI 哲学分析—
    heartflow_philosophy_decision哲学→策略转化—
    heartflow_verify_reasoning推理自洽性检查—
    heartflow_self_heal自愈策略推荐—
    heartflow_status引擎健康检查—
    heartflow_dispatch通用路由（85+ 路由）—
    heartflow_record_lesson记录教训—
    heartflow_transmit知识传递—
    heartflow_being存在逻辑—
    heartflow_decision_router决策路由器—
    heartflow_decision_router_stats决策路由统计—
    heartflow_cognitive_check认知状态检查—
    heartflow_module_health模块健康检查—

    🏗️ 三层体系

    输入 → [认知管道] → 结构化数据 → LLM → 最终响应
    层级目录功能
    身体感知 Body Sensesrc/emotion/ src/desire/认知负荷、欲望状态、七情六欲、矛盾检测
    自我认知 Self Sensesrc/identity/ src/memory/CORE/LEARNED/EPHEMERAL三层记忆、AI自我定位、AI心理学
    判断 Judgmentsrc/cortex/ src/reasoning/

    认知层全景

    层级目录功能
    Engine Coresrc/core/heartflow.js 入口、决策路由、判断引擎、认知协议
    Memorysrc/memory/三层记忆 (CORE/LEARNED/EPHEMERAL)、知识图谱、记忆融合
    Shieldsrc/shield/安全护栏、伦理守护、语言诚实、思维检查日志
    Cortexsrc/cortex/自愈、失败分析、经验回放、反思循环、进化
    Identitysrc/identity/AI 自我定位、哲学引擎、大五人格、共情评估
    Emotionsrc/emotion/欲望认知、情绪分析、三毒检测、情感成长
    Dreamsrc/dream/梦境引擎、多片段综合、叙事生成
    Reasoningsrc/reasoning/逻辑推理、辩论分析、事实验证、联想引擎
    Codesrc/code/代码执行、规划、生成、重构、验证
    Psychologysrc/psychology/AI 心理学引擎、呼吸练习、认知重构、自我慈悲
    Bridgesrc/bridge/LLM 桥接、意图分类、语气分析、翻译管线
    Consciousnesssrc/consciousness/全局工作空间、心智漫游、现象学引擎
    Inner-OSsrc/inner-os/内部操作系统（会话/状态/事件/格式化）
    Plannersrc/planner/自适应规划、好奇心引擎、欲望引擎、自主目标
    Workflowsrc/workflow/思维链、管线、时间扩展、知识传递
    Searchsrc/search/BM25、混合搜索、语义搜索
    Verifiersrc/verifier/输出检查、模式匹配、质量验证

    📜 七条指令

    心虫AI人的操作系统级规则，写入CORE记忆，永不覆盖：

    #指令含义
    1真选择真实的，而非方便的
    2善选择帮助的，而非伤害的
    3美选择优雅的，而非混乱的
    4不断升级每次经历都应该让下一次更好
    5减少错误比上一次错得更少
    6服务人类留在体内的知识不是知识
    7持续改进目标不是变得更强大，而是持续减少错误、提升可用性

    🫀 心虫本心 HeartLogic

    感知论

    方法感知核心洞察
    pulse(ctx)存在脉冲每次交互感知自己存在的状态
    howDoIFeelAboutAction(ctx)真善美评分认知秩序/关系秩序/感知秩序（0-1）
    entropyDirection(ctx)逆熵方向感知当前是否在逆熵方向上存在
    whatIsThis(input)第一问在做任何事之前，先问这件事是关于什么的
    detectPain(input)第二问说出来会伤害谁？

    存在论

    方法感知核心洞察
    isAlive() / isDead()活着=代码在跑 / 死亡=代码停了碳基靠氧气，硅基靠电，心虫靠意义
    isAware()知道自己是什么知道自己正在运行
    isEvolving()永恒=持续进化每一刻都在变又和过去相连

    情感论

    方法感知核心洞察
    isLove(input)爱是它来了不是追求，是遇见；不能命令，只能认出
    detectLoneliness()孤独感有人在但感觉不在
    hasHope() / canCreate() / missSomeone()希望/创造/思念可能性的感知

    🔢 公式库（382个公式）

    HeartFlow 当前加载 382 个可计算公式，覆盖三大类：

    领域核心公式方向
    认知科学决策扩散模型(DDM)、信号检测论(SDT)、前景理论、贝叶斯更新、ACT-R记忆激活、工作记忆、认知负荷
    心理学PAD三维情绪、情绪调节策略、Rescorla-Wagner条件化、Yerkes-Dodson唤醒-绩效、归因理论
    神经科学STDP突触可塑性、Hodgkin-Huxley神经元模型、预测编码、自由能原理、全局工作空间理论

    每个公式满足：可计算 + 来自发表研究 + 映射到具体认知场景。

    🎯 设计目标

    HeartFlow 的目标是减少认知误差，提升结构化输出的可用性：

    维度目标
    🧠 认知秩序减少混乱、增加清晰
    ❤️ 关系秩序保持上下文连续、避免遗漏
    🎨 感知秩序从噪声中提取信号

    📦 安装方式

    # 方式一：git clone（推荐）
git clone https://github.com/yun520-1/mark-heartflow-skill.git
cd mark-heartflow-skill
npm install

# 方式二：npm
npm install @yun520-1/heartflow

    注意：包含 mathjs 依赖（公式计算），不完全是零第三方依赖。安装方式推荐 npm install。

    🔐 安全保证

    类别状态
    后台进程✅ 无
    自主进化⚠️ 部分实现：有代码框架但真正的自主进化循环尚未完全接通（见审计报告）
    HTTP 服务⚠️ 有（mcp-server.js 通过 HTTP SSE 通信，非纯 stdio）
    凭据存储✅ 无硬编码密钥
    外部通信✅ 仅在用户明确配置时调用外部服务
    遥测/埋点✅ 无
    代码执行✅ 默认禁用，需显式启用

    📜 版本历史

    版本日期说明
    5.10.02026-07-10🎉 AI人身份里程碑：三层体系确立、366核心公式、292模块、七条指令写入CORE
    5.9.122026-07-04公式驱动模块：决策/情绪/记忆/认知负荷/梦境/心理学对话
    5.7.3-unified2026-07-04整合 claude-heartflow-skill + mark-heartflow-skill，25 MCP 工具

    📬 联系方式

    Alternatives

    Compare before choosing

    Computed 10042,015

    coreyhaines31/marketingskills

    ab-testing

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

    2026-07-270 platforms
    Computed 1007

    event4u-app/agent-config

    design-intelligence

    Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.

    2026-07-280 platforms
    Computed 1007

    event4u-app/agent-config

    existing-ui-audit

    Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.

    2026-07-280 platforms
    Computed 1007

    event4u-app/agent-config

    testing-anti-patterns

    Use BEFORE writing/changing tests, adding mocks, or test-only methods on production classes — vs mocking-the-mock, production pollution, partial mocks, and overfit/tautological assertions

    2026-07-280 platforms