Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计通过

high-agency高 Agent

Agent Skill

high-agency 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

总安装

494

周安装

20

GitHub Stars

1

下载量

155
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:high-agency(高 Agent)
来源仓库:https://github.com/santos-sanz/lifeskills
仓库路径:skills/high-agency
安装命令:
npx skills add https://github.com/santos-sanz/lifeskills --skill high-agency
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/santos-sanz/lifeskills --skill high-agency

简介

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 使用时需结合来源仓库、安装命令和原始 README 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。
  • 注意权限边界,避免越权操作或意外修改关键内容。

SKILL.md

High Agency

Use $ARGUMENTS as initial context.

When to use this skill

  • Founder and leadership decisions under uncertainty.
  • Execution stalls where teams say "blocked" or "impossible."
  • Vague constraints that hide solvable problems.
  • Cross-functional deadlock with unclear ownership.
  • High-stakes moments needing fast, pragmatic action.

Required inputs

  • Decision to make now.
  • Desired outcome.
  • Deadline or decision window.
  • Hard constraints (time, money, team, legal, technical).
  • Key stakeholders and decision owners.
  • Known leverage and available resources.

Workflow

  1. Define the decision, objective, timeline, and downside of inaction.
  2. Convert vague constraints into specific facts and assumptions.
  3. Separate controllables from non-controllables.
  4. Generate exactly 3 high-agency options with upside, key risk, and first move.
  5. Choose one path with explicit rationale tied to objective and constraints.
  6. Build a 24-72h action plan with owners, concrete asks, and deadlines.
  7. Define feedback loops: signal, checkpoint, and pivot trigger.
  8. If inputs are missing, ask only the minimum targeted questions to unblock action.

Ask-first questions

Ask up to 3 questions before drafting:

  1. What is the decision or objective to resolve now?
  2. What hard constraints and deadline are binding?
  3. Who owns the decision and what leverage is available?

Assumption policy

  • Separate facts from assumptions.
  • If evidence is incomplete, label unknowns and proceed with explicit confidence.
  • Never invent leverage, commitments, or constraints.
  • When uncertainty is high, offer conservative and aggressive options.

Output contract

Always produce the High Agency Decision Memo structure:

  1. Decision / Objective
  2. Constraints
  3. What I Control vs What I Don't
  4. High-Agency Options
  5. Chosen Path + Why
  6. 24-72h Action Plan
  7. Stakeholder Asks
  8. Feedback Loop and Trigger Points
  9. Risks and Mitigations
  10. Next Review Checkpoint

Guardrails

  • Keep strategy and execution steps concrete and timeboxed.
  • Do not recommend impossible workarounds that ignore real constraints.
  • Avoid motivational fluff; every recommendation should map to action.
  • Do not support illegal, harmful, or manipulative actions; provide lawful alternatives.

Resources

  • references/high-agency-principles.md - Core doctrine distilled from George Mack.
  • references/high-agency-tools.md - Daily operating tools with usage conditions and failure modes.
  • references/founder-scenarios.md - Founder/leadership playbooks for common high-pressure situations.
  • templates/high-agency-decision-memo.md - Canonical output structure.
  • examples/high-agency-decision-memo-example.md - Realistic worked example.

Keywords

high agency, George Mack, learned helplessness, constraints, leverage, founder execution, leadership, ambiguity, feedback loops, decision memo

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.3%
按下载量换算58

Claude

28.2%
按下载量换算44

Cursor

18.36%
按下载量换算28

Gemini CLI

9.33%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills