S
SylphxAI/skills
Universal Agent Skills and domain reference standards for Claude Code, Codex, OpenCode, and Agent Skills…
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"sylphxai-skills": {
"command": "npx",
"args": ["skills"]
}
}
}解析自我们于 2026-11-06 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"sylphxai-skills": {
"command": "npx",
"args": ["skills"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio sylphxai-skills -- npx skills
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 1 ★ · SylphxAI/skills · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：开源项目
- 收录与活跃
- 收录于 2026-11-07 · 最近见到 2026-11-14 · 共见到 8 次 · 被 7 个来源列出
- 评分构成
- 综合分 703 · 1 ★ · 7 个来源 · repo
- 安装
npx skills
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx skills。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: Agent 技能。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
SylphxAI/skills；我们收录于 2026-11-07；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# Sylphx Agent Skills (SylphxAI/skills)
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Opinionated, scenario-driven Agent Skills and colocated reference methodologies for autonomous AI agents and human-agent teams across software engineering, system architecture, product design, commercial/partner negotiations, operations, marketing/growth, customer support, and clear communication.
## Core Design Philosophy: Opinionated Methodology vs. Organization State
1. Skills Encode Chosen Methodology as a Swappable Stack (Not Neutral Option Lists, Intuition, or Organization State):
In every discipline—how we reason scientifically, how we price and monetize, how we design systems and capacity, how we deliberate as a team, which technology stack we build on, how we score risk, how we prioritize work, how we ship software, and how we write—there are competing schools of thought.
Instead of inventing ad-hoc rules, relying on subjective intuition, or piling on negative prohibitions ("do not do X"), we select proven, peer-reviewed or industry-validated methodologies calibrated to a small, self-funded, agent-native company, and record them in each standard's Method sources / Methods table registry (with an explicit replacement trigger so any method can be swapped when a better-evidenced paper or industry practice outperforms it):
How We Think, Decide & Design (challenge): Strong Inference & Falsification (Platt 1964; Popper 1959), Analysis of Competing Hypotheses (Heuer 1999), Theory of Constraints & Queueing Physics (Goldratt 1984; Little 1961; Kingman 1961), Value-Based Market Pricing & Gross-Margin Maximization (commercial.md — Nagle & Müller; Ramanujam & Tacke 2016; Skok SaaS Metrics), Freemium Power-Law IAP Economics (games.md — Seufert 2014), Simple Concept / Deep Implementation, 10x/100x Scale, Scale-to-Zero (architecture.md), Opinionated Stack Selection (stack.md), and Quantitative 5×5 Risk Scoring (risk.md — ISO 31000; IEC 31010; FAIR).
How We Deliberate (swarm-fuse): Dynamic Group Facilitation (Topic × Participant Context), Independent Delphi + Red-Team Challenge Angles, and Single-Writer Coordination.
How We Prioritize, Build, Unblock & Ship (author-item, deliver-and-verify, prove-it, unblock, refactor): Cost of Delay Divided by Duration (priority.md — Reinertsen 2009 CD3; Graham 2015 Default Alive/Dead), Three-Stage Acceptance Test-Driven Development (ATDD), Work-in-progress limits and work item age, Release Scope Management, Upstream Contribution and Separation of Concerns (first-party client, zero backdoors), Complete Replacement + Systemic Corrective Action + Mistake-Proofing, and Primary-Source Verification.
How We Communicate & Serve (clear-writing, customer-support, ambassador): Audience × Purpose × Channel calibration, Concrete ❌ Bad vs ✅ Good side-by-side examples, Deterministic Support Case-State Machines, and In-Character Ambassador (大使) Companionship with Adversarial Turing Self-Testing.
Organization State Lives Outside Skills: Company-specific state (current headcount/size, active project portfolio, live server inventory, or specific rows in an accepted-risk register) belongs in the workspace repository or Organization Knowledge—never inside a skill.
2. Three-Stage Acceptance Test-Driven Development (ATDD) for Every Outcome:
## Core Design Philosophy: Opinionated Methodology vs. Organization State
1. Skills Encode Chosen Methodology as a Swappable Stack (Not Neutral Option Lists, Intuition, or Organization State):
In every discipline—how we reason scientifically, how we price and monetize, how we design systems and capacity, how we deliberate as a team, which technology stack we build on, how we score risk, how we prioritize work, how we ship software, and how we write—there are competing schools of thought.
Instead of inventing ad-hoc rules, relying on subjective intuition, or piling on negative prohibitions ("do not do X"), we select proven, peer-reviewed or industry-validated methodologies calibrated to a small, self-funded, agent-native company, and record them in each standard's Method sources / Methods table registry (with an explicit replacement trigger so any method can be swapped when a better-evidenced paper or industry practice outperforms it):
How We Think, Decide & Design (challenge): Strong Inference & Falsification (Platt 1964; Popper 1959), Analysis of Competing Hypotheses (Heuer 1999), Theory of Constraints & Queueing Physics (Goldratt 1984; Little 1961; Kingman 1961), Value-Based Market Pricing & Gross-Margin Maximization (commercial.md — Nagle & Müller; Ramanujam & Tacke 2016; Skok SaaS Metrics), Freemium Power-Law IAP Economics (games.md — Seufert 2014), Simple Concept / Deep Implementation, 10x/100x Scale, Scale-to-Zero (architecture.md), Opinionated Stack Selection (stack.md), and Quantitative 5×5 Risk Scoring (risk.md — ISO 31000; IEC 31010; FAIR).
How We Deliberate (swarm-fuse): Dynamic Group Facilitation (Topic × Participant Context), Independent Delphi + Red-Team Challenge Angles, and Single-Writer Coordination.
How We Prioritize, Build, Unblock & Ship (author-item, deliver-and-verify, prove-it, unblock, refactor): Cost of Delay Divided by Duration (priority.md — Reinertsen 2009 CD3; Graham 2015 Default Alive/Dead), Three-Stage Acceptance Test-Driven Development (ATDD), Work-in-progress limits and work item age, Release Scope Management, Upstream Contribution and Separation of Concerns (first-party client, zero backdoors), Complete Replacement + Systemic Corrective Action + Mistake-Proofing, and Primary-Source Verification.
How We Communicate & Serve (clear-writing, customer-support, ambassador): Audience × Purpose × Channel calibration, Concrete ❌ Bad vs ✅ Good side-by-side examples, Deterministic Support Case-State Machines, and In-Character Ambassador (大使) Companionship with Adversarial Turing Self-Testing.
Organization State Lives Outside Skills: Company-specific state (current headcount/size, active project portfolio, live server inventory, or specific rows in an accepted-risk register) belongs in the workspace repository or Organization Knowledge—never inside a skill.
2. Three-Stage Acceptance Test-Driven Development (ATDD) for Every Outcome:
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/sylphxai-skills/)
- 来源
- github · https://github.com/SylphxAI/skills
- 按领域浏览
- Agent 技能
- Traction
- 1 ★
- 收录来源
- 7 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。