agent-skills-standard 2.0.0 → 2.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +72 -102
  2. package/dist/index.js +577 -64
  3. package/dist/index.js.map +1 -1
  4. package/package.json +1 -1
package/README.md CHANGED
@@ -1,148 +1,118 @@
1
- # Agent Skills Standard CLI: Deployment & Sync Engine 🚀
1
+ # Agent Skills Standard CLI
2
2
 
3
3
  [![NPM Version](https://img.shields.io/npm/v/agent-skills-standard.svg?style=flat-square)](https://www.npmjs.com/package/agent-skills-standard)
4
4
  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://github.com/HoangNguyen0403/agent-skills-standard/blob/main/LICENSE)
5
5
 
6
- **The heavy-lifting engine for High-Density AI Agent Instructions. Deploy professional standards to any project in seconds.**
6
+ **Sync 237 AI coding standards to any project in one command.** Works with Cursor, Claude Code, GitHub Copilot, Gemini, Windsurf, Trae, Kiro, and Roo.
7
7
 
8
- The `agent-skills-standard` CLI is the official command-line tool to manage, sync, and version-control engineering standards (often called **"Cursor Rules"** or **"Agent Skills"**) across all major AI agents (**Cursor, Claude Code, GitHub Copilot, Gemini, Roo Code, and more**).
9
-
10
- ---
11
-
12
- ## 📌 Table of Contents
13
-
14
- - [💡 What does this tool do?](#-what-does-this-tool-do)
15
- - [🛠 The Solution: Digital DNA for AI](#-the-solution-digital-dna-for-ai)
16
- - [🚀 Installation & Quick Start](#-installation--quick-start)
17
- - [⚙️ Configuration (`.skillsrc`)](#️-configuration-skillsrc)
18
- - [🔒 Privacy & Security](#-privacy--security)
19
- - [❓ FAQ & Links](#-faq--links)
8
+ ```bash
9
+ npx agent-skills-standard@latest init # detect your stack
10
+ npx agent-skills-standard@latest sync # install skills
11
+ ```
20
12
 
21
13
  ---
22
14
 
23
- ## 💡 What does this tool do?
24
-
25
- If the **Agent Skills Standard** is the "instruction manual" for your AI, this CLI is the **delivery engine** that brings those instructions to your project.
15
+ ## What It Does
26
16
 
27
- ### 🎯 Who is this for?
17
+ The CLI takes engineering standards from the [Agent Skills Standard registry](https://github.com/HoangNguyen0403/agent-skills-standard) and installs them into your AI agent's native format:
28
18
 
29
- | Role | Benefit |
30
- | :------------------- | :---------------------------------------------------------------------------------- |
31
- | **🚀 Builders** | No more copy-pasting `.cursorrules`. One command syncs your entire AI workspace. |
32
- | **🛡️ Architects** | Push global engineering standards to every developer's IDE automatically. |
33
- | **📈 Organizations** | Standardize AI behavior across your company. Ensure every agent "knows" your stack. |
34
-
35
- ### 🔄 CLI Sync Workflow
36
-
37
- ```mermaid
38
- graph LR
39
- A[Developers] -- run ags sync --> B[CLI Engine]
40
- B -- fetch --> C[Cloud Registry]
41
- C -- deploy --> D[Local IDE Settings]
42
- D -- power-up --> E[Expert AI Coding]
19
+ ```bash
20
+ npx agent-skills-standard sync
43
21
 
44
- style E fill:#dcfce7,stroke:#166534
22
+ - Updated .cursor/skills/ (Cursor)
23
+ - Updated .claude/skills/ (Claude Code)
24
+ - Updated .github/skills/ (Copilot)
25
+ - Generated _INDEX.md for 8 categories.
26
+ - AGENTS.md router index updated.
45
27
  ```
46
28
 
47
- ---
48
-
49
- ## 🛠 The Solution: Digital DNA for AI
50
-
51
- Modern AI coding agents are powerful, but giant rule files consume **30% - 50% of the AI's memory**, making it less effective. Agent Skills Standard solves this by treating prompt instructions as **versioned dependencies**.
52
-
53
- - **🎯 Smart Loading**: We use a "Search-on-Demand" pattern. The AI only looks at detailed examples when it specifically needs them, saving its memory for your actual code.
54
- - **🚀 High-Density Language**: We use a specialized "Compressed Syntax" that is **40% more efficient** than normal English. This means the AI understands more while using fewer resources.
55
- - **🔁 One-Click Sync**: A single command ensures your AI tool stays up-to-date with your team's latest standards.
56
-
57
- > [!IMPORTANT]
58
- > **Context is Currency**: By reducing instruction overhead by **88%**, you free up your AI's memory and budget for complex logic and large codebases.
29
+ The result: your AI agent reads `AGENTS.md`, follows the router to the right category, and loads only the skills that match what you're editing.
59
30
 
60
31
  ---
61
32
 
62
- ## 🚀 Installation & Quick Start
63
-
64
- You can run the tool instantly without installing, or install it globally for convenience:
65
-
66
- ```bash
67
- # Use instantly (Recommended)
68
- npx agent-skills-standard@latest init
69
- npx agent-skills-standard@latest sync
70
-
71
- # Or install globally
72
- npm install -g agent-skills-standard
73
- ags sync
74
- ```
33
+ ## Commands
75
34
 
76
- ### 🛠 Basic Commands
77
-
78
- - `init`: Detect your project type and choose which "skills" you want your AI to have.
79
- - `sync`: Fetch the latest high-density instructions and install them into your hidden agent folders (like `.cursor/skills/` or `.github/skills/`).
80
- - `validate`: Validate custom skills against the standard.
81
- - `feedback`: Submit feedback to improve the global registry.
35
+ | Command | What it does |
36
+ | :--------- | :--------------------------------------------------------------------------------------------- |
37
+ | `init` | Detects your tech stack (Flutter, React, Go, etc.) and creates a `.skillsrc` config |
38
+ | `sync` | Fetches skills from the registry, writes to agent folders, generates `_INDEX.md` + `AGENTS.md` |
39
+ | `validate` | Checks your custom skills against format and token standards |
40
+ | `feedback` | Submits improvement suggestions to the registry |
41
+ | `upgrade` | Updates the CLI to the latest version |
82
42
 
83
43
  ---
84
44
 
85
- ## ⚙️ Configuration (`.skillsrc`)
45
+ ## Configuration
86
46
 
87
- The `.skillsrc` file allows you to customize how skills are synced to your project.
47
+ The `.skillsrc` file controls everything:
88
48
 
89
49
  ```yaml
90
50
  registry: https://github.com/HoangNguyen0403/agent-skills-standard
91
- agents: [cursor, copilot]
51
+ agents: [cursor, copilot, claude]
92
52
  skills:
93
- flutter:
94
- ref: flutter-v1.1.0
95
- # 🚫 Exclude specific sub-skills from being synced
96
- exclude: ['getx-navigation']
97
- # ➕ Include specific skills (supports cross-category 'category/skill' syntax)
98
- include:
99
- - 'bloc-state-management'
100
- - 'react/hooks'
101
- # 🔒 Protect local modifications from being overwritten
102
- custom_overrides: ['bloc-state-management']
103
- # 🤖 Optional: Sync workflows to .agent/workflows/
104
- workflows: true
53
+ react:
54
+ ref: react-v1.3.1
55
+ golang:
56
+ ref: golang-v1.3.1
57
+ exclude: ['golang-tooling'] # skip skills you don't need
58
+ common:
59
+ ref: common-v2.0.1
60
+ custom_overrides: ['common-tdd'] # protect your local edits
105
61
  ```
106
62
 
107
63
  ---
108
64
 
109
- ## 🔒 Privacy & Security
65
+ ## What Gets Generated
66
+
67
+ After `sync`, your project contains:
110
68
 
111
- We take security seriously. Here is what you need to know:
69
+ ```bash
70
+ project/
71
+ AGENTS.md # Router table (~20 lines)
72
+ .cursor/skills/
73
+ golang/_INDEX.md # Trigger table for Go skills
74
+ golang/golang-language/SKILL.md # The actual skill
75
+ golang/golang-testing/SKILL.md
76
+ react/_INDEX.md # Trigger table for React skills
77
+ react/react-hooks/SKILL.md
78
+ ...
79
+ ```
112
80
 
113
- - **No Code Execution**: The CLI `sync` command only downloads **text files** (Markdown/JSON). It does _not_ download or execute binaries, scripts, or unknown code.
114
- - **Transparent Operations**: The CLI simply fetches text files from the [official registry](https://github.com/HoangNguyen0403/agent-skills-standard) and copies them to your local `.agent/skills` folder. No background daemons or hidden network calls.
115
- - **Privacy First**: We never collect usage telemetry or analytics. Feedback is only shared if you explicitly trigger it using `ags feedback`.
81
+ **`AGENTS.md`** maps file extensions to category indexes.
82
+ **`_INDEX.md`** has two sections: **File Match** (auto-check against your file) and **Keyword Match** (activates when you mention a concept).
83
+ **`SKILL.md`** is the skill itself — loaded on demand, averaging ~500 tokens.
116
84
 
117
85
  ---
118
86
 
119
- ## ❓ FAQ & Links
120
-
121
- <details>
122
- <summary><b>Do I need to install this globally?</b></summary>
123
- <br>
124
- We recommend using <code>npx agent-skills-standard sync</code> to always use the latest version without global installation.
125
- </details>
87
+ ## Privacy & Security
126
88
 
127
- <details>
128
- <summary><b>Does it overwrite my custom rules?</b></summary>
129
- <br>
130
- No. If you have custom rules in <code>.cursorrules</code> or other files, you can use the <code>custom_overrides</code> feature in your <code>.skillsrc</code> and the CLI will intelligently skip overwriting them.
131
- </details>
89
+ - **Text only** — the CLI downloads Markdown and JSON files, never binaries or scripts
90
+ - **No telemetry** — zero data collection, no background processes
91
+ - **Transparent** — fetches from the [public registry](https://github.com/HoangNguyen0403/agent-skills-standard), nothing hidden
92
+ - **Override protection** — `custom_overrides` prevents the CLI from touching your local modifications
132
93
 
133
- <br>
94
+ ---
134
95
 
135
- ### 🔗 Useful Links
96
+ ## Links
136
97
 
137
- - **Registry Source**: [GitHub Repository](https://github.com/HoangNguyen0403/agent-skills-standard)
138
- - **CLI Architecture**: [Internal Services & Design](https://github.com/HoangNguyen0403/agent-skills-standard/blob/develop/cli/ARCHITECTURE.md)
139
- - **Standard Specs**: [Documentation](https://github.com/HoangNguyen0403/agent-skills-standard#📂-standard-specification)
140
- - **Issues**: [Report a bug](https://github.com/HoangNguyen0403/agent-skills-standard/issues)
98
+ - [Registry & Skills](https://github.com/HoangNguyen0403/agent-skills-standard)
99
+ - [Architecture](./ARCHITECTURE.md)
100
+ - [Report an Issue](https://github.com/HoangNguyen0403/agent-skills-standard/issues)
141
101
 
142
102
  ### 📜 Benchmark History
143
103
 
144
104
  | Version | Date | Skills | Avg Tokens | Savings (%) | Report |
145
105
  | --- | --- | --- | --- | --- | --- |
106
+ | v2.1.0 | 2026-04-04 | 237 | 526 | 86% | [Report](benchmarks/archive/v2.1.0.md) |
107
+ | v2.0.1 | 2026-03-30 | 238 | 527 | 86% | [Report](benchmarks/archive/v2.0.1.md) |
146
108
  | v2.0.0 | 2026-03-25 | 235 | 523 | 86% | [Report](benchmarks/archive/v2.0.0.md) |
147
109
  | v1.10.3 | 2026-03-21 | 234 | 505 | 86% | [Report](benchmarks/archive/v1.10.3.md) |
148
110
  | v1.10.1 | 2026-03-16 | 229 | 428 | 88% | [Report](benchmarks/archive/v1.10.1.md) |
111
+ | v1.10.0 | 2026-03-16 | 229 | 434 | 88% | [Report](benchmarks/archive/v1.10.0.md) |
112
+ | v1.9.3 | 2026-03-15 | 229 | 460 | 87% | [Report](benchmarks/archive/v1.9.3.md) |
113
+ | v1.9.2 | 2026-03-07 | 228 | 458 | 87% | [Report](benchmarks/archive/v1.9.2.md) |
114
+ | v1.9.1 | 2026-03-07 | 228 | 458 | 87% | [Report](benchmarks/archive/v1.9.1.md) |
115
+ | v1.9.0 | 2026-03-05 | 228 | 457 | 88% | [Report](benchmarks/archive/v1.9.0.md) |
116
+ | v1.8.0 | 2026-03-02 | 228 | 443 | 88% | [Report](benchmarks/archive/v1.8.0.md) |
117
+ | v1.7.3 | 2026-02-25 | 222 | 418 | 89% | [Report](benchmarks/archive/v1.7.3.md) |
118
+ | v1.7.2 | 2026-02-25 | 220 | 413 | 89% | [Report](benchmarks/archive/v1.7.2.md) |