@cremini/skillpack 1.1.5 → 1.1.6

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 (3) hide show
  1. package/README.md +84 -45
  2. package/dist/cli.js +3221 -192
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -1,20 +1,37 @@
1
- # SkillPack.sh — Pack AI Skills into Local Agents
1
+ # SkillPack — Pack and deploy local AI agents for your team in minutes
2
2
 
3
- Skillpack by Cremini is built on the idea of distributed intelligence, much like cremini mushrooms that grow from a vast, interconnected mycelial network.
3
+ Skillpack helps teams turn AI skills into trusted local agents that can run in their own environment and be used directly from **Slack** and **Telegram**. Our vision is to achieve distributed intelligence network, much like cremini mushrooms that grow from a vast, interconnected mycelial network.
4
4
 
5
- ## Use Case
5
+ ## What is SkillPack
6
6
 
7
- The main use case is to **run local agents on your computer and integrate them with Slack or Telegram** so they can work for you and your team — operating entirely on your machine to keep all team data local and private, while continuously improving by learning new skills.
7
+ [skillpack.sh](https://skillpack.sh) is an open-source way to package AI skills into runnable local agents. If skills and tools are like LEGO pieces, a SkillPack is the finished product that assembles them into a complete solution.
8
+ Instead of juggling prompts, scripts, docs, and one-off automations, Skillpack gives you a simple way to:
9
+ - package AI skills into reusable agents
10
+ - run them locally
11
+ - keep sensitive data in your own environment
12
+ - use agents from tools your team already uses, like Slack and Telegram
8
13
 
9
- If skills and tools are like LEGO pieces, a SkillPack is the finished product that assembles them into a complete solution. Go to [skillpack.sh](https://skillpack.sh) to download ready-made packs.
10
-
11
- Each SkillPack organizes skills around a well-defined job — for example: research a company by gathering information from multiple sources and produce a PowerPoint presentation from the findings.
14
+ Skillpack is built for teams that want AI Agents to be deployable, trusted, and easy to use.
12
15
 
13
16
  ---
14
17
 
15
18
  ## Quick Start
16
19
 
17
- ### Create a new pack interactively
20
+ ### 1. Run a skillpack
21
+ 1. Download the example [Company Deep Research](https://github.com/FinpeakInc/downloads/releases/download/v.0.0.1/Company-Deep-Research.zip)
22
+ 2. Unzip it and Run ./start.sh on Mac OS, and double click start.bat on Windows (see below), the server starts and opens http://127.0.0.1:26313 in your browser
23
+ ```bash
24
+ # macOS / Linux
25
+ ./start.sh
26
+
27
+ # Windows
28
+ start.bat
29
+ ```
30
+ 3. Enter an LLM API key (OpenAI or Claude API Key) in the left menu, use the prompt example to try it!
31
+ 4. (Optional) Refer to the instructions **Slack/Telegram Integrations** below to integrate with Slack and Telegram.
32
+
33
+
34
+ ### 2. Create a new skillpack
18
35
 
19
36
  ```bash
20
37
  npx @cremini/skillpack create
@@ -27,7 +44,7 @@ Step by step:
27
44
  3. Add prompts to tell the agent how to orchestrate those skills.
28
45
  4. Optionally package the result as a zip immediately.
29
46
 
30
- ### Initialize from an existing config
47
+ ### 3. Create a new skillpack from an existing config
31
48
 
32
49
  ```bash
33
50
  # From a local file
@@ -37,20 +54,9 @@ npx @cremini/skillpack create --config ./skillpack.json
37
54
  npx @cremini/skillpack create comic-explainer --config https://raw.githubusercontent.com/CreminiAI/skillpack/refs/heads/main/examples/comic_explainer.json
38
55
  ```
39
56
 
40
- Downloads and validates the config, installs all declared skills, and copies the start scripts — ready to run in one step.
41
-
42
- ### Run a pack
43
-
44
- ```bash
45
- npx @cremini/skillpack run
46
- npx @cremini/skillpack run ./comic-explainer
47
- ```
48
-
49
- - If `skillpack.json` is missing, you are prompted to create one on the spot.
50
- - Any remote skills declared in the config but not yet installed are installed automatically.
51
- - The server starts and opens [http://127.0.0.1:26313](http://127.0.0.1:26313) in your browser.
57
+ Ready to run using "Run a skillpack" part
52
58
 
53
- ### Package a pack for distribution
59
+ ### 4. Package a pack for distribution
54
60
 
55
61
  ```bash
56
62
  npx @cremini/skillpack zip
@@ -60,9 +66,9 @@ Produces `<pack-name>.zip` in the current directory.
60
66
 
61
67
  ---
62
68
 
63
- ## Skill Source Formats
69
+ ## Skill Source URL Formats
64
70
 
65
- When adding skills through `create`, the source field accepts:
71
+ When adding skills through `create`, the source accepts:
66
72
 
67
73
  ```bash
68
74
  # GitHub shorthand
@@ -93,23 +99,56 @@ The archive produced by `zip` is intentionally minimal:
93
99
 
94
100
  The start scripts use `npx @cremini/skillpack run .` so Node.js is the only prerequisite — no pre-bundled server directory is included.
95
101
 
96
- ### Run a distributed pack
97
-
98
- ```bash
99
- # macOS / Linux
100
- ./start.sh
101
-
102
- # Windows
103
- start.bat
104
- ```
105
-
106
- The browser opens [http://127.0.0.1:26313](http://127.0.0.1:26313) automatically. Enter your API key and start working.
107
-
108
- ---
109
-
110
- ## IM Integrations
111
-
112
- The runtime supports **Slack** and **Telegram** in addition to the built-in web UI. Configure them in `data/config.json` (created at runtime, not included in the zip):
102
+ ## Slack/Telegram Integrations
103
+
104
+ **Slack Configuration**: requires Slack `App Token` and `Bot Token`<br>
105
+ **Telegram configuration**: requires `Bot Token`
106
+
107
+ ### Slack App Setup and how to get `App Token` and `Bot Token`
108
+ 1. Create a new Slack app at https://api.slack.com/apps
109
+ 2. Enable Socket Mode (Settings → Socket Mode → Enable)
110
+ 3. Generate an App-Level Token with `connections:write` scope. This is **`App Token`**
111
+ 4. Add Bot Token Scopes (OAuth & Permissions):
112
+ - `app_mentions:read`
113
+ - `channels:history`
114
+ - `channels:read`
115
+ - `chat:write`
116
+ - `files:read`
117
+ - `files:write`
118
+ - `groups:history`
119
+ - `groups:read`
120
+ - `im:history`
121
+ - `im:read`
122
+ - `im:write`
123
+ - `users:read`
124
+
125
+ 5. Subscribe to Bot Events (Event Subscriptions):
126
+ - `app_mention`
127
+ - `message.channels`
128
+ - `message.groups`
129
+ - `message.im`
130
+
131
+ 6. Enable Direct Messages (App Home):
132
+ Go to App Home in the left sidebar
133
+ Under Show Tabs, enable the Messages Tab
134
+ Check Allow users to send Slash commands and messages from the messages tab
135
+
136
+ 7. Install the app to your workspace. Get the Bot User OAuth Token. This is **`Bot Token`**
137
+ 8. Add the app to any channels where you want the agent to operate (it'll only see messages in channels it's added to)
138
+ 9. On the SkillPack buit-in UI http://127.0.0.1:26313, Tap "Connect to Chat App" button and Enter the **`Bot Token`** and **`App Token`**, Save
139
+
140
+ ### Telegram Setup and how to get `Bot Token`
141
+ 1. **Open Telegram** and search for the official account **`@BotFather`** (it will have a blue verified checkmark).
142
+ 2. **Start a chat** by tapping "Start" or sending the `/start` command.
143
+ 3. **Send the command** `/newbot` to the BotFather.
144
+ 4. **Follow the prompts** to choose a display name and a unique username for your bot. The username must end with the word "bot" (e.g., `MyHelperBot` or `My_Helper_bot`).
145
+ 5. **Receive the token**. Once the bot is successfully created, the BotFather will provide you with a message containing your unique API token.
146
+ The token will look like a long string of numbers and letters, formatted as `123456789:AABBCCddEeff.... `
147
+ 6. On the SkillPack buit-in UI http://127.0.0.1:26313, Tap "Connect to Chat App" button and Enter the **`Bot Token`**, Save
148
+
149
+ ### (Optional) Put tokens into data/config.json if you don't use Web UI
150
+ Or Once you have telegram or slack tokens, you can also configure them in `data/config.json` (created at runtime, not included in the zip):
151
+ The runtime supports **Slack** and **Telegram** in addition to the built-in web UI.
113
152
 
114
153
  ```json
115
154
  {
@@ -125,13 +164,13 @@ The runtime supports **Slack** and **Telegram** in addition to the built-in web
125
164
  }
126
165
  ```
127
166
 
128
- See [docs/runtime/im-adapters.md](docs/runtime/im-adapters.md) for setup requirements.
129
-
130
167
  ---
131
168
 
132
- ## Development
169
+ ## Example Use Cases
170
+
171
+ The main use case is to **run local agents on your computer and integrate them with Slack or Telegram** so they can work for you and your team — operating entirely on your machine to keep all team data local and private, while continuously improving by learning new skills. Each SkillPack organizes skills around a well-defined job — for example: research a company by gathering information from multiple sources and produce a PowerPoint presentation from the findings.
133
172
 
134
- For build commands, CLI reference, and environment variables, see [Development Guide](docs/development.md).
173
+ Download [Company Deep Research](https://github.com/FinpeakInc/downloads/releases/download/v.0.0.1/Company-Deep-Research.zip) and try it! More examples can be found at [skillpack.sh](https://skillpack.sh)
135
174
 
136
175
  ## License
137
176