Skip to content
Back to search

skillpack

SkillWorks with Claude CodeGitHub

Pack and deploy local AI agents for your team in minutes

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/creminiai-skillpack/badge.svg)](/listings/creminiai-skillpack)

HTML

<a href="/listings/creminiai-skillpack"><img src="/api/listings/creminiai-skillpack/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Run a skillpack

1. Download the example - [Garry Tan SkillPack](https://github.com/CreminiAI/skillpack-examples/releases/download/v.0.0.3/garry-tan.zip) - [Company Deep Research SkillPack](https://github.com/FinpeakInc/downloads/releases/download/v.0.0.1/Company-Deep-Research.zip) 2. Unzip it and Run ./start.sh on Mac OS, Or double click start.bat on Windows (see below), the server starts and opens http://127.0.0.1:26313 in your browser

# macOS / Linux
./start.sh

# Windows
start.bat

3. Enter an LLM API key (OpenAI or Claude API Key) in the left menu, use the prompt example to try it! 4. (Optional) Refer to the instructions **Slack/Telegram Integrations** below to integrate with Slack and Telegram.

2. Create a new skillpack

npx @cremini/skillpack create

Step by step:

1. Set the pack name and description. 2. Add skills from GitHub repos, URLs, or local paths. 3. Add prompts to tell the agent how to orchestrate those skills. 4. Optionally package the result as a zip immediately.

3. Create a new skillpack from an existing config

# From a local file
npx @cremini/skillpack create --config ./skillpack.json

# From a remote URL (no directory = current directory)
npx @cremini/skillpack create comic-explainer --config https://raw.githubusercontent.com/CreminiAI/skillpack/refs/heads/main/examples/comic-explainer.json

Ready to run using "Run a skillpack" part

4. Package a pack for distribution

npx @cremini/skillpack zip

Produces `<pack-name>.zip` in the current directory.

To package the skills already present in `skills/` without reinstalling them:

npx @cremini/skillpack zip --skip-skill-install

This faster mode still syncs skill descriptions from the existing `SKILL.md` files before packaging.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 146 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # SkillPack — Pack and deploy local AI agents for your team in minutes
  2. 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.
  3. ## What is SkillPack
  4. [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.
  5. Instead of juggling prompts, scripts, docs, and one-off automations, Skillpack gives you a simple way to:
  6. - package AI skills into reusable agents
  7. - run them locally
  8. - keep sensitive data in your own environment
  9. - use agents from tools your team already uses, like Slack and Telegram
  10. Skillpack is built for teams that want AI Agents to be deployable, trusted, and easy to use.
  11. ---
  12. ## Quick Start
  13. ### 1. Run a skillpack
  14. 1. Download the example
  15. - [Garry Tan SkillPack](https://github.com/CreminiAI/skillpack-examples/releases/download/v.0.0.3/garry-tan.zip)
  16. - [Company Deep Research SkillPack](https://github.com/FinpeakInc/downloads/releases/download/v.0.0.1/Company-Deep-Research.zip)
  17. 2. Unzip it and Run ./start.sh on Mac OS, Or double click start.bat on Windows (see below), the server starts and opens http://127.0.0.1:26313 in your browser
  18. ```bash
  19. # macOS / Linux
  20. ./start.sh
  21. # Windows
  22. start.bat
  23. ```
  24. 3. Enter an LLM API key (OpenAI or Claude API Key) in the left menu, use the prompt example to try it!
  25. 4. (Optional) Refer to the instructions **Slack/Telegram Integrations** below to integrate with Slack and Telegram.
  26. ### 2. Create a new skillpack
  27. ```bash
  28. npx @cremini/skillpack create
  29. ```
  30. Step by step:
  31. 1. Set the pack name and description.
  32. 2. Add skills from GitHub repos, URLs, or local paths.
  33. 3. Add prompts to tell the agent how to orchestrate those skills.
  34. 4. Optionally package the result as a zip immediately.
  35. ### 3. Create a new skillpack from an existing config
  36. ```bash
  37. # From a local file
  38. npx @cremini/skillpack create --config ./skillpack.json
  39. # From a remote URL (no directory = current directory)
  40. npx @cremini/skillpack create comic-explainer --config https://raw.githubusercontent.com/CreminiAI/skillpack/refs/heads/main/examples/comic-explainer.json
  41. ```
  42. Ready to run using "Run a skillpack" part
  43. ### 4. Package a pack for distribution
  44. ```bash
  45. npx @cremini/skillpack zip
  46. ```
  47. Produces `<pack-name>.zip` in the current directory.
  48. To package the skills already present in `skills/` without reinstalling them:
  49. ```bash
  50. npx @cremini/skillpack zip --skip-skill-install
  51. ```
  52. This faster mode still syncs skill descriptions from the existing `SKILL.md` files before packaging.
  53. ---
  54. ## Skill Source URL Formats
  55. When adding skills through `create`, the source accepts:
  56. ```bash
  57. # GitHub shorthand
  58. vercel-labs/agent-skills --skill frontend-design
  59. # Full GitHub URL
  60. https://github.com/JimLiu/baoyu-skills/tree/main/skills --skill baoyu-comic
  61. # Local path
  62. ./skills/my-local-skill
  63. ```
  64. Multiple skill names from the same source can be listed comma-separated.
  65. ---
  66. ## Zip Output
  67. The archive produced by `zip` is intentionally lightweight:
  68. ```text
  69. <pack-name>/
  70. ├── skillpack.json # Pack configuration
  71. ├── job.json # Optional scheduled jobs shipped with the pack
  72. ├── AGENTS.md # Optional pack policy
  73. ├── SOUL.md # Optional pack persona
  74. ├── skills/ # Installed skills
  75. ├── start.sh # One-click launcher for macOS / Linux
  76. └── start.bat # One-click launcher for Windows
  77. ```
  78. The start scripts use `npx @cremini/skillpack run .` so Node.js `22.19.0+` is the only prerequisite — no pre-bundled server directory is included.
  79. If present, `job.json` defines scheduled jobs that travel with the pack and are loaded by the scheduler at runtime.
  80. If present, `AGENTS.md` and `SOUL.md` are read by SkillPack itself when a new chat session starts. SkillPack injects them into the runtime system prompt as pack-level policy and persona, without depending on the host machine's `AGENTS.md`, `.pi/SYSTEM.md`, or `APPEND_SYSTEM.md`.
  81. ## Slack/Telegram Integrations
  82. Talk to your Agents on Slack and Telegram
  83. ### 5 mins to get Slack `App Token` and `Bot Token`
  84. https://skillpack.gitbook.io/skillpack-docs/getting-started/slack-integration
  85. ### 1 min to get Telegram `Bot Token`
  86. https://skillpack.gitbook.io/skillpack-docs/getting-started/telegram-integration
  87. ---
  88. ## Example Use Cases
  89. 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.
  90. 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)
  91. ## Questions?
  92. Join our Discord at https://discord.gg/nj8Br4ePJc
  93. ## License
  94. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.