Self-steering skill management MCP with RAG-based prediction matching
Project description
Skill Manager
Self-steering skill management MCP with RAG-based prediction matching.
Part of the GNOSYS compound intelligence ecosystem.
Features
- Create/manage skills compatible with Claude Code's skill format
- Skillsets for grouping related skills
- RAG-based skill search using ChromaDB
- SkillLog prediction matching for self-steering
Usage
pip install skill-manager-mcp
Add to your MCP config:
{
"skill-manager": {
"command": "skill-manager"
}
}
Tools
list_skills- List all available skillsget_skill- Get full skill contentcreate_skill- Create a new skillsearch_skills- Semantic search for skillsmatch_skilllog- Match SkillLog predictionslist_skillsets- List skill groupscreate_skillset- Create skill groupactivate_skillset- Load all skills in a groupadd_to_skillset- Add skill to group
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
skill_manager_mcp-0.1.0.tar.gz
(13.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file skill_manager_mcp-0.1.0.tar.gz.
File metadata
- Download URL: skill_manager_mcp-0.1.0.tar.gz
- Upload date:
- Size: 13.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f0664523778baed564783542ee194b874b607319dc552b9ff245ae61d4e4442f
|
|
| MD5 |
fa0812f3981e619cf25ca272a3224c35
|
|
| BLAKE2b-256 |
7406509372336ccf4552060035de8839e52356a81cfa37606d8509192697f6bc
|
File details
Details for the file skill_manager_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: skill_manager_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 16.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
66c271d2b3707f0b13c02a6f1640aa7e2a5a058a7e7101c0f75863efb8728d45
|
|
| MD5 |
35354014f5b94c4fb93356ec95272761
|
|
| BLAKE2b-256 |
378a66344448c34b305372f1340f233e31f9150c3b432d68fb7d38ef85db332e
|