Self-steering skill management MCP with RAG-based prediction matching
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"skill-manager-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Skill Manager Self-steering skill management MCP with RAG-based prediction matching. Part of the [GNOSYS](https://github.com/sancovp/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 ```bash pip install skill-manager-mcp ``` Add to your MCP config: ```json { "skill-manager": { "command": "skill-manager" } } ``` ## Tools - `list_skills` - List all available skills - `get_skill` - Get full skill content - `create_skill` - Create a new skill - `search_skills` - Semantic search for skills - `match_skilllog` - Match SkillLog predictions - `list_skillsets` - List skill groups - `create_skillset` - Create skill group - `activate_skillset` - Load all skills in a group - `add_to_skillset` - Add skill to group
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.