Standards
A self-learning AI standards system that automatically captures tool executions from Claude Code and extracts patterns to continuously improve CLAUDE.md files and project standards. Built by Matt Strautmann, the implementation uses significance scoring to identify valuable learning opportunities from tool usage, tracks agent performance over time, and maintains temporal knowledge graphs to understand how preferences evolve. The system provides intelligent hooks for automatic knowledge capture, pattern extraction for learning from corrections and repetitions, and validation engines that enforce quality gates while learning from failures, making it useful for development teams who want their AI assistants to automatically learn and adapt project-specific conventions without manual intervention.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/airmcp-com/mcp-standards
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Standards from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.