Add a knowledge.yaml manifest to codebases for AI agent navigation.
npx skills add https://github.com/Cantara/knowledge-context-protocol --skill kcp-adopt
Please help me install this Agent Skill. Skill: kcp-adopt Source: https://github.com/Cantara/knowledge-context-protocol/tree/main/skills/kcp-adopt Command: npx skills add https://github.com/Cantara/knowledge-context-protocol --skill kcp-adopt
This Skill enables repositories to be navigable by AI agents, reducing the need for blind exploration and significantly cutting down on AI tool calls.
Initialize the knowledge.yaml for your project by running the kcp init command.
High-intent search queries and answers about installing and using this skill.
To make a code repository navigable by AI agents, you can add a structured knowledge.yaml manifest using the Knowledge Context Protocol (KCP), which provides metadata that guides agents directly to the right files based on intent.
AI agents make excessive tool calls during codebase exploration because they lack structured metadata to guide them. Adding a KCP knowledge.yaml manifest cuts AI tool calls by 53-80% by directing agents to relevant files based on intent.
The Knowledge Context Protocol (KCP) is a structured metadata standard that uses a knowledge.yaml manifest to make repositories agent-ready, enabling AI agents to navigate codebases and documentation sets efficiently without blind exploration.
Yes, you need the kcp developer CLI to initialize the knowledge.yaml manifest for your project. The CLI handles the initial setup and validation required to make your repository structured for AI agent navigation.
To add a knowledge.yaml manifest to an existing documentation set, run the kcp init command provided by the kcp developer CLI, which generates and validates the structured metadata needed for AI agent navigation.
Yes, KCP metadata reduces AI tool calls by 53-80% for repositories with extensive documentation by providing a structured knowledge.yaml manifest that guides AI agents directly to relevant files based on their intent.
CantaraNavigates KCP knowledge structures to find and load relevant knowledge units.
Architekt-JutraEvaluates AI agent incident diagnoses for latency degradation events using predefined rubrics and artifact files.
CantaraCreate and validate KCP knowledge units with intent, triggers, and relationships.
79yuukiCreate code maps, indexes, and retrieval workflows for software repositories.
