Kvendra Skills

Kvendra Skills: publication card

What it is and what problem it solves

This publication gathers the engineering knowledge of kvendra-skills, an open source component of Kvendra, a system that gives AI agents a structured knowledge base (KB) and lets them operate on real infrastructure without handing them the secrets directly.

• SKILLS — kvendra-skills (Markdown prompts). It is the Claude Code plugin with the official Kvendra skills: 28 skills that work on the KB through its MCP tools. Pipelines (new-feature, bug, incident-manager, release-manager, regression) coordinate specialised subagents (planner, implementer, validator, tester, updater, analyzer, functional-expert), open a transaction, write draft entities and activate them together, so every change leaves a trace in the KB. Other skills cover documentation, requirements, consultancy, the lifecycle of a project's CLAUDE.md, environment checks and deployment. The same repository ships kvendra-companion, an optional read-only band above the Claude Code prompt. It is for developers and teams who want their AI agents to keep a structured, auditable project memory while they work.
• Sister project — kvendra-platform (TypeScript; not included in this publication). It is the single-tenant KB engine that anyone can run on their own machine; it exposes the core subset of the MCP tool contract the skills use against the hosted service (entities, transactions, search, configuration and help). It has its own publication in the catalog.
• Sister project — kvendra-cli (Rust; not included in this publication). It is the MCP capability broker with a local zero-knowledge vault: the skills that run git, cloud or package operations do it through the broker, and the tokens stay in the local vault. It has its own publication in the catalog.

How to use it and fork it

Navigating the publication. The publication has three parts, and each one is reachable from the top navigation:

• The cover page — this card. Read it first: it tells you what is in the snapshot and how it is licensed.
• Manuals — the English book of the skills, organised in chapters: overview, installation and sign-in, the KB concepts the skills rely on, pipelines, subagents, documentation and reporting, consultancy and requirements, project setup and environment, the companion band, and contributing and licensing.
• The entity index — every published KB entity, grouped by type. Each entity page shows its content, its tags and its relations. Start with the component entity CMP-KVD-SKILLS, which describes the scope, the skills by family and the status of the component, and follow the relations from there.

Relations to entities that are not part of this publication are shown as "[private entity]", without an id or a title. This is intentional.

Using the code. The repository is public on GitHub and is also the plugin marketplace:

• KvendraAI/kvendra-skills (https://github.com/KvendraAI/kvendra-skills) — in Claude Code, run /plugin marketplace add KvendraAI/kvendra-skills and then /plugin install kvendra-skills@kvendra-marketplace (and, optionally, /plugin install kvendra-companion@kvendra-marketplace).

The sister projects are public too: KvendraAI/kvendra-platform (https://github.com/KvendraAI/kvendra-platform) and KvendraAI/kvendra-cli (https://github.com/KvendraAI/kvendra-cli).

Forking. Fork the repository on GitHub and respect its license (see "Licenses"). Each skill is a single SKILL.md; technology-specific recipes live in STD entities of your own KB rather than in the skill, so most adaptations need no fork. Use this KB as a map of the design: the requirements explain what was asked for and why, the interfaces describe the exact contracts, and the manual explains how the pieces fit together. If you reuse the KB content, credit the source as the content license requires.

KB structure

The KB is made of typed entities. Each entity has a stable identifier of the form TYPE-PROJECT-COMPONENT-SUFFIX, Markdown content, tags, and typed relations to other entities. The types in this publication are:

| Type | What it is |
|------|------------|
| CMP | component sheet: scope, skills, status and repository of the component |
| IF | interfaces and contracts the skills read or produce |
| REQ | requirements: what was asked for, why, and the acceptance criteria |

The manual is not an entity: the skills book is published as its own section, chapter by chapter.

The most common relations are part_of (an entity belongs to the project), affects (an entity concerns a component), fulfills (a component fulfils a requirement), depends_on and derives_from. A good reading order is: skills book → CMP → IF → REQ.

Licenses

• SKILLS code (kvendra-skills): MIT.
• Content of this publication (the text of the KB entities, the manual and this card): MIT, the same license as the code.

The sister projects are not part of this publication: kvendra-platform is licensed under AGPL-3.0-only and kvendra-cli under Apache-2.0, as stated in their repositories.

Maintainer

Kvendra team — hello@kvendra.ai

Version

Content as of 2026-10-17. Component versions at that date:

• SKILLS: kvendra-skills 1.25.0 (28 skills) and kvendra-companion 0.2.0, published through the repository's own marketplace.

The publication version number is assigned by the server when the snapshot is published.

What is included and what is not

Included component:

• SKILLS (CMP-KVD-SKILLS) — kvendra-skills, the Claude Code plugin with the Kvendra skills and the companion band, together with its English book in Manuals.

For this component the publication includes its component sheet and its active entities of type CMP, IF and REQ. Requirements still marked as candidates and internal documentation entities are left out.

Sister projects. kvendra-platform and kvendra-cli are mentioned on this card as context. Their component sheets, entities and books are not part of this publication.

Language of the entities. The card and the manual are in English. The entities are published in their original language, and part of this KB is written in Spanish.

Not included:

• Issues, tests, releases, roadmap items and architecture decision records (ISSUE, TEST, REL, ROAD and ADR) are left out by default.
• Requirements still marked as candidates and internal documentation entities of the component.
• The sister projects kvendra-platform and kvendra-cli, the other components of the project, and its cross-cutting context.
• Drafts, proposals and archived entities.
• Restricted types (COST, CFG, ENV, RUN) and security or incident issues.
• Internal metadata, change history and authorship of the entities.