How MCP delivery works
Quiver delivers skills only through its MCP server, quiver mcp. The assistant starts it on stdio at the beginning of a session.
1. The server finds the project
Section titled “1. The server finds the project”The server serves the project of its working folder, found by walking up to .quiver.json, or of $QUIVER_PROJECT when that is set. Without a project it serves the global skills only. It logs the folder and the project to ~/.quiver/logs/mcp.log.
2. The skills reach the model
Section titled “2. The skills reach the model”MCP servers can send instructions when a session starts. Quiver's instructions are short. They tell the assistant:
- how to use the tools:
get_skill,get_skill_file,list_skillsandsearch_skills, - that new skills are saved with
create_skill, - the names of the always-on skills, for an assistant without a session-start hook,
- to call
list_skillsbefore its first reply when the conversation has no<quiver-skills>block.
The skills themselves come from a session-start hook, which quiver install sets up for Claude Code, Codex, Cursor, Antigravity and VS Code. It adds the always-on skills in full, and the ID and description of every other skill served here, project skills first, to the conversation. An assistant takes only so much text from one hook command, so Quiver splits it over as many hook commands as needed. A skill that cannot be read is named in a <quiver-notice> block. See Always-on skills.
Tool descriptions are not used for the catalog: Claude Code defers MCP tools, so the model does not see their descriptions until it looks them up.
3. The assistant loads what fits
Section titled “3. The assistant loads what fits”When a task fits a skill's description, the assistant calls get_skill with its ID. The result is the skill's instructions, a list of its extra files, and the skill's folder. The assistant reads an extra file with get_skill_file, and runs a skill's scripts itself, from that folder.
Only the skills a task needs are read into the conversation.
4. Skills as prompts
Section titled “4. Skills as prompts”Every served skill is also an MCP prompt. In Claude Code it appears as /quiver:<id>. Text after the command is passed to the skill as the task.
5. Live updates
Section titled “5. Live updates”While a session runs, the server watches the library and the assignments. Skills you add, remove or change show up in list_skills and the prompts right away; the server sends prompts/list_changed. The hook's text is built when a session starts, so the skill list and the always-on skills in it change from the next session.
Writing skills from the conversation
Section titled “Writing skills from the conversation”The assistant can also write to your library:
create_skillcreates a local skill, commits it and assigns it to this project or globally.update_skillchanges a local skill served in this project and commits the change. Source skills are read-only, and so are always-on skills: change those withquiver edit.search_skillssearches the whole library, also skills not assigned here. The assistant may suggest an unassigned skill, but asks before using it.
See MCP tools and prompts for the inputs and results of every tool.
Where it differs by assistant
Section titled “Where it differs by assistant”Not every assistant passes instructions to the model up front. Claude Desktop drops them and has no hook, so there skills are used when you ask for them. The other supported assistants run the session-start hook, so the skills reach the model without the instructions; see Always-on skills and Connect an assistant.