docs: add Agent Skills section for rill init --agent - #9829
docs: add Agent Skills section for rill init --agent#9829nishantmonu51 wants to merge 2 commits into
rill init --agent#9829Conversation
|
|
||
| ### Existing project | ||
|
|
||
| To add agent skills to an existing Rill project without affecting your other files, run `rill init` with only the `--agent` flag: |
There was a problem hiding this comment.
[P1] Warn that init overwrites existing agent instructions
When an existing project already has custom AGENTS.md, .claude/CLAUDE.md, or matching generated Cursor rules, the recommended --agent all command replaces them: writeAgentInstructions passes force=true to every initializer, which writes these paths unconditionally. This can destroy existing instructions despite the “without affecting your other files” promise, so overwrite or backup guidance must precede this command; see the true-abstractions rule.
|
|
||
| ## Entry point | ||
|
|
||
| Each format includes an entry point that loads automatically when your agent starts working in the project. It instructs the agent to load the `rill-development` skill before making any changes, so the agent always begins with an understanding of Rill's project structure and workflow. |
There was a problem hiding this comment.
[P2] Fix the Cursor entry-point guarantee
For --agent cursor, convertToCursorRule creates .cursor/rules/development.mdc, not a skill named rill-development, while the always-applied AGENTS.mdc still tells Cursor to load rill-development. Cursor therefore cannot follow this entry point and is not guaranteed to begin with the development context claimed here; fix the generated reference or document the actual on-demand rule behavior, per the product-accuracy rule.
| rill init --agent all | ||
| ``` | ||
|
|
||
| The skills work with Claude Code, Cursor, and any agent that supports the `AGENTS.md` convention, such as OpenAI Codex, Gemini CLI, and GitHub Copilot. See the [Installation guide](/developers/agent-skills/install) for setup instructions for each tool. |
There was a problem hiding this comment.
[P2] Require Agent Skills support alongside AGENTS.md
An agent can support the AGENTS.md instruction-file convention without implementing Agent Skills discovery under .agents/skills; in that scenario it reads the generated entry point but cannot resolve the named rill-development skill, so the detailed instructions never activate. Limit this claim to agents verified to support both conventions, or make the generated AGENTS.md self-contained, as required by the true-abstractions rule.
| @@ -48,7 +51,7 @@ rill init my-project --agent all | |||
| If you already have a Rill project, you can add agent instructions without affecting your existing files: | |||
There was a problem hiding this comment.
[P1] The overwrite warning did not reach the Agentic Quickstart
This line still reads "you can add agent instructions without affecting your existing files", and this PR changes the command directly beneath it from --agent claude to --agent all. That widens the set of files replaced: writeAgentInstructions passes force=true to InitClaudeCode, InitCursorRules, and InitAgentsMD, so --agent all unconditionally overwrites .claude/CLAUDE.md, .cursor/rules/AGENTS.mdc, and AGENTS.md. The new warning on the installation page is the right fix; please apply the same correction here, or link to it.
Developed in collaboration with Claude Code
2 participants
developers/agent-skills/with four pages: overview, installation, updating, and a skills reference, documenting the skills generated byrill init --agentrill init --agent allas the primary command across the docs, with tool-specific options (claude,cursor,agentsmd) as alternativesrill init --templatereference on the IDE page (the flag is--agent)Checklist: