Help us improve
Share bugs, ideas, or general feedback.
From grepai
Use when a project needs GrepAI initialized with config file and gitignore setup
npx claudepluginhub jugrajsingh/skillgarden --plugin grepaiHow this skill is triggered — by the user, by Claude, or both
Slash command
/grepai:initializingThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Initialize grepai config for the current project with the chosen embedding provider, model, and storage backend.
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
Share bugs, ideas, or general feedback.
Initialize grepai config for the current project with the chosen embedding provider, model, and storage backend.
This skill expects context from the grepai:setting-up skill:
If invoked standalone (via /grepai:init), ask for these values via AskUserQuestion.
When invoked standalone (not from setting-up skill), ask scope: single project (recommended) or workspace (requires PostgreSQL/Qdrant). If workspace: ask directory, workspace name, create or add to workspace via grepai:workspace-managing skill, then continue with steps 1-5 for per-project config.
See references/workspace-setup.md for scope prompts, workspace creation flow, and CLAUDE.md guidance.
Glob: .grepai/config.yaml
If .grepai/ exists, warn:
Existing .grepai/config.yaml found. Reinitializing will overwrite it.
Ask via AskUserQuestion:
Existing grepai config found. What to do?
○ Overwrite — reinitialize with new settings (Recommended)
○ Cancel — keep existing config
If cancel, stop.
Use --yes flag with provider and backend flags to avoid interactive prompts:
grepai init --yes -p {PROVIDER} -b {BACKEND}
Where:
{PROVIDER} is ollama or openai{BACKEND} is gob, postgres, or qdrantThis creates .grepai/config.yaml with defaults and auto-adds .grepai/ to .gitignore.
For workspace mode: always use GOB for the local config since the workspace handles the shared store separately:
grepai init --yes -p ollama -b gob
Read the generated config:
Read: .grepai/config.yaml
If the chosen model differs from the default (nomic-embed-text for Ollama), edit the config to set the correct model and dimensions:
Edit: .grepai/config.yaml
embedder.model: {MODEL}
embedder.dimensions: {DIMS}
| Model | Dimensions |
|---|---|
| mxbai-embed-large | 1024 |
| nomic-embed-text | 768 |
| bge-m3 | 1024 |
| nomic-embed-text-v2-moe | 768 |
| text-embedding-3-small | 1536 |
| text-embedding-3-large | 3072 |
grepai init auto-adds .grepai/ to .gitignore. Verify it was added:
Read: .gitignore
If .gitignore does not exist or .grepai/ is missing from it, append:
# grepai index
.grepai/
Append workspace usage instructions to CLAUDE.md so agents use workspace search parameters with MCP tool. See references/workspace-setup.md for the CLAUDE.md template.
Print config summary with embedder, storage, gitignore status, workspace membership, and next steps. See references/workspace-setup.md for the summary template.