Initialize grepai in a project — run grepai init, configure provider/model/storage in .grepai/config.yaml, and update .gitignore.
Initializes grepai project configuration and workspace integration for AI-powered code search.
npx claudepluginhub jugrajsingh/skillgardenThis skill is limited to using the following tools:
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 via AskUserQuestion:
Project scope?
○ Single project — index this project only (Recommended)
○ Workspace — cross-project search (requires PostgreSQL or Qdrant)
If workspace:
Determine which directory to add as the project. Ask via AskUserQuestion:
Which directory should be added to the workspace?
○ Current directory ({cwd}) (Recommended)
○ Parent directory ({parent}) — if it contains multiple project subdirectories
○ Custom path
Ask for workspace name (suggest based on parent directory name)
Check if workspace exists:
grepai workspace list
If new workspace: invoke the grepai:workspace-managing skill with operation=create, then return here
If existing workspace: add the chosen directory:
grepai workspace add {NAME} {ABSOLUTE_PATH}
Note: grepai derives the project name from filepath.Base(path).
Still run steps 1-5 below for per-project config (chunking, ignore patterns, MCP anchor)
In the summary (step 6), note workspace membership and add CLAUDE.md guidance
If single project: continue with step 1.
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/
When workspace mode is active, append workspace usage instructions to the project's CLAUDE.md (or AGENTS.md) so agents know to use workspace search parameters with the MCP tool:
## grepai Workspace
This project is part of the `{WORKSPACE}` grepai workspace.
When using the `grepai_search` MCP tool, pass `workspace="{WORKSPACE}"` to search across all workspace projects.
Use `projects="{PROJECT_NAME}"` to narrow results to a specific project.
If CLAUDE.md does not exist, create it with just this section. If it exists, append the section (checking it doesn't already have a grepai workspace section).
============================================================================
GrepAI Initialized
============================================================================
Config: .grepai/config.yaml
Embedder: {PROVIDER} / {MODEL} ({DIMS} dims)
Storage: {BACKEND}
Chunking: 512 tokens, 50 overlap
.gitignore: .grepai/ excluded
Workspace: {NAME} (only if workspace mode, otherwise omit this line)
CLAUDE.md: workspace guidance added (only if workspace mode)
Next steps:
grepai index # Build initial index
grepai watch --background # Start file watcher (single project)
grepai watch --workspace {NAME} --background # Start workspace watcher
/grepai:status # Verify all components
============================================================================
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.