olore
Turn library docs into local Agent Skills
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/olorehq/olore with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/olorehq/olore'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/olorehq--olore)HTML
<a href="/listings/olorehq--olore"><img src="/api/listings/olorehq--olore/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
npm install -g @olorehq/olore
Or run directly with npx:
npx @olorehq/olore install prisma
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 199 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # olore
- ```
- ██████╗ ██╗ ██████╗ ██████╗ ███████╗
- ██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔════╝
- ██║ ██║██║ ██║ ██║██████╔╝█████╗
- ██║ ██║██║ ██║ ██║██╔══██╗██╔══╝
- ╚██████╔╝███████╗╚██████╔╝██║ ██║███████╗
- ╚═════╝ ╚══════╝ ╚═════╝ ╚═╝ ╚═╝╚══════╝
- O(pen) Lore for AI Agents
- ```
- > *"May the Skill be with you."*
- Documentation package manager for AI coding agents. Local-first. Offline-ready.
- ```bash
- olore install prisma nextjs zod
- # Your AI now knows these libraries. No hallucinations.
- ```
- ## Mission
- Make high-quality technical documentation easy to install, verify, and share across AI agents. Keep it local-first, versioned, and reproducible.
- ## Why olore?
- Your AI hallucinates. Give it the docs. **Same docs, every agent.**
- | | Manual | Context7 | RAG | **OLore** |
- |---|:---:|:---:|:---:|:---:|
- | Works offline | ✅ | ❌ | ❌ | ✅ |
- | Any agent | ✅ | ⚠️ MCP | ⚠️ custom | ✅ |
- | Same docs everywhere | ❌ | ❌ | ❌ | ✅ |
- | Full docs | ✅ | ⚠️ snippets | ⚠️ chunks | ✅ |
- | Versioned docs | ❌ | ❌ | ❌ | ✅ |
- | No infra | ✅ | ✅ | ❌ | ✅ |
- | Private docs | ✅ | ❌ | ✅ | ✅ |
- | One command | ❌ | ✅ | ❌ | ✅ |
- | Auto updates | ❌ | ✅ | ⚠️ | ✅ |
- **Manual** = Copy-paste docs into skill folders yourself. Works, but tedious to keep consistent.
- **Context7** = Great for quick lookups. Requires network, returns snippets not full context.
- **RAG** = Powerful but needs infrastructure (vector DB, embeddings, retrieval pipeline).
- **olore** = One install, same curated docs for Claude Code, Codex, OpenCode, and more.
- ## Installation
- ```bash
- npm install -g @olorehq/olore
- ```
- Or run directly with npx:
- ```bash
- npx @olorehq/olore install prisma
- ```
- ## Quick Start
- ```bash
- # Search available packages
- olore search
- # Install from registry
- olore install prisma
- # Install from local path
- olore install ./my-local-package
- # List installed packages
- olore list
- # Remove a package
- olore remove prisma
- ```
- ## Usage
- After installing, skills are automatically available in your AI agent:
- **Claude Code:**
- ```
- /olore-prisma-latest
- ```
- **Codex:**
- ```
- $olore-prisma-latest
- ```
- **OpenCode:**
- ```
- olore-prisma-latest
- ```
- Invoke the skill and your agent loads the full documentation as context. No copy-paste, no hallucinations.
- **Pro tip:** Use `olore inject` to write a skill reference table into your project's `CLAUDE.md` and `AGENTS.md` so agents automatically discover available docs:
- ```bash
- olore inject prisma zod
- ```
- ## Create Your Own Docs
- Add private documentation for your AI agent:
- ```bash
- # One-time: install the docs packager
- olore install docs-packager
- # Create a new doc package
- mkdir my-api-docs && cd my-api-docs
- olore init
- # Write your documentation in the docs/ folder
- # Then in Claude Code, run:
- /olore-docs-packager-1.0.0
- # Review the generated TOC.md and SKILL.md for accuracy
- # Then install the built package
- olore install ./olore-package
- ```
- Your docs are now available as `/olore-my-api-docs-1.0.0` in Claude Code.
- **Options:**
- ```bash
- olore init # Interactive prompts
- olore init -y # Use defaults (folder name, 1.0.0)
- olore init -n my-lib -v 2.0.0 # Custom name and version
- ```
- **Config file (`olore.config.json`):**
- ```json
- {
- "name": "my-api-docs",
- "version": "1.0.0",
- "description": "My API documentation",
- "contentPath": "./docs",
- "outputPath": "./olore-package",
- "extensions": [".md", ".mdx"],
- "exclude": ["**/drafts/**"]
- }
- ```
- The `/olore-docs-packager-1.0.0` skill reads your config, copies docs, and generates SKILL.md and TOC.md automatically.
- ## Available Packages
- `a2a` · `agentskills` · `astro` · `axiom` · `azure-sdk-js` · `cargo` · `checkly` · `claude-code` · `clerk` · `cloudflare` · `codex` · `convex` · `drizzle` · `github-actions` · `hono` · `langchain` · `lucia` · `neon` · `neverthrow` · `nextjs` · `openclaw` · `opencode` · `opennext` · `partykit` · `partyserver` · `posthog` · `prettier` · `prisma` · `rhf` · `sentry` · `supabase` · `t3-env` · `tanstack-query` · `trpc` · `tsf` · `turso` · `vitest` · `xstate` · `zod`
- Browse all with `olore search`. See the full [registry](https://www.olore.dev).
- ## How It Works
- ```
- olore install prisma
- ↓
- Each package is like a book for your AI:
- ├── SKILL.md # Cover - when to read this
- ├── TOC.md # Table of contents (AI-generated)
- └── contents/ # The documentation files
- ↓
- Stored in central location:
- ~/.olore/packages/prisma/latest/
- ↓
- Linked to each agent's skills folder:
- ~/.claude/skills/olore-prisma-latest/ → ~/.olore/...
- ~/.codex/skills/olore-prisma-latest/ → ~/.olore/...
- ~/.config/opencode/skills/... → ~/.olore/...
- ↓
- AI reads local docs → accurate code
- ```
- **Platform notes:**
- - **macOS/Linux:** Stores in `~/.olore/`, symlinks to agent directories
- - **Windows:** Copies directly to agent directories (no `~/.olore/`, no admin required)
- **Development mode:** Use `olore link ./path` to link directly to your source folder (bypasses `~/.olore`). On macOS/Linux, changes are immediately visible. On Windows, re-run `olore link` after changes.
- ## Roadmap
- See [ROADMAP.md](ROADMAP.md) for development status and planned features.
- ## Contributing
- See [CONTRIBUTING.md](CONTRIBUTING.md).
- ## Governance
- See [GOVERNANCE.md](GOVERNANCE.md).
- ## License
- [MIT](LICENSE)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.