SkillDB

by devchad-cmd

Not rated
GitHub

About

Searchable library of 5,900+ agent skills — 10 MCP tools; free tier serves metadata, a free API key unlocks full skill content. Remote Streamable HTTP at mcp.skilldb.dev.

Details

Author
devchad-cmd
Categories
Developer Tools

Setup

Install SkillDB in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/devchad-cmd/skilldb-sdk

Follow the installation instructions in the repository README, then restart your MCP client.

CLI, TypeScript SDK, andMCP ServerforSkillDB— discover, install, and manage AI agent skills.

5,900+ expert skills across 429 packs for Claude Code, Cursor, Windsurf, VS Code, and any MCP-compatible AI tool.

Open source for transparency.This is the full source for theskilldbnpm package — the CLI and MCP server that runon your machineand handleyour API key. It's published to npm viaTrusted Publishing(OIDC, with provenance), so the published artifact is verifiably built from this repo. Audit away, and PRs welcome. MIT licensed.

Connect SkillDB directly to your AI coding tool via the Model Context Protocol:

# Step 1 (optional): install globally. You can also skip this — the npx form below works without it. npm install -g skilldb # Step 2: Get your free API key at https://skilldb.dev/api-access # Step 3: Add to Claude Code (with API key for full content) claude mcp add skilldb -- npx -p skilldb skilldb-mcp --api-key sk_live_YOUR_KEY

Note:skilldb-mcpis a binary inside theskilldbpackage, not its own npm package — always invoke it asnpx -p skilldb skilldb-mcp(notnpx skilldb-mcp).

⚠️ Without an API key, you can search and browse skills (metadata only).With a free API key, you get full skill content — the actual markdown instructions your agent uses. Get your key in 30 seconds atskilldb.dev/api-access.

{ "mcpServers": { "skilldb": { "command": "npx", "args": ["-p", "skilldb", "skilldb-mcp"] } } }
{ "mcpServers": { "skilldb": { "command": "npx", "args": ["-p", "skilldb", "skilldb-mcp", "--api-key", "sk_live_xxx"] } } }
code --add-mcp '{"name":"skilldb","command":"npx","args":["-p","skilldb","skilldb-mcp"]}'

Or add the same server block to.vscode/mcp.json(workspace) / usermcp.jsonunder"servers".

Once connected, your AI assistant can search and load skills natively. Just ask:

- "Search SkillDB for React performance patterns"
- "Load the code review skill"
- "What skills should I use for this project?"
- "Save this as a private skill"(Studio plan — see below)

10 tools exposed:skilldb_search,skilldb_get,skilldb_list,skilldb_suggest,skilldb_recommend,skilldb_purge,skilldb_set_key(set/swap your API key mid-session, no restart), and the private-skill toolsskilldb_my_skills,skilldb_create_skill,skilldb_update_skill(Studio plan + write-scoped key).

# Search for skills (with inline preview) npx skilldb search "code review" # Install a skill pack npx skilldb add software-skills # Activate a smart profile (only loads what you need) npx skilldb use frontend # Or auto-detect from your project npx skilldb use auto

The Memory Problem (And How We Solve It)

Loading 500 skills into your agent's context is worse than loading the right 5. SkillDB uses a3-layer architectureto manage this:

.skilldb/ ├── skills/ ← Full cache (everything downloaded) ├── active/ ← Active profile (what your agent sees — 5-15 focused skills) ├── slim/ ← Compressed cheat sheets (10x smaller) ├── config.json ← Profile + budget settings └── manifest.json ← What's installed

Your CLAUDE.md or .cursorrules points at.skilldb/active/, not the full cache. The agent gets focused, relevant skills — not noise.

Detect your IDE (Claude Code, Cursor, Codex CLI, OpenClaw), create.skilldb/, and add integration config.

Search skills by keyword. Shows inline slim preview so you know what you're getting before downloading.

skilldb search "debugging" skilldb search "api design" --category "Technology & Engineering" skilldb search "testing" --limit 10

Download a skill pack to local cache. Idempotent — skips already-cached skills.

skilldb add software-skills skilldb add autonomous-agent-skills skilldb add vibe-coding-security-skills

Show metadata, slim summary, and full preview for a skill.

skilldb info software-skills/code-review

List available categories, packs, and skills.

skilldb list skilldb list --category "Autonomous Agents" skilldb list --pack software-skills

Prompts for your API key and saves it to~/.skilldbrc(user-wide) so every project picks it up via the resolution chain inAuthentication. The recommended alternative to settingSKILLDB_API_KEYby hand.

Activate a focused profile — only loads relevant skills into.skilldb/active/.

skilldb use frontend # React, testing, web-polish, accessibility skilldb use backend # API design, databases, security, performance skilldb use devops # Kubernetes, Docker, CI/CD, monitoring skilldb use security # Trust audit, input validation, credentials skilldb use data # SQL, pipelines, analytics, visualization skilldb use fullstack # Frontend + backend combined skilldb use mobile # Mobile / React Native / app development skilldb use ai-agent # Autonomous agent meta-skills skilldb use auto # Auto-detect from your project files skilldb use --list # Show available profiles skilldb use --current # Show active profile skilldb use none # Deactivate (clear active/)

automode scans yourpackage.json, file extensions, and imports to recommend the right profile.

Set a maximum context budget so your agent doesn't get overloaded.

skilldb budget # Show current usage skilldb budget set 5000 # Max 5,000 lines skilldb budget set 50k # Max 50,000 tokens skilldb budget optimize # Re-rank and trim active skills to fit

Generate compressed cheat-sheet versions of skills (~30 lines instead of 300).

skilldb slim # Slim all active skills skilldb slim software-skills # Slim a specific pack skilldb slim --ratio 0.3 # Keep 30% of content

Check for newer versions of installed skills and update them.

skilldb update # Update everything skilldb update software-skills # Update one pack
skilldb remove software-skills/code-review # Remove single skill skilldb remove software-skills # Remove entire pack skilldb remove --unused # Remove skills not in active profile

Health check and audit of your skill setup.

Shows: outdated skills, unused skills, missing dependencies, budget status, coverage gaps.

Shows: installed count, total lines, tokens, active profile, categories covered.

Compare your local (possibly customized) version with the latest remote.

skilldb diff software-skills/code-review skilldb diff # Diff all installed

Remove cached skills to free disk space.

skilldb purge --inactive # Remove skills not in the active profile skilldb purge --all # Remove ALL cached skills (including active) skilldb purge --slim # Also drop slim summaries skilldb purge --dry-run # Preview what would be removed, delete nothing

Create skills that onlyyou(and people you share them with) can read. They surface in your own search results when you're authenticated. Creating/editing requires theStudio planand an API key withwritescope — mint one atskilldb.dev/account#api-keys.

Create (or update) a private skill from a local Markdown file. The skill name defaults to the filename; the title resolves as--titleflag → first Markdown# H1→ filename.

skilldb push ./my-react-patterns.md # create (pack defaults to "personal") skilldb push ./my-react-patterns.md -p team --tags react,perf skilldb push ./my-react-patterns.md --update # update the skill with the same name/pack

Options:-p, --pack,-n, --name,-t, --title,-d, --description,--tags <comma,list>,-u, --update.

List your private skills (ones you own plus skills shared with you).

You can also do all of this from your agent via the MCP toolsskilldb_create_skill/skilldb_update_skill/skilldb_my_skills.

Export your setup for sharing or IDE integration.

skilldb export claude # CLAUDE.md snippet with skill references skilldb export cursor # .cursorrules block skilldb export profile # Shareable .skilldb-profile.json skilldb export inject <id> # Print skill to stdout (for piping)

Scan your project and get personalized skill recommendations.

skilldb recommend # Analyze project and suggest skilldb recommend --install # Auto-install recommendations
import { createClient } from 'skilldb'; const db = createClient(); // auto-loads key from env/config // Search with slim previews const results = await db.search('code review'); for (const skill of results.skills) { console.log(skill.title); console.log(skill.slim); // Quick summary } // Get full skill content const skill = await db.get('software-skills/code-review.md'); console.log(skill.content); // List with filters const listing = await db.list({ category: 'Autonomous Agents', limit: 10 });

The SDK and CLI resolve your API key in order:
- SKILLDB_API_KEYenvironment variable (CI-friendly)
- .skilldbrcin project root (project-specific)
- ~/.skilldbrcin home directory (user-wide)

- No key— browse and search (metadata only).
- Pro or Studio key— full skill content (the actual markdown instructions).
- Studio key withwritescope— private skills (skilldb push/my-skills, and thecreate/updateMCP tools). Read-only keys are rejected with a write-scope error. Create a write-scoped key at
skilldb.dev/account#api-keys.

Built-in profiles map to curated skill sets:

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Create crafted UI components inspired by the best 21st.dev design engineers.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

ALAPI MCP Tools,Call hundreds of API interfaces via MCP

AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform

MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.

APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.