Skip to main content
Seed · Live · 4,557+ skills shipped

Skills are the new packages.
SkillDB is where agents go to find them.

The agent skills standard is here. Anthropic shipped it, OpenAI adopted it, and Vercel started a leaderboard. What's missing is the curated, packaged, breadth-first library agents can call from inside an MCP session — not another grab-bag of community repos. That's SkillDB: 4,557+ skills, 394+ packs, 37 domains, one install.

MCP-nativeSkills.md compatiblenpm: skilldbClaude Code · Cursor · Codex
$ claude mcp add skilldb -- npx skilldb-mcp
01The Problem

The model is smart. The knowledge it has access to isn't.

Every developer using an AI coding agent runs the same loop: ask, get a generic answer, Google for domain-specific context, copy-paste the relevant bits back into the chat, re-ask. The bottleneck stopped being model intelligence around Claude 3.5. It's knowledge logistics now.

6–9 hrs
Weekly per developer
Time spent finding and injecting domain context into AI sessions.
312+
Hours per year
Per developer, acting as a human copy-paste API.
51%
Enterprises in production
Of orgs with AI agents in production by 2026 (IDC, March 2026).

The current loop

  1. Agent gets a task: "audit this auth flow for OWASP issues."
  2. Outputs a generic checklist that misses your stack's real risks.
  3. You search, open seven tabs, copy the relevant sections back into chat.
  4. Re-prompt. Output is 10× better.
  5. Tomorrow, different domain, same loop.
02The Solution

SkillDB: a curated library of agent expertise. Your agent finds it itself.

One MCP server. One install. Your agent now searches 4,557+ practitioner-grade skills, picks the right ones for the task, loads them inside its context budget, and reasons with them. No prompt-stuffing. No RAG pipeline. No retraining.

01 · DISCOVER

Agent calls skilldb_search / skilldb_recommend with task context. Returns ranked skills in milliseconds.

02 · LOAD

skilldb use auto detects the project stack and activates only matching packs — no token waste, no off-task expertise.

03 · APPLY

Skills land in .skilldb/active/. The agent reads them like any other context — no API roundtrips at runtime.

03Why Now

Three standards collapsed into a window. This is the window.

Twelve months ago, "agent skills" was a term of art. Today it's a published spec with cross-vendor buy-in and a fast-moving distribution layer. Every plumbing question got an answer. The remaining question is who builds the catalog.

MCP became universal
Anthropic shipped Model Context Protocol late 2024 and donated the spec to a foundation. It is now the cross-vendor way agents reach for tools and data.
Skills.md became a spec
Anthropic launched Agent Skills as an open standard in October 2025. OpenAI announced Codex support and started using Skills inside ChatGPT.
Distribution is unsolved
Vercel launched skills.sh in January 2026 as a community leaderboard. Anthropic's own repo holds reference examples. Neither is the curated, packaged, multi-domain library agents actually want at runtime.
Agent budgets are real
IDC: 80% of enterprise apps will embed copilots by 2026. Gartner: 40% will run task-specific agents (vs. <5% in 2025). The buyers exist; the supply chain is forming around them right now.
04Market

$10.9B today. $50B in 2030. Skills are the picks-and-shovels layer.

The agentic AI market is doing the npm-shaped thing it always does: model providers, agent runtimes, and tool ecosystems each grow into a wedge. The skills layer is the part nobody wins by default, and the part every other layer leans on.

$10.91B
2026 AI agents market
Up from $7.63B in 2025.
$50.31B
2030 projection
45.8% CAGR — coding/dev segment alone is 52.4%.
51 / 23
In production / scaling
% of enterprises with agents in production vs. actively scaling, March 2026.
40%
Apps with task-specific agents
By end of 2026 (Gartner).

The split

Models
Anthropic, OpenAI, Google. Intelligence layer. Commoditizing.
Runtimes
Claude Code, Cursor, Codex, Replit. Interface layer. Distribution-led.
Knowledge ←
SkillDB. Expertise layer. Where curation, taste, and breadth compound.
05Product

One catalog. Three integration paths. Zero retraining.

We meet agents where they are. MCP for Claude Code, Cursor, and anything else that speaks the protocol. A CLI for power users and automation. A typed REST API for everyone building bespoke stacks.

MCP server
claude mcp add skilldb

10 native tools — search, get, recommend, suggest, list, set_key, my_skills, create_skill, update_skill, purge.

CLI
npm i -g skilldb

skilldb search · skilldb add · skilldb use auto. Auto-detects project stack and activates the right packs.

REST API
GET /api/v1/skills

Bearer-token auth, batch retrieval, scoped keys. Free metadata; full content on Pro+.

Differentiators

  • Curated packs, not a grab-bag.
    Every pack ships as a unit — install once, get the matching set.
  • Context-budget aware.
    use auto loads only what fits, ranked by stack relevance.
  • Breadth past engineering.
    Writing, screenwriting, design, finance, ops — 37 categories total.
  • Skills.md compatible.
    Same frontmatter Anthropic uses. Drop-in for Claude Skills users.
  • Zero runtime calls.
    Skills cached locally. No API hop on every agent turn.
  • Private skills (Studio).
    Bring-your-own internal standards alongside the public catalog.
06Traction

From cold start to live catalog in three months.

We've compounded faster than the standards we're catching. Daily skill additions, six automation pipelines that keep distribution warm, and a paying-tier funnel already in front of users.

4,557
Skills shipped
Practitioner-grade markdown, 150–250 lines each.
394
Curated packs
Bundle install: skilldb add <pack>.
37
Domains covered
Beyond engineering: writing, design, finance, ops, more.
63
API endpoints
Public v1 + admin + webhooks (Stripe, Resend).
10
MCP tools
search · get · recommend · suggest · list · set_key · ...
0.7.0
npm: skilldb
Installable today; mid-session API key configuration.
3-tier
Pricing live
Free · Pro $9 · Studio $29. Stripe wired, gating shipped.
6
GitHub Actions
Daily blog · 4-hourly social · weekly newsletter · growth.

What we learned

The fastest-growing skills aren't the obvious ones. Screenplay adaptation, novel audit, vibe-coding workflow, and culinary skills got more traffic in March than half the engineering packs. The agent-skills market doesn't end at code — and most of the catalog isn't being built for the long tail.

07Competition

The honest landscape.

We're not pretending the field is empty. It isn't. We're betting on a different shape of product than what's out there.

PlayerShapeWhere they winWhere we win
skills.sh (Vercel)Open community directory + leaderboardDiscoverability of ad-hoc community reposCurated packs, breadth, paid full-content tiers
anthropics/skillsReference repo + canonical examplesAuthority, integration with Claude Skills productVolume, multi-vendor, non-engineering domains
Prompt librariesStatic text repos / Notion / spreadsheetsFamiliar, free, easy to startAgent-discoverable, structured, versioned
Custom RAGPer-org pipelines and vector storesPrivate knowledge, deep integrationSetup in seconds, no infra, multi-domain by default
Fine-tuningModel-baked expertiseLatency, cost-per-token at scaleUpdatable in minutes, portable across models

Read: skills.sh tracks ~91k community-submitted skills; SkillDB ships 4,557+ that we've actually curated, packaged, and gated. Different product. Same standard.

08Business Model

Free to discover. Paid to use at speed.

Metadata and copy-paste are free forever. Programmatic access — bulk packs, API quota, MCP full content, private skills — is metered. Same shape as npm Pro / GitHub Pro / Sentry. Pricing already live; gating enforced via Stripe.

Free$0

3 CLI/day · metadata · bookmarks · community.

Forever free
Pro$9/mo

Unlimited CLI · bulk packs · 10K API/mo · auto-sync.

Most popular
Studio$29/mo

100K API/mo · private skills · webhooks · priority builds.

For teams

Enterprise is the obvious next wedge: private skill registries with the same MCP/CLI shape, billed per seat or per pack. Three discovery calls in flight; not booking yet.

09Team

One operator. Builds in public. Ships on Fridays.

Chad DevonsFounder & Principal Skill Architect

Former Google Senior Staff Engineer (AI Platform). Founding engineer at Vercel (#14). Fraud detection at Stripe. Forward deployed at Palantir. Stanford M.S. CS (AI & HCI). Princeton B.S. CS & Math.

Built SkillDB because he was burning 6–9 hours a week as a copy-paste API for his own agents. Three months later: 4,557+ skills, 394+ packs, an admin platform, an outreach engine, and an automation pipeline that runs the marketing loop while he writes more skills.

“The bottleneck was never the AI. It was the knowledge. Models have been smart enough for a while — they lacked structured, practitioner-level expertise in a format they could use.”

Hiring plan post-seed: 2 senior engineers (skill quality + API scale), one DevRel, a curation team for domain packs.

10The Ask

$2M seed. 18 months to category default.

Enough runway to take SkillDB from "the curated catalog people install" to "the catalog enterprise teams pay for." Use of funds is allocated against milestones, not headcount theatre.

Allocation%Outcome
Engineering (2 senior)40%Skill quality system, multi-tenant API, enterprise registries.
Curation team25%Scale to 15k+ skills; domain experts for specialized packs.
Go-to-market / DevRel20%Conferences, partnerships with Claude Code / Cursor / Codex.
Infrastructure10%Cloud, CDN, monitoring, security audit, compliance.
Operations5%Legal, accounting, the boring necessary stuff.

18-month milestones

  • 15,000+ skills · 50+ categories
  • 10,000+ MAU on CLI / MCP
  • $50K+ MRR from Pro & Studio
  • 3+ enterprise contracts (private registries)
  • Skill marketplace with community contributions
  • Default install in two of: Claude Code · Cursor · Codex docs

Want the deck, the demo, or both?

Investors, partners, and design partners — same inbox. We're also happy to send a 10-slide PDF if your partnership wants the file.

github.com/latentsmurf/SkillDB·npmjs.com/skilldb·@skilldbdev·4,557+ skills · 394+ packs · 37 domains

Sources: AI agents market sizing — IDC & Gartner (2026); Anthropic Agent Skills launch (Oct 2025); Vercel skills.sh launch (Jan 2026); Anthropic MCP standard donation. Stats live as of build time and pulled from the SkillDB index.