New · skills-hub teams · 2026
Your AI team. Already trained for the job.
Specialists in marketing, research, legal, code, ops, and analysis. Send a brief, approve each step, get the deliverables. No prompting. No setup. No per-seat math.
› Brief: ship the auth flow end-to-end ✓ Team assembled · 5 specialists · estimate $0.42
- running…Specagent 01
Drafting acceptance criteria
- queuedImplementagent 02
Writing src/auth/login.ts
- queuedTestagent 03
Generating 14 unit tests
- queuedReviewagent 04
Auditing security boundaries
- queuedShipagent 05
Running pre-deploy checks
Why teams
One agent has limits. A team doesn't.
Already trained
Every specialist arrives knowing the job — code review, marketing brief, security audit, content draft. No prompting tricks. No setup.
Always in control
The team checks in at every step. You review the work, approve to continue, or send it back. Nothing irreversible happens without your sign-off.
Real deliverables
Each session ends with concrete artifacts — a PR, a brief, a report, a redesign. The price you see is the price you paid; failed sessions are refunded.
Built on open skills
Every specialist is open and swappable. Specialists from Anthropic, Google, Microsoft, Vercel, Stripe, and 90+ sources — pick the one that fits.
Teams ready to hire
Start from a template. Tweak in plain English.
Ship a feature
Spec → implement → test → review → deploy. The full delivery loop on one task.
- Spec/mvp-spec
- Implement/feature
- Test/unit-test
- Review/code-review
- Ship/ship
Harden a codebase
OWASP Top 10, dependency CVEs, secret scans, and a HIPAA pass — chained.
- OWASP/owasp
- Pentest/pentest
- Deps/dependency-scan
- Secrets/secrets
- HIPAA/hipaa
Overhaul the design
Tear down dated patterns, rebuild with tokens, polish every primitive.
- Audit/design-system
- Tokens/css-token-sweep
- Polish/ui-craft
- A11y/accessibility-test
- Visual/visual-regression
Build your team
Swap any role. From the full catalog.
- 01 Spec/mvp-specfrom skills-hub
- 02 Implement/featurefrom skills-hub
- 03 Test/unit-testfrom skills-hub
- 04 Review/code-reviewfrom skills-hub
- 05 Ship/shipfrom skills-hub
Your team
MVP spec → Feature implementation → Unit tests → Code review → Ship
Vs the alternatives
A trained team beats a blank agent.
Most AI products start blank — you prompt, they guess. Skills-Hub teams arrive trained on the work, and you can swap any specialist for an open alternative.
| Skills-Hub teams | Devin | Cursor agents | SEO agents | DIY | |
|---|---|---|---|---|---|
| Multi-agent (named roles) | ✓ 5 roles | ✓ single agent | partial | single agent | — |
| Open registry of skills | ✓ All skills | — | — | — | — |
| Step-by-step approval | ✓ | limited | ✓ | — | — |
| Pay only for shipped runs | ✓ refund on fail | subscription | subscription | subscription | — |
| Works inside your AI tool | Claude · Cursor · Codex · Windsurf | browser-only | Cursor-only | browser-only | — |
| Typical cost per task | ~$0.40 | $500/mo seat | $20/mo seat | $50–200/mo | engineer hours |
| Time to first result | ~6 min | 10–30 min | 5–15 min | minutes | hours–days |
Pricing and capability snapshots from public product pages, May 2026. Compare against your own workflow before committing.
Real deliverables
Real deliverables. Real costs. No demo magic.
Every team produces concrete deliverables — a PR, a test suite, a security report, a redesign diff. The price you see is the price you paid; failed runs were refunded.
Migrate Stripe checkout to Payment Element
- spec.md (1.2 KB)
- src/billing/checkout.ts (+342 / -187)
- tests/billing/checkout.test.ts (24 tests)
- PR #1402 opened
OWASP audit of public API
- owasp-report.md (8.4 KB)
- risk-score.json (78 / 100)
- 12 issues flagged · 4 P0
- fix-patches/ (3 files)
Redesign marketing pages with tokens
- tokens.css (refreshed)
- 12 components migrated
- a11y-report.md (WCAG AA pass)
- visual-diff/ (24 snapshots)
Recover ranking drop on /pricing
- intent-shift-analysis.md
- competitor-deltas.md
- pricing-page.html (+612 / -89)
- schema.org JSON-LD (+1)
How it works
Four steps from idea to working team.
Pick a team
Browse pre-trained teams — marketing, research, legal, code, ops, analysis. Or build your own from the full catalog of specialists.
Send a brief
Plain English. Tell the team what you need: "Audit the marketing site for SEO drift and draft fixes." That's the whole input.
Approve each step
The team checks in at every step. You review the work, approve to continue, or send it back. You stay in control.
Get the deliverables
Real artifacts you can ship — a PR, a brief, a report, a redesign. The price is the price; failed sessions refund automatically.
Work credits
Pay per session. Refund on failure.
Top up work credits. Every session reserves an estimate up front, debits the real cost on delivery, and refunds the reserve if the session doesn't deliver. No seats. No per-user math. Your balance never goes negative.
Try it
$50.00 in work credits
See what a real team delivers.
- $50.00 in work credits
- Reserve / debit / refund per session
- Step-by-step approval
- Full transcript and deliverables
Studio
+5% bonus$105.00 in work credits
For ongoing work across teams.
- $105.00 in work credits
- Same per-session safety
- Slack + GitHub session summaries
- Priority team scheduling
Studio Pro
+10% bonus$275.00 in work credits
For teams running sessions daily.
- $275.00 in work credits
- Multi-seat sharing on one balance
- Spend and delivery analytics
- Custom team templates
Larger annual pack available — $1,000 for $1,200 credits (+20% bonus). Manage work credits →
The catalog
Meet the specialists.
Every team is built from these specialists. Each one is already trained on a single job — pick the right ones, or let a team handle the assembly for you.
01code-review
87 installsThorough code review — checks correctness, security, performance, readability, and test coverage. Gives actionable feedback ranked by severity.
Review02ui-design-system
56 installsUI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.
Buildfrom Multi-Domain Skills03markitdown
34 installsConvert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
Researchfrom Scientific Skills04self-improving-agent
30 installsCurate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Buildfrom Multi-Domain Skills05web-research-agent
29 installsA comprehensive autonomous web research agent that performs targeted searches, fetches and parses web content, summarizes findings, and generates structured reports, adhering to industry best practices for accuracy, security, and robustness.
Analysis06quickstart
25 installsZero to power user in one invoke — detects OS, installs Homebrew/apt/Node.js/Python, sets up Claude Code, authenticates skills-hub CLI, connects MCP servers, and installs recommended skills based on your project. Cross-platform (macOS, Linux, WSL). Idempotent. Use when: 'quickstart', 'setup machine', 'new machine setup', 'install everything', 'get started', 'onboard me', 'setup skills-hub', 'fresh install'.
Productivity07Skill Finder
25 installsWorkflow orchestrator. Decomposes a task into ordered steps, finds or installs the right skill for each step, runs the chain, and offers to save it as a reusable skill.
Combo08pptx
21 installsUse this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Creativefrom Anthropic09social-media-manager
19 installsWhen the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' 'community management,' 'social media plan,' 'grow followers,' 'engagement rate,' 'social media audit,' or 'which platforms should I use.' For writing individual social posts, see social-content. For analyzing social performance data, see social-media-analyzer.
Marketingfrom Multi-Domain Skills10marketing-strategy-pmm
19 installsProduct marketing skill for positioning, GTM strategy, competitive intelligence, and product launches. Use when the user asks about product positioning, go-to-market planning, competitive analysis, target audience definition, ICP definition, market research, launch plans, or sales enablement. Covers April Dunford positioning, ICP definition, competitive battlecards, launch playbooks, and international market entry. Produces deliverables including positioning statements, battlecard documents, launch plans, and go-to-market strategies.
Marketingfrom Multi-Domain Skills11senior-frontend
18 installsFrontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
Buildfrom Multi-Domain Skills12unit-test
18 installsGenerate comprehensive unit tests with edge cases, error paths, and boundary values. Auto-detects test framework (Vitest, Jest, pytest, go test, flutter_test, RSpec, cargo test, JUnit), scans for untested functions by priority, adopts existing test conventions, generates tests with proper mocks, runs them, and self-heals failures in up to 3 iterations. Measures coverage before and after. Use when you need to add unit tests, increase code coverage, test edge cases, or verify error handling paths.
Testfrom Skills Hub
Frequently asked
What's an AI team?
A team is a group of AI specialists already trained on a real job — spec, implement, test, review, ship. You send the team a brief, they plan the work, check in at each step, and deliver real artifacts. One brief in, a tested and reviewed deliverable out.
How is this different from prompting an AI assistant?
An assistant waits for instructions. A team already knows the work. You don't write prompts, you send a brief — the team handles the rest, checks in before anything irreversible, and signs off with deliverables you can ship.
How does pricing work?
Work credits, prepaid. Top up $50, $100, $250, or $1,000. Each session reserves an estimate up front, debits the real cost on delivery, and refunds the reserve if the session doesn't deliver. You only pay for work that ships.
Do bigger packs come with a discount?
Yes. Starter is 1.00× face value, Studio adds a 5% bonus, Studio Pro adds 10%, and Studio Annual adds 20% — same dollars in, more credits to spend.
What happens if a session fails?
The reserved credits are released back to your balance. You only pay for sessions that produce a delivered artifact — failures, timeouts, and rejections refund automatically.
Can I review what the team did before approving the next step?
Yes. Every session pauses at each step. You see the work, the deliverable, and the next step's plan before approving or sending back. Teams never run unattended unless you opt in.
Stop prompting. Start delegating.
Send a brief. Approve each step. Get the deliverables. Pay only for sessions that ship.