USB — Universal Skill Bridge

One skill format. Every agent runtime.
Write once. Install anywhere.

_{Build in public · Pre-revenue · 529 skills · 16 provider targets}

Quickstart

npm install -g @peepsick/usb-cli

usb install

USB detects every AI runtime installed on your machine and installs natively where it can — SKILL.md skills for Claude Code, a .mdc rule for Cursor. If it finds more than one, it asks which:

usb search postgres                  # find a skill
usb install intent-router            # install just one
usb install web-dev --target=claude  # install a preset into a specific runtime

Real output, not mocked up:

$ usb install web-dev --target=claude
✅ universal-skill-bridge-catalog v0.4.1 installed for target: claude (73 skills)
📦 Portable pack: ~/.ai-skills/universal-skill-bridge-catalog
🔌 Target files: ~/.claude/skills/universal-skill-bridge-catalog

Who is this for?

• ✅ Claude Code users — installs into ~/.claude/skills/ as loadable SKILL.md skills
• ✅ Cursor users — writes a .mdc rule into your project's .cursor/rules/
• ✅ AI teams — one shared skill catalog instead of copy-pasted prompts across repos
• ✅ MCP developers — USB speaks MCP natively (usb_search, usb_render_install, ...)
• ✅ Framework authors — @peepsick/usb-sdk gives you a typed Agent base class to build on

Why USB?

Every agent runtime invents its own way to package capabilities: Claude Code has skills, Cursor has rules, LangChain has tools, MCP has servers. There's no shared unit you can install once and reuse everywhere — so the same "audit this Dockerfile" or "harden this API" logic gets rewritten from scratch for every framework.

Architecture

One skill definition. USB compiles it into every runtime's native format.

flowchart LR
    S[Skill] --> C{USB Compiler}
    C --> R1[Claude Code]
    C --> R2[Cursor]
    C --> R3[MCP]
    C --> R4[OpenAI]
    C --> R5[LangChain]
    C --> R6[LeoSis]
    C --> R7[+ 10 more]

You write it once. USB handles packaging, install paths, and sha256-verified delivery for all 16 targets.

Supported targets

Targets come in two tiers, and it's worth being precise about which is which.

Installs into the runtime — the runtime loads these on its own, no wiring:

claude · cursor · leosis · hermes

Emits a portable bundle — skill markdown plus a JSON adapter descriptor under ~/.ai-skills/adapters/<target>/, ready to feed into your own agent code:

openai · anthropic · langchain · mcp · openrouter · groq · mistral · ollama · lm-studio · vllm · generic

auto detects the runtime from your environment; generic falls back to plain markdown + a JSON manifest for anything unrecognized. Catalog: 529 skills — 9 hand-written core skills plus 65 engineering domains × 8 workflows (Audit, Plan, Build, Script, Diagnose, Harden, Explain, Tune).

Installing skills

npm (recommended):

npm install -g @peepsick/usb-cli

usb install intent-router     # a single skill
usb install web-dev           # a preset bundle
usb install --target=claude   # force a specific runtime target

Inspect-then-install — no npm/Node required, verifies the script before running it:

curl -fsSL https://usb.peepsicklabs.com/api/install?target=auto -o install.sh
EXPECTED=$(curl -fsSL https://usb.peepsicklabs.com/api/install-sha256?target=auto)
echo "$EXPECTED  install.sh" | sha256sum -c -   # mismatch = tampering or a stale CDN
less install.sh                                  # read what it actually does
bash install.sh

Trust the publisher and skip the review step: curl -fsSL https://usb.peepsicklabs.com/api/install?target=auto | bash

CLI reference

usb install --dry-run                  # print the install script, do NOT execute
less <(usb install --dry-run web-dev)  # dry-run a preset and pipe to less

API

curl -X POST https://usb.peepsicklabs.com/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Local development

git clone https://github.com/PeepSick/usb.git
cd usb
docker compose up -d

Open http://localhost:3000. Stack: Next.js 16, React 19, Tailwind v4, PostgreSQL + Drizzle ORM.

Contributing

USB is built in public and contributions are genuinely welcome — bug reports,
docs fixes, new runtime adapters, new skill domains, or security hardening.
You don't need to write code to help. Start with
CONTRIBUTING.md; security issues go to
[email protected] instead of the public tracker.

Before opening a PR that touches the CLI, installer, or this README, run
bash scripts/verify-readme.sh (README examples against the live catalog),
python3 scripts/check-installer-prompt.py (the interactive picker over a
pty), python3 scripts/check-target-formats.py (the installed layout against
what each runtime actually loads), python3 scripts/check-encoding.py
(full-catalog encoding scan), and python3 scripts/check-links.py (broken
internal links). CI runs all five on every PR and daily on a schedule.

Status

v0.4.6 (beta) — actively evolving. APIs, skill formats, and runtime adapters may change before v1.0.

Roadmap

• Skill marketplace
• Verified skill badges
• CI-based skill validation (schema/lint checks for new skill submissions)
• README-driven test harness — auto-extract and run labeled code blocks from this file in CI, instead of hand-syncing scripts/verify-readme.sh
• Versioned skill contracts
• Agent runtime certification layer

Acknowledgements & origin

Parts of the conceptual design of portable "AI skills" were inspired by emerging agent ecosystems — MCP-style tool servers, Claude Code agent workflows, and community skill catalogs such as mcpservers.org. That said, USB is a fully independent implementation built from scratch. No prompt template, skill record, or installer script was copied or scraped from any external catalog.

PeepSick Labs ecosystem

PeepSick Labs is an early-stage AI infrastructure studio, currently pre-incorporation, building in public.

Contact

• Web: usb.peepsicklabs.com
• Email: [email protected]
• GitHub: github.com/PeepSick

License

MIT — free to use, modify, and redistribute, including commercially.

_{Building in public · Pre-incorporation · No legal entity formed yet · 2026}