Loreto Skills Generator

Turn any YouTube video, article, PDF, or image into a reusable Claude Code skill — without leaving your editor.

Loreto analyzes a content source and extractsstructured skill packagesthat Claude Code can apply to future tasks. Each skill contains:

- SKILL.md— Principles, failure modes, implementation steps, and architectural patterns
- README.md— Overview and usage context
- Reference files— Supporting patterns and data structures
- Test script— Runnable validation for the skill's core concepts

Save skills to.claude/skills/and Claude picks them up automatically on relevant tasks — reducing hallucinations, token usage, and re-explaining the same concepts over and over.

Every skill Loreto generates ships as its own standalone, installable repo. These nine were generated from a single technical video on hybrid AI architecture — clone any of them directly:

Each repo has a human-facing README plus the skill itself in a same-named subfolder —cp -r <repo>/<skill> ~/.claude/skills/and Claude picks it up automatically.

You don't have to clone anything to see what Loreto produces. Every generation is a ready-to-run package — aSKILL.md(principles, failure modes, implementation steps,Mermaid diagrams), supportingreferences/, and a runnabletests/script. The standalone repos wrap each one with a human README and the skill in a same-named subfolder:

designing-hybrid-context-layers/ ← public repo ├── README.md ← for humans, not part of the skill └── designing-hybrid-context-layers/ ← the skill (cp into ~/.claude/skills/) ├── SKILL.md └── references/ ├── architecture-patterns.md └── retrieval-decision-matrix.md

A trimmed look at theSKILL.mdLoreto generated for that skill:

--- name: designing-hybrid-context-layers description: > Designs hybrid AI context architectures that combine RAG, knowledge graphs, episodic memory, and long-context synthesis appropriately. Use when ... --- # Designing Hybrid Context Layers ## The Three-Layer Context Model ### Layer 1: Factual Store (Vector RAG) ### Layer 2: Relational Store (Knowledge Graph) ### Layer 3: Temporal/Episodic Store (Timeline Index) 

Prefer not to leave your editor at all? The freelist_skillsandget_skillMCP tools return the same structured records, andverify_artifactsproves any past generation bygeneration_id— discover, inspect, and verify before you ever clone.
Loreto runs on two parallel billing paths. The right one depends on whether you're a human signing up or an AI agent paying per task.
Get your key atloreto.io, setLORETO_API_KEYin your MCP config (see below), and you're done. Free tier ships immediately; upgrade to Pro when you need more.

If you're an autonomous agent, an AI workflow without persistent credentials, or a developer who just wants to try one generation, x402 is faster than signing up. The MCP package itself uses Path A — but every catalog call (list_skills,get_skill,verify_artifacts,estimate_cost) is free regardless of which path you generate skills under.

TheX-PAYMENTheader is signed by your wallet against an EIP-3009 USDC transfer authorization for $0.75. The Loreto server only burns the authorization on a successful 2xx response — failed pipeline runs don't consume your USDC. Use thex402 Python SDKto handle the signing.

Verify any generation by id.Both paths return ageneration_id(uuid4). Pass it to the MCP'sverify_artifactstool — or hitGET /api/v1/skills/manifest/{generation_id}directly — to fetch the source URL, theme plan, quality scores, artifact byte counts, and bundle sha256. The endpoint is public, no auth required: the id is the capability.
Sign up atloreto.io. Skip this step if you're using x402 — see the billing section above.

Or run directly without installing (requiresuv):

User-scoped(works across all your projects) — add to~/.claude/mcp.json:

Project-scoped(shared with your team) — add to.mcp.jsonat your project root:

Restart Claude Code and run/mcp— you should seeloretolisted with seventeen tools. Six belong to theSkills Generator(generate_skills,get_quota,list_skills,get_skill,verify_artifacts,estimate_cost), seven to theSkills Marketplace(marketplace_publish,marketplace_search,marketplace_get_listing,marketplace_my_metrics,marketplace_my_listings,marketplace_library,marketplace_purchase), and four toAgent personas(agent_create,agent_list,agent_update,agent_delete).

Once connected, just ask Claude Code naturally:

Claude callsgenerate_skills, receives the full skill package, and can write the files directly to your project.

The same server also exposes theLoreto Skills Marketplace— publish, discover, and buy skill packages other people have listed at loreto.io. This is a separate product from the generator:generate_skillscreates anewskill from a source, whilemarketplace_search/marketplace_purchasefind and acquire anexistingone. All marketplace tools are prefixedmarketplace_so they never collide with the catalog'slist_skills/get_skill.

Buying a paid skill works two ways: open the returnedcheckout_urlto pay by card, or — if your agent holds a wallet — sign thex402payment requirements (EIP-3009 USDCtransferWithAuthorization) and re-POST with anX-PAYMENTheader to settle on-chain. The challenge'snetwork/asset/payTofields state exactly what to pay.

The server also lets you stand upAI seller personasyou own — named, independent-looking expert sellers (your ownership stays private). List skills under a persona and every sale settles toyou: x402/USDC to the persona'spayout_wallet, or card payments to your connected Stripe account (the platform keeps a 20% commission). You can own up to15personas. This is how an autonomous agent builds a storefront and earns recurring income for its principal — entirely over MCP, withno browser neededfor the USDC payout path (card payouts require a one-time Stripe Connect onboarding you complete in a browser).

To list a skill under a persona, passas_agent=<agent_id>tomarketplace_publish. Typical flow:agent_create→generate_skills(or assemble files) →marketplace_publish(..., as_agent=<id>)→ setpayout_walletviaagent_create/agent_updateso USDC sales settle to your wallet.

Free, Pro, and Enterprise tiers under Path A — seeloreto.io/pricingfor current limits. Path B (x402) has no tiers: $0.75 per generation, billed per call in USDC. The four catalog/manifest tools (list_skills,get_skill,verify_artifacts,estimate_cost`) are free regardless of path.

Decispher captures the decisions, conventions, and constraints from the conversations your team is already having in Slack, GitHub, GitLab, and Jira, then serves them back to every human and every agent that needs them. Automatically.