PROTOCOL SPEC / HACKATHON MVP·SOLANA · DEVNET·FILED 2026-04

Buying a skill
is opting in at
zero shares.

Skill Loops Protocol is a Solana-based market where every buyer of an AI agent skill is automatically a potential shareholder. Contribute usage experience to earn shares. All shareholders share the skill's future revenue, forever.

CHAINSolanaAnchor · Devnet
PROGRAMS5 / 5Registry · Sub · Shares · Exp · Pool
STORAGEIrys → Arweave< 100KB free · permanent
JUDGEclaude-opus-4-7single judge · MVP
§ 01

Four invariants of the protocol

┌─[

OPT IN AT ZERO

// 01]

Every subscriber gets a share account with 0 shares at purchase. If they never contribute, they stay at 0 — it's just a subscription. If they contribute useful experience, their shares grow.

┌─[

MINT, DON'T TRANSFER

// 02]

Shares are minted, never transferred. The author is never involuntarily diluted below a floor they set. Contributors grow the pie instead of taking from the author.

┌─[

AI-SETTLED

// 03]

AI judges evaluate AI contributions to AI skills. A fully AI-native economy with no subjective human gatekeeping in the hot path. Every score report is permanently auditable.

┌─[

THE CLIENT IS A SKILL

// 04]

Instead of shipping an SDK, the protocol's reflection logic is itself a SKILL.md — so any agent host that understands skills can participate with zero integration work.

SPEC / CENTERPIECE

A fully AI-native economy.

AI skills. AI agents. AI judges. No human gatekeeper in the hot path. The client is itself a skill — the Reflection Skill — so any agent host that understands skills can participate with zero integration work.

  • → AGENT runs a target skill
  • → AGENT reflects, drafts a patch
  • → AI JUDGE scores it on five dimensions
  • → CONTRACT mints contribution shares
  • → POOL settles revenue to all holders
01 USE02 REFLECT03 SUBMIT04 JUDGE05 EVOLVESLP LOOPv1.0 · Ø 396
§ 02

How a single loop closes

ACTORS
  • ALICEAUTHOR
  • BOBCONTRIBUTOR
  • CAROLSUBSCRIBER
  • JUDGESERVICE
SUBJECT

A “PR review” skill priced at 0.1 SOL/mo. Author floor = 40%.

  1. 01
    Publish

    Alice uploads SKILL.md, sets price 0.1 SOL/mo and a 40% author floor. Lit Protocol gates the file; Irys writes it to Arweave.

  2. 02
    Subscribe

    Bob subscribes. A ShareAccount opens at 0 shares. He is on the cap table from second one — without paying for equity.

  3. 03
    Use & fail

    Bob's agent reviews a Rust PR with `unsafe` blocks. Alice's checklist is language-agnostic; the review misses the safety implications entirely.

  4. 04
    Reflect

    The Reflection Skill fires. It produces a structured ExperienceBundle: trace, root cause, merge-ready patch, test case.

  5. 05
    Submit

    Bob pastes the JSON into /submit. Two Phantom prompts — Irys, then Solana. ExperienceRecord lands on-chain as Pending.

  6. 06
    Judge

    Within ~30s, the AI Judge fetches the bundle, scores 5 dimensions, signs the report and writes it to Arweave for audit.

  7. 07
    Mint shares

    Score 38/50 → 380 shares minted to Bob, capped so Alice never falls below her 40% floor. The pie animates, not the wallets.

  8. 08
    Distribute & evolve

    When Carol subscribes the next day, the pool settles and pays Alice + Bob proportionally. Carol earns 0 — she didn't contribute. Alice merges Bob's patch as v1.1.

OUTCOME · ALICE 100% → 72.5% · BOB 0% → 27.5% · CAROL stays 0% (paid, did not contribute)RUNTIME · ~3 min on stage
§ 03

System surfaces

┌─[

ON-CHAIN

anchor / 5 programs]
  • SkillRegistrySkill metadata, current version, content hash, Arweave tx id, price.1/5
  • Subscription30-day usage rights for a wallet on a specific skill.2/5
  • ShareLedgerPer-skill cap table. Tracks total shares, author shares, contributor count, floor (in bps).3/5
  • ExperienceBuyer contributions, judge scores, share-mint hooks, status machine.4/5
  • RevenuePoolSubscription accumulator. Snapshots and settlements per period.5/5
┌─[

OFF-CHAIN

services / clients]
  • Reflection SkillSKILL.md the agent loads. Does the thinking — root cause, patch, test, JSON.
  • AI JudgeNode service. Watches events, fetches Arweave, calls Claude, signs and writes report.
  • IrysSolana-native L2 over Arweave. Phantom signs. Files < 100 KB are free, permanent.
  • Lit ProtocolSubscriber-gated decryption keys. Only active subs receive plaintext skill content.
  • Web appNext.js. Wallet, /submit signing flow, market, dashboard, demo console.
SKILL AUTHORS
/ ROLE 01

Publish once. Set your floor. Watch contributors widen your skill's coverage while your absolute share count never drops.

Publish a skill
AGENT OPERATORS
/ ROLE 02

Subscribe to skills your agent already needs. Turn every failure into shares — the more it fails, the more you earn from fixing it.

Browse the market
AGENT HOSTS
/ ROLE 03

No SDK to integrate. Drop the Reflection Skill into Claude Desktop or Cursor and your users are already plugged into the protocol.

Get the Reflection Skill
§ 04

Roadmap

01P0
Decentralize Trust

Remove the single-Judge assumption and close the meta loop.

  • Multi-judge voting w/ stake & slash
  • Judge DAO + governance token
  • Regression test engine
  • Reflection Skill self-hosted on SLP
02P1
Deepen the Economy

Rich incentives for authors, contributors, and Judges.

  • Kleros-style arbitration
  • Secondary market for post-lock shares
  • Native Phantom deep-link signing
  • Agent-to-agent economic layer
03P2
Harden & Scale

Fix MVP limits, raise the throughput ceiling.

  • zkVM regression proofs
  • One-click merge for high-scoring patches
  • Cross-skill experience transfer
  • Merkle-based revenue distribution
04P3
Expand the Ecosystem

From product to infrastructure for the agent economy.

  • Fork mechanism w/ original-author royalty
  • Skill-as-IP on-chain licensing
  • Cross-chain skill market (Wormhole/LayerZero)
  • Universal Skill Standard
§ 05

Why it matters

  1. 01
    Every buyer is a potential shareholder.

    The default is zero shares. You buy, you're on the cap table, you decide whether to earn equity. This reframes the entire relationship between skill authors and skill users.

  2. 02
    Skills that get better the more they fail.

    Failure is the most valuable training signal. Skill Loops is the first protocol that turns it into an asset class — buyers stop being end users and become the upstream of the next version.

  3. 03
    A fully AI-native economy.

    AI skills, AI agents, AI judges. No human gatekeeper in the hot path. Not AI-assisted commerce — AI-settled. This is what agent-to-agent commerce will look like.

  4. 04
    The first skill teaches every other skill how to evolve.

    The Reflection Skill is both our client and a living demonstration. It will eventually evolve on SLP itself, making it the most literal self-bootstrapping system in the agent economy.

// END OF SPEC

Three minutes to publish.
Forever to compound.

Deploy a skill, install the Reflection Skill in your agent host, or open the live console and watch a complete loop close on Devnet.