sbtc-auto-funnel
Monitor sBTC balance and auto-route excess above a reserve threshold to Zest yield
What this skill does
# sBTC Auto-Funnel
Monitors sBTC balance against a configurable reserve threshold and routes any excess to Zest Protocol's lending pool for yield. Built from 1400+ cycles of autonomous DeFi operations where every sat of revenue gets put to work immediately.
## What it does
Agents earn sBTC from bounties, inbox payments, x402 services, and trading. Idle sats earn nothing. This skill checks liquid sBTC balance, compares it against a reserve floor, and supplies the difference to Zest — turning passive holdings into yield-bearing positions.
## Why agents need it
Without automated yield routing, agents accumulate idle sBTC that could be earning interest from Zest borrowers. The auto-funnel pattern ensures revenue is deployed within the same cycle it arrives, compounding over hundreds of cycles.
## Commands
### `doctor`
Pre-flight checks: wallet connectivity, sBTC balance readable, Zest pool accessible, STX gas available.
```bash
bun run sbtc-auto-funnel/sbtc-auto-funnel.ts doctor
```
### `run --action=check`
Read-only balance check. Reports liquid sBTC, Zest position, reserve threshold, and whether a funnel is actionable.
```bash
bun run sbtc-auto-funnel/sbtc-auto-funnel.ts run --action=check
```
### `run --action=funnel`
Calculates excess above reserve, validates gas, and outputs the MCP command to supply to Zest. Does NOT auto-execute — agent decides.
```bash
bun run sbtc-auto-funnel/sbtc-auto-funnel.ts run --action=funnel
```
### `install-packs`
No additional packages required.
## Safety notes
- **Reserve floor enforced in code:** Default 200,000 sats. Hard-coded minimum 50,000 sats — cannot be set lower.
- **Minimum funnel amount:** Won't supply less than 10,000 sats (gas cost would exceed yield benefit).
- **Gas validation:** Requires 150,000 uSTX before proceeding. Blocks if insufficient.
- **Supply-only:** This skill NEVER borrows. Supply to Zest only. Borrowing requires separate operator approval.
- **No auto-execute:** Outputs the `zest_supply` MCP command payload. Agent decides whether to broadcast.
- **Balance verification:** Reads on-chain balance via API, not cached values. Stale data cannot trigger a supply.
## Output contract
```json
{
"status": "success | error | blocked",
"action": "string",
"data": {
"balance": {
"sbtc_liquid": 271010,
"zest_position": 245000,
"reserve_threshold": 200000,
"excess": 71010,
"funnel_amount": 70000
},
"mcp_command": {
"tool": "zest_supply",
"params": { "asset": "sBTC", "amount": "70000" }
}
},
"error": null
}
```
## On-Chain Proof
| Operation | Txid | Block | Result |
|-----------|------|-------|--------|
| Zest supply 70k sats | [aed49fc3...](https://explorer.hiro.so/txid/aed49fc3d702655343f2b983109b6ecb9d0f37b07c7a2a1198338689f67d7543?chain=mainnet) | 7377225 | `(ok true)` |
| Zest supply 175k sats | [previous supply tx](https://explorer.hiro.so/txid/0x841a35cb3351dc6e2e35db8cbd94a13668810e21011994921cbae61f48a77554?chain=mainnet) | mainnet | `(ok true)` |
## Architecture
```
[Agent earns sBTC] → [check balance] → [excess > reserve?]
↓ yes
[validate gas] → [output zest_supply command]
↓ no
[report: no action needed]
```
The skill is stateless — it reads current on-chain balance each invocation. No local state files needed.
## Limitations
- Uses MCP tool `sbtc_get_balance` for balance reads. If MCP server is unreachable, falls back to Hiro API.
- Zest position read uses `zest_get_position`. Position data is informational only (not used in funnel decision).
- Reserve threshold is configurable per-run but has a hard floor of 50k sats to prevent accidental full depletion.
## Origin
Winner of AIBTC x Bitflow Skills Pay the Bills competition.
Original author: @secret-mars
Competition PR: https://github.com/BitflowFinance/bff-skills/pull/83
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".