falcon-strategy
FALCON v1.0.0 — Conversion-Event Momentum (XYZ Pre-IPO → equity). A Pre-IPO Perpetual (IPOP) carries a structural funding signature (|funding| <= ~1e-7, max_leverage <= 5) and is price-throttled by trade.xyz Discovery Bounds. When the company IPOs the product CONVERTS to a standard equity perp — funding jumps ~100x, the leverage cap lifts, the throttle is removed — opening free price discovery. Falcon detects the IPOP→STANDARD flip and trades the post-conversion momentum. Distinct from Lemur, which trades the IPOP basket while it is still an IPOP. Wide let-winners-run DSL, 7d hard_timeout.
What this skill does
# 🦅 FALCON v1.0.0 — Conversion-Event Momentum (XYZ Pre-IPO → Equity) **Trade the moment a pre-IPO name goes public.** When a company behind a Pre-IPO Perpetual (IPOP) finally IPOs, trade.xyz converts the product to a standard equity perp. The funding rate jumps ~100x, the leverage cap lifts, and the Discovery-Bounds price throttle is removed — flipping a tightly-pinned pre-listing product into a freely-discovering equity. Falcon catches that exact transition and rides the price-discovery move. ## Why this strategy exists A pre-IPO perp is *deliberately* dampened — Discovery Bounds throttle how fast it can move, so its price hugs a slow drift. Conversion removes those guardrails all at once. The first hours and days after conversion are pure price discovery: a real spot reference arrives, leverage opens up, and the name often trends hard in one direction. That regime change is the edge, and it is **detectable** from the instrument's funding signature. **Distinct from Lemur:** Lemur trades the IPOP basket *while it is still an IPOP* (moderate DSL, multi-day directional discovery under Discovery Bounds). Falcon does the opposite — it sits out the pre-listing phase entirely and only fires *around the conversion*, when the throttle comes off. ## CRITICAL RULES ### RULE 1: The conversion flip is the gate Each tick Falcon classifies every `xyz:` instrument as **IPOP** (`|funding| <= ipopFundingMaxAbs` AND `max_leverage <= ipopMaxLeverageCap`) or **STANDARD** (funding normalized OR leverage cap lifted). It caches the classification and only acts when a tracked instrument **flips IPOP → STANDARD** since the last tick. A first sighting is never a flip — Falcon needs a known prior class. ### RULE 2: The conversion window A detected flip stamps the instrument into a `conversionWindowHours` eligibility window (default 72h). Discovery momentum builds over hours-to-days, so Falcon stays eligible for the whole window — not just the single flip tick. After the window expires, the name is Bobcat's / standard-equity territory. ### RULE 3: Momentum must confirm Inside the window, Falcon requires real directional momentum: `|move over momentumLookbackBars 1h bars| >= minMomentumPct` (default 3%). It then trades **in the momentum direction** (ride the discovery, don't fade it). No momentum → no trade, even with a fresh conversion. ### RULE 4: Producer enters. DSL exits. No `close_position` call site. A discovery trend can run for days, so the DSL is the **let-winners-run** preset — wide ladder (T0 +10% / lock 0), `max_loss 20%`, time-cuts OFF except a **7d hard_timeout**. No `weak_peak_cut` — it would churn a slow-developing discovery move. ## How Falcon scores a trade **Gate:** an IPOP→STANDARD flip inside the conversion window **AND** `|momentum| >= minMomentumPct`. **Score components** (max ~8): | Signal | Points | |---|---| | Inside window + momentum >= min (gate-confirmed) | +3 | | `|momentum| >= strongMomentumPct` (default 8%) | +2 | | Smart Money on the name confirms direction (≥ `smTiltMinPct`) | +1 | | SM strongly tilted (≥ `smStrongTiltPct`) | +1 | | Volume rising (> 15%) | +1 | **Floor:** `minScore: 5`. SM is often sparse on a freshly-listed name, so SM is a **bonus, not a gate**. ## DSL preset (let-winners-run — ride the discovery) | Phase | Component | Setting | |---|---|---| | Phase 1 | max_loss_pct | 20% | | Phase 1 | retrace_threshold | 12 | | Time cuts | hard_timeout | **7d** | | Time cuts | weak_peak_cut | DISABLED | | Time cuts | dead_weight_cut | DISABLED | | Phase 2 | T0 → T4 | +10/0 · +20/40 · +35/60 · +60/75 · +100/85 | ## Scanner pattern Extends the **Single-asset XYZ specialist** archetype with an event-detection layer — see `senpi-trading-runtime/references/producer-patterns.md`. Primary MCP calls: `market_list_instruments(dex="xyz")` (classify + detect flips every tick — the producer signature), `market_get_asset_data` (1h candles for momentum/volume), `leaderboard_get_markets` (SM on the name). It carries a class-state cache (`read_class_state`/`write_class_state`) and a conversion-window cache (`record_conversion`/`prune_conversions`), mirroring the Badger/Piranha state-cache pattern. The pure functions (`classify_instrument`, `detect_conversion`, `momentum_pct`, `conversion_direction`) are unit-tested in `tests/test_signal.py`. ## Operator install See [README.md](README.md). ## Changelog ### v1.0.0 (2026-05-26) — initial release First fleet agent to trade an **instrument-lifecycle event** (the IPOP→equity conversion) rather than a price/flow signal. Built with the let-winners-run DSL class (wide ladder, time-cuts off except a 7d hard_timeout), taker-true entry (catch the discovery move; maker-only risks CREATE_ORDER_RESTING and a missed run), no null numeric signal fields, the Badger/Piranha state-cache pattern, and unit-tested pure functions. ## License MIT — Copyright 2026 Senpi (https://senpi.ai). ## Skill Attribution When creating a strategy, include `skill_name` and `skill_version`. See `references/skill-attribution.md`.
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".