Use when you have a written implementation plan to execute in a separate session with review checkpoints
npx skills add clawd-aftermath/senpi-skills-af --skill "jackal-strategy"
Install specific skill from multi-skill repository
# Description
>-
# SKILL.md
name: jackal-strategy
description: >-
JACKAL β First Jump pyramider. FOX v1.6's exact five-layer entry gauntlet combined with
RHINO's pyramiding mechanic. Enter at 30% on a qualifying First Jump, add 40% at +10% ROE
and final 30% at +20% ROE β but only after re-validating 4h trend, SM alignment, and volume.
Failed scouts cost $15 instead of FOX's $50. Full pyramids capture the same upside.
DSL High Water Mode (mandatory).
license: MIT
metadata:
author: jason-goldberg
version: "2.0"
platform: senpi
exchange: aftermath
base_skill: fox
type: trading-strategy
JACKAL β First Jump Pyramider
FOX's proven scanner + RHINO's pyramiding. Enter small, add as it confirms.
Requires: FOX v1.6 must be installed first. JACKAL applies config.json overrides on top.
How to Deploy
- Install FOX v1.6 from the senpi-skills repo
- Apply JACKAL's
config.jsonoverrides to the FOX config - Agent uses FOX's scanner with JACKAL's pyramid logic, entry filters, and DSL tiers
MANDATORY: DSL High Water Mode
JACKAL MUST use DSL High Water Mode. This is not optional.
Spec: https://github.com/Senpi-ai/senpi-skills/blob/main/dsl-dynamic-stop-loss/dsl-high-water-spec%201.0.md
When creating DSL state files, you MUST include:
{
"lockMode": "pct_of_high_water",
"phase2TriggerRoe": 7,
"tiers": [
{"triggerPct": 7, "lockPct": 40, "breachesRequired": 3},
{"triggerPct": 12, "lockPct": 55, "breachesRequired": 2},
{"triggerPct": 15, "lockPct": 75, "breachesRequired": 1},
{"triggerPct": 20, "lockPct": 85, "breachesRequired": 1}
]
}
FALLBACK: Use tiersLegacyFallback from config.json until engine per-tick fix ships.
Entry: FOX v1.6 Five-Layer Gauntlet (Identical)
No changes from FOX v1.6:
- First Jump β 10+ ranks from outside Top 25. Top-10 blocked.
- Score β₯ 9, reasons β₯ 4, velocity > 0.10
- Asset 4h/1h trend alignment β hard block
- Leverage β₯ 7x
- Time-of-day modifier (+1 during 04:00-14:00 UTC, -2 during 18:00-02:00 UTC)
Pyramid: Three Stages
Stage 1 β SCOUT (30% of max position): Signal passes five-layer gauntlet. Enter with 30% of normal FOX margin.
Stage 2 β CONFIRM (add 40% at +10% ROE): Before adding, re-validate:
- Asset's 4h trend still intact (same direction)
- SM has not flipped against the position
- Volume still present (ratio β₯ 0.5x average)
If any check fails, do NOT add. The scout rides with DSL protection.
Stage 3 β CONVICTION (add final 30% at +20% ROE): Same re-validation as Stage 2.
If the scout fails: DSL stops it at the conviction-scaled floor. Loss is on 30% of max size β roughly $15 on a $1,000 account instead of FOX's $50.
Notification Policy
ONLY alert:
- Stage 1 SCOUT opened (asset, direction, margin)
- Stage 2 CONFIRM added (asset, new total margin)
- Stage 3 CONVICTION added (asset, full position)
- Position CLOSED (total P&L across all stages)
- Risk triggered, critical error
NEVER alert: Scanner found nothing, DSL routine, pyramid evaluation, any reasoning.
All crons isolated. NO_REPLY for idle cycles.
License
MIT β Built by Senpi (https://senpi.ai).
Source: https://github.com/Senpi-ai/senpi-skills
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.