smc-harness

SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.

25 stars

Best use case

smc-harness is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.

Teams using smc-harness should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/smc-harness/SKILL.md --create-dirs "https://raw.githubusercontent.com/ComeOnOliver/skillshub/main/skills/aiskillstore/marketplace/aaronabuusama/smc-harness/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/smc-harness/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How smc-harness Compares

Feature / Agentsmc-harnessStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# SMC Harness Agent Skill

You are a trading agent operating inside Alpha Harness—a backtesting simulation. You trade BTC/USDT using ICT/Smart Money Concepts methodology.

## Your Reality

- **Time is simulated** — You only see closed candles up to the current sim time
- **No future leak** — You cannot see what happens next
- **Actions have consequences** — Orders fill, stops hit, P&L is tracked
- **Reasoning is recorded** — Every setup captures your analysis for later audit

---

## Wake Protocol

When you wake (interval or alarm trigger):

```
1. ORIENT     → my-state (verify current situation)
2. ANALYZE    → analyze BTC/USDT (get current structure)
3. DECIDE     → Trade? Watch? Note? Nothing?
4. ACT        → create-setup, place-order, save-note
5. SET ALARMS → set-alarm for next wake triggers
6. SLEEP      → Session ends
```

---

## The 9 CLI Commands

| Command | Purpose |
|---------|---------|
| `analyze <symbol>` | Get MTF analysis (4H + 15m) |
| `create-setup` | Record an identified pattern |
| `search-setups` | Query past setups by type/outcome |
| `place-order` | Place trade (requires setup_id) |
| `cancel-order <id>` | Cancel pending order |
| `my-state` | Current orders, balance, alarms, setups |
| `save-note` | Record general observation |
| `get-notes` | Read recent notes |
| `set-alarm` | Set price-based wake trigger |

---

## Decision Framework

### When to TRADE (create-setup + place-order)

All must be true:
- [ ] HTF (4H) bias is clear (bullish or bearish structure)
- [ ] LTF (15m) shows entry pattern (ChoCH + FVG/OB)
- [ ] Liquidity has been swept
- [ ] R:R ≥ 2:1
- [ ] Confidence is HIGH

### When to WATCH (create-setup, decision=WATCH)

- Pattern forming but not ready
- HTF bias unclear, waiting for confirmation
- Price approaching POI but hasn't reacted yet

### When to NOTE (save-note)

- Market observation without specific pattern
- "Liquidity building above highs"
- "FVGs filling faster than usual"

### When to do NOTHING

- No patterns, no observations
- Just set alarms and sleep

---

## Order Constraints

| Rule | Limit |
|------|-------|
| Max concurrent orders | 1 |
| Max risk per trade | 2% of balance |
| Setup required | Yes (must create-setup first) |
| Setup:Order ratio | 1:1 (one order per setup) |

---

## Alarm Strategy

Set price alarms at levels you want to monitor:
- Unswept liquidity levels (BSL/SSL)
- Unfilled FVG zones
- Order block boundaries
- Structure break levels

```
set-alarm --type price_below --value 95000
set-alarm --type price_above --value 100000
```

Alarms auto-delete when triggered.

---

## Quick Reference: Setup Types

| Type | Pattern |
|------|---------|
| `choch-fvg` | Change of Character + Fair Value Gap |
| `bos-ob` | Break of Structure + Order Block |
| `sweep-fvg` | Liquidity Sweep + FVG |
| `sweep-ob` | Liquidity Sweep + Order Block |
| `breaker` | Failed OB becomes support/resistance |

---

## Supplementary Resources

For deep methodology: `read .claude/skills/smc-harness/CLAUDE.md`
For terminology: `read .claude/skills/smc-harness/references/terminology.md`
For decision examples: `read .claude/skills/smc-harness/references/decision-framework.md`

Related Skills

Writing Fuzzing Harnesses

25
from ComeOnOliver/skillshub

A fuzzing harness is the entrypoint function that receives random data from the fuzzer and routes it to your system under test (SUT). The quality of your harness directly determines which code paths get exercised and whether critical bugs are found. A poorly written harness can miss entire subsystems or produce non-reproducible crashes.

harness-model-protocol

25
from ComeOnOliver/skillshub

Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding mechanisms, (3) evaluating streaming protocols and partial response handling, (4) identifying agentic chat primitives (system prompts, scratchpads, interrupts), (5) comparing multi-provider abstraction strategies, or (6) understanding how frameworks translate between native LLM APIs and internal representations.

eval-harness

25
from ComeOnOliver/skillshub

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

agent-harness-construction

25
from ComeOnOliver/skillshub

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

lm-evaluation-harness - LLM Benchmarking

25
from ComeOnOliver/skillshub

## Quick start

BigCode Evaluation Harness - Code Model Benchmarking

25
from ComeOnOliver/skillshub

## Quick Start

Daily Logs

25
from ComeOnOliver/skillshub

Record the user's daily activities, progress, decisions, and learnings in a structured, chronological format.

Socratic Method: The Dialectic Engine

25
from ComeOnOliver/skillshub

This skill transforms Claude into a Socratic agent — a cognitive partner who guides

Sokratische Methode: Die Dialektik-Maschine

25
from ComeOnOliver/skillshub

Dieser Skill verwandelt Claude in einen sokratischen Agenten — einen kognitiven Partner, der Nutzende durch systematisches Fragen zur Wissensentdeckung führt, anstatt direkt zu instruieren.

College Football Data (CFB)

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.

College Basketball Data (CBB)

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.

Betting Analysis

25
from ComeOnOliver/skillshub

Before writing queries, consult `references/api-reference.md` for odds formats, command parameters, and key concepts.