strategy-framework

Name: strategy-framework
Author: agiprolabs

235stars53forks

How to install strategy-framework?

agiprolabs/claude-trading-skills/strategy-framework

$npx -y skills add agiprolabs/claude-trading-skills --skill strategy-framework

Installs into the current project.

Summary

Standardized template for defining trading strategies with entry rules, exit rules, position sizing, risk parameters, and performance criteria

Files · 1

View on GitHub

SKILL.md

1	# Strategy Framework
2
3	A standardized system for defining, documenting, testing, and managing trading strategies. This skill provides templates and tools that enforce discipline, enable reproducibility, and make strategies testable.
4
5	## Why a Strategy Framework Matters
6
7	Trading without a written strategy framework leads to:
8	- Inconsistency: ad-hoc decisions driven by emotion rather than rules
9	- Untestability: vague ideas that cannot be backtested or evaluated
10	- Scope creep: strategies that drift without version-controlled definitions
11	- Unmanaged risk: missing stop losses, position limits, or drawdown halts
12
13	A strategy framework forces you to:
14	1. State a falsifiable hypothesis about a market inefficiency
15	2. Define precise, machine-testable entry and exit rules
16	3. Specify position sizing and risk parameters before trading
17	4. Set minimum performance criteria for continuation or retirement
18	5. Track changes through versioned strategy documents
19
20	## Strategy Definition Template
21
22	Every strategy must be documented using the standard template. The full copy-paste template is in `references/strategy_template.md`.
23
24	### Core Sections
25
26	Identity
27	```
28	Name: SOL-EMA-Cross v1.0
29	Asset class: Solana tokens (top 50 by 24h volume)
30	Timeframe: Primary 1H, confirmation 4H
31	Style: Trend following
32	```
33
34	Edge Hypothesis: State what market inefficiency you are exploiting and why it exists.
35
36	```
37	Hypothesis: Solana mid-cap tokens exhibit momentum persistence
38	on the 1H timeframe due to retail herding behavior and low
39	institutional participation. EMA crossovers capture the
40	initiation of these trends.
41	```
42
43	Entry Rules: Specific, testable conditions combined with AND/OR logic.
44
45	```python
46	def entry_signal(data: pd.DataFrame) -> bool:
47	"""All conditions must be True (AND logic)."""
48	ema_cross = data["ema_12"] > data["ema_26"] # EMA 12 crossed above 26
49	ema_rising = data["ema_26"].diff(3) > 0 # 26 EMA trending up
50	volume_ok = data["volume"] > data["vol_sma_20"] * 1.5 # Volume confirmation
51	regime_ok = data["adx"] > 20 # Trending regime
52	return ema_cross & ema_rising & volume_ok & regime_ok
53	```
54
55	Exit Rules: Every strategy needs multiple exit mechanisms.
56
57	\| Exit Type \| Method \| Parameters \|
58	\|-----------\|--------\|------------\|
59	\| Stop Loss \| ATR-based \| 2.0 × ATR(14) below entry \|
60	\| Take Profit \| Risk multiple \| 3.0 × risk (3:1 R:R) \|
61	\| Trailing Stop \| Chandelier \| 3.0 × ATR(14) from highest high \|
62	\| Time Stop \| Bar count \| Close if flat after 20 bars \|
63	\| Signal Exit \| EMA reversal \| EMA 12 crosses below EMA 26 \|
64
65	Position Sizing: Method and parameters. See the `position-sizing` skill for details.
66
67	```python
68	risk_per_trade = 0.02 # 2% of portfolio
69	stop_distance_pct = 0.05 # 5% from entry (ATR-derived)
70	position_size = (portfolio * risk_per_trade) / stop_distance_pct
71	```
72
73	Risk Parameters: Portfolio-level guardrails. See the `risk-management` skill.
74
75	```
76	Max concurrent positions: 5
77	Risk per trade: 2% of portfolio
78	Daily loss limit: 5% of portfolio
79	Max drawdown halt: 15% — stop trading, review strategy
80	Correlated exposure limit: 10% (e.g., meme tokens combined)
81	```
82
83	Filters: Conditions that prevent entry even if signals fire.
84
85	```python
86	def filters_pass(token: dict, market: dict) -> bool:
87	"""All filters must pass before entry is allowed."""
88	volume_ok = token["volume_24h"] > 500_000 # Min $500K volume
89	liquidity_ok = token["liquidity"] > 100_000 # Min $100K liquidity
90	age_ok = token["age_days"] > 7 # Not brand new
91	holders_ok = token["holder_count"] > 500 # Sufficient distribution
92	regime_ok = market["regime"] != "crisis" # No crisis regime
93	return all([volume_ok, liquidity_ok, age_ok, holders_ok, regime_ok])
94	```
95
96	Performance Criteria: When to continue, review, or retire.
97
98	```
99	Continue: Sharpe > 1.0, PF > 1.5, Win Rate > 40%, MDD < 20%
100	Review: Any metric degrades 25% from baseline
101	Retire: Rolling 30-day Sharpe < 0, or 3 consecutive losing months
102	```
103
104	## Strategy Lifecycle
105
106	### 1. Hypothesis
107
108	Identify a market inefficiency and explain why it exists and why it might persist.
109
110	Good hypothesis: "New PumpFun tokens that reach 80+ SOL in bonding curve within 10 minutes have a 65% probability of graduating to Raydium, creating a predictable price spike at graduation."
111
112	Bad hypothesis: "SOL will go up." (Not specific, not testable, no edge identified.)
113
114	### 2. Definition
115
116	Write the full strategy document using the template in `references/strategy_template.md`. Every field must be filled. If you cannot fill a field, the strategy is not ready.
117
118	### 3. Backtest
119
120	Test on historical data using `vectorbt` or equivalent. Requirements:
121	- Minimum 100 trades in the test period
122	- Use walk-forward validation (train on 70%

People who liked this also viewed

6 picks

Type

azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026275k1.3k
pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 202638k41k
stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 202611k38k
startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 20269.5k38k
tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 20265.0k75
azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 20264.5k37k

strategy-framework

235stars53forks

View on GitHub

How to install strategy-framework?

agiprolabs/claude-trading-skills/strategy-framework

$npx -y skills add agiprolabs/claude-trading-skills --skill strategy-framework

Installs into the current project.

Summary

Standardized template for defining trading strategies with entry rules, exit rules, position sizing, risk parameters, and performance criteria

Files · 1

View on GitHub

SKILL.md

1	# Strategy Framework
2
3	A standardized system for defining, documenting, testing, and managing trading strategies. This skill provides templates and tools that enforce discipline, enable reproducibility, and make strategies testable.
4
5	## Why a Strategy Framework Matters
6
7	Trading without a written strategy framework leads to:
8	- Inconsistency: ad-hoc decisions driven by emotion rather than rules
9	- Untestability: vague ideas that cannot be backtested or evaluated
10	- Scope creep: strategies that drift without version-controlled definitions
11	- Unmanaged risk: missing stop losses, position limits, or drawdown halts
12
13	A strategy framework forces you to:
14	1. State a falsifiable hypothesis about a market inefficiency
15	2. Define precise, machine-testable entry and exit rules
16	3. Specify position sizing and risk parameters before trading
17	4. Set minimum performance criteria for continuation or retirement
18	5. Track changes through versioned strategy documents
19
20	## Strategy Definition Template
21
22	Every strategy must be documented using the standard template. The full copy-paste template is in `references/strategy_template.md`.
23
24	### Core Sections
25
26	Identity
27	```
28	Name: SOL-EMA-Cross v1.0
29	Asset class: Solana tokens (top 50 by 24h volume)
30	Timeframe: Primary 1H, confirmation 4H
31	Style: Trend following
32	```
33
34	Edge Hypothesis: State what market inefficiency you are exploiting and why it exists.
35
36	```
37	Hypothesis: Solana mid-cap tokens exhibit momentum persistence
38	on the 1H timeframe due to retail herding behavior and low
39	institutional participation. EMA crossovers capture the
40	initiation of these trends.
41	```
42
43	Entry Rules: Specific, testable conditions combined with AND/OR logic.
44
45	```python
46	def entry_signal(data: pd.DataFrame) -> bool:
47	"""All conditions must be True (AND logic)."""
48	ema_cross = data["ema_12"] > data["ema_26"] # EMA 12 crossed above 26
49	ema_rising = data["ema_26"].diff(3) > 0 # 26 EMA trending up
50	volume_ok = data["volume"] > data["vol_sma_20"] * 1.5 # Volume confirmation
51	regime_ok = data["adx"] > 20 # Trending regime
52	return ema_cross & ema_rising & volume_ok & regime_ok
53	```
54
55	Exit Rules: Every strategy needs multiple exit mechanisms.
56
57	\| Exit Type \| Method \| Parameters \|
58	\|-----------\|--------\|------------\|
59	\| Stop Loss \| ATR-based \| 2.0 × ATR(14) below entry \|
60	\| Take Profit \| Risk multiple \| 3.0 × risk (3:1 R:R) \|
61	\| Trailing Stop \| Chandelier \| 3.0 × ATR(14) from highest high \|
62	\| Time Stop \| Bar count \| Close if flat after 20 bars \|
63	\| Signal Exit \| EMA reversal \| EMA 12 crosses below EMA 26 \|
64
65	Position Sizing: Method and parameters. See the `position-sizing` skill for details.
66
67	```python
68	risk_per_trade = 0.02 # 2% of portfolio
69	stop_distance_pct = 0.05 # 5% from entry (ATR-derived)
70	position_size = (portfolio * risk_per_trade) / stop_distance_pct
71	```
72
73	Risk Parameters: Portfolio-level guardrails. See the `risk-management` skill.
74
75	```
76	Max concurrent positions: 5
77	Risk per trade: 2% of portfolio
78	Daily loss limit: 5% of portfolio
79	Max drawdown halt: 15% — stop trading, review strategy
80	Correlated exposure limit: 10% (e.g., meme tokens combined)
81	```
82
83	Filters: Conditions that prevent entry even if signals fire.
84
85	```python
86	def filters_pass(token: dict, market: dict) -> bool:
87	"""All filters must pass before entry is allowed."""
88	volume_ok = token["volume_24h"] > 500_000 # Min $500K volume
89	liquidity_ok = token["liquidity"] > 100_000 # Min $100K liquidity
90	age_ok = token["age_days"] > 7 # Not brand new
91	holders_ok = token["holder_count"] > 500 # Sufficient distribution
92	regime_ok = market["regime"] != "crisis" # No crisis regime
93	return all([volume_ok, liquidity_ok, age_ok, holders_ok, regime_ok])
94	```
95
96	Performance Criteria: When to continue, review, or retire.
97
98	```
99	Continue: Sharpe > 1.0, PF > 1.5, Win Rate > 40%, MDD < 20%
100	Review: Any metric degrades 25% from baseline
101	Retire: Rolling 30-day Sharpe < 0, or 3 consecutive losing months
102	```
103
104	## Strategy Lifecycle
105
106	### 1. Hypothesis
107
108	Identify a market inefficiency and explain why it exists and why it might persist.
109
110	Good hypothesis: "New PumpFun tokens that reach 80+ SOL in bonding curve within 10 minutes have a 65% probability of graduating to Raydium, creating a predictable price spike at graduation."
111
112	Bad hypothesis: "SOL will go up." (Not specific, not testable, no edge identified.)
113
114	### 2. Definition
115
116	Write the full strategy document using the template in `references/strategy_template.md`. Every field must be filled. If you cannot fill a field, the strategy is not ready.
117
118	### 3. Backtest
119
120	Test on historical data using `vectorbt` or equivalent. Requirements:
121	- Minimum 100 trades in the test period
122	- Use walk-forward validation (train on 70%

People who liked this also viewed

6 picks

Type