This commit is contained in:
2026-08-15 15:42:41 -04:00
commit 379add3932
26 changed files with 3286 additions and 0 deletions

View File

@@ -0,0 +1,17 @@
# Scan Watchlist ICM Workspace
This workspace orchestrates a multi-stage watchlist confluence scan for trading ideas.
The agent follows the numbered stages to filter tickers, analyze confluence, construct trade plans, and produce a summary card.
Folder structure:
- CLAUDE.md (Layer 0): workspace identity
- CONTEXT.md (Layer 1): workspace-level routing
- stages/: numbered stage folders
- 00_clarify/: ask key questions
- 01_broad_filter/: broad filter across tickers
- 02_confluence_analysis/: confluence analysis on shortlist
- 03_trade_plan/: trade plan construction
- 04_summary_card/: summary card creation
- _config/: Layer 3 reference material (stable across runs)
- shared/: Layer 3 shared references
- Each stage's output/ holds Layer 4 working artifacts for handoff to next stage.

View File

@@ -0,0 +1,16 @@
# Workspace Context: Watchlist Confluence Scan
## Routing
Given the goal to scan 54 tickers for trade setups with confluence, the workflow proceeds through stages:
1. **00_clarify** - Ask clarifying questions about long/short bias, time horizon, asset class focus.
2. **01_broad_filter** - Perform broad filter across all tickers to narrow candidates.
3. **02_confluence_analysis** - Analyze confluence factors for each candidate.
4. **03_trade_plan** - Construct detailed trade plans for top setups.
5. **04_summary_card** - Produce a structured summary card of setups and sitting-on-hands list.
## Shared Resources
- _config/: Contains references such as ticker list, default parameters.
- shared/: May contain common tools or scripts (if any).
The agent should read the stage's CONTEXT.md for detailed inputs, process, and outputs.

View File

@@ -0,0 +1,14 @@
# Trade Plan Template
**Symbol:**
**Side:** (Long/Short)
**Entry Zone:**
**Stop:**
**Targets:** T1: , T2: , T3:
**Time Horizon:**
**Rationale:**
**Invalidation Condition:**
**Options Structure (if applicable):**
- Credit spread strikes:
- Bid-ask spread:
- Time decay:

View File

@@ -0,0 +1,55 @@
AAPL
UPS
UBER
TSM
TSLS
TSLA
TGT
TAN
SQQQ
SPY
SPX
SOXL
SEDG
SBUX
RUN
ROKU
RIVN
RBLX
QQQ
PYPL
PLTR
PINS
PANW
NVDA
NKE
NFLX
MU
MSFT
META
KRE
INTC
HOOD
HD
GOOGL
GOOG
FSLR
FDX
ETSY
ENPH
DIS
DE
DDOG
CRWD
CRM
COST
COIN
CAT
BITO
BABA
BA
ARKK
AMZN
AMD
AFRM
ADBE
1 AAPL
2 UPS
3 UBER
4 TSM
5 TSLS
6 TSLA
7 TGT
8 TAN
9 SQQQ
10 SPY
11 SPX
12 SOXL
13 SEDG
14 SBUX
15 RUN
16 ROKU
17 RIVN
18 RBLX
19 QQQ
20 PYPL
21 PLTR
22 PINS
23 PANW
24 NVDA
25 NKE
26 NFLX
27 MU
28 MSFT
29 META
30 KRE
31 INTC
32 HOOD
33 HD
34 GOOGL
35 GOOG
36 FSLR
37 FDX
38 ETSY
39 ENPH
40 DIS
41 DE
42 DDOG
43 CRWD
44 CRM
45 COST
46 COIN
47 CAT
48 BITO
49 BABA
50 BA
51 ARKK
52 AMZN
53 AMD
54 AFRM
55 ADBE

View File

@@ -0,0 +1,15 @@
# Stage 00 Clarify: Ask Key Questions
## Inputs
- (none) - Start of workflow
## Process
Ask the user the following key questions to configure the scan:
1. Long only, or long + short? (Specify bias: long, short, or both)
2. Time horizon: 0DTE intraday scalps, or day/swing holds?
3. Asset class focus: Equities only, or include ETFs (SPY/QQQ/TAN/SOXL/SQQQ/KRE) in the confluence review?
Record the answers in a markdown file.
## Outputs
- user_preferences.md -> output/

View File

@@ -0,0 +1,18 @@
# Stage 01 Broad Filter: Initial Ticker Screening
## Inputs
- Layer 4 (working): ../00_clarify/output/user_preferences.md
- Layer 3 (reference): shared/cha-martin-watchlist.ms.csv
## Process
1. Read user preferences to determine bias, time horizon, and asset class focus.
2. Load the full ticker list from the watchlist CSV.
3. Establish market context by pulling snapshot data for SPY and QQQ to determine the day's regime (trend, range, key levels).
4. Perform a batch scan (using Finviz or equivalent) filtering for:
- Price within ~3% of the 50-day MA
- Consolidation/base pattern or pullback setup
- Above/below VWAP context
5. Record the resulting shortlist of candidates (expected 10-15 tickers) for further analysis.
## Outputs
- shortlist.md -> output/

View File

@@ -0,0 +1,18 @@
# Stage 02 Confluence Analysis: Evaluate Candidates
## Inputs
- Layer 4 (working): ../01_broad_filter/output/shortlist.md
- Layer 3 (reference): shared/cha-martin-watchlist.ms.csv (full ticker list for reference)
## Process
For each ticker in the shortlist, evaluate the following confluence factors:
1. Daily chart structure: load symbol, D timeframe to assess trend, price vs 50MA/200MA, support/resistance zones, base/consolidation patterns.
2. Intraday setup: load 3-min or 5-min chart to examine VWAP relationship, pre-market gap vs overnight range, opening range break potential.
3. Volume profile: check volume indicator for above-average volume confirming move or thin volume suggesting trap.
4. Options flow / unusual activity: use MCP → ttg-options chain snapshot to spot unusual call/put volume, max pain, gamma exposure.
5. Relative strength: visually compare chart to sector/market to see if holding while sector/market sells.
Record analysis for each ticker, noting which factors align.
## Outputs
- confluence_analysis.md -> output/

View File

@@ -0,0 +1,23 @@
# Stage 03 Trade Plan: Construct Detailed Trade Plans
## Inputs
- Layer 4 (working): ../02_confluence_analysis/output/confluence_analysis.md
- Layer 3 (reference): _config/trade_plan_template.md (optional template for structuring plans)
## Process
1. From the confluence analysis, select the top 2-4 tickers with the strongest confluence.
2. For each selected ticker:
- Load the ticker on AI chart with overlays: VWAP, 50 EMA, key support/resistance levels.
- Identify the exact entry zone, stop level, and target levels (T1/T2/T3).
- Draft a trade plan including:
* Symbol, side, entry zone, stop, targets, time horizon
* Rationale: confluence factors that align (daily structure + intraday trigger + flow confirmation)
* What invalidates it: the one condition that kills the thesis
- Given preference for credit spreads, evaluate options structure:
* Credit spread strikes (defined risk, collect premium)
* Bid-ask spread width (< $0.25 preferred for scalps)
* Time decay working in your favor
3. Compile all trade plans into a single document.
## Outputs
- trade_plans.md -> output/

View File

@@ -0,0 +1,20 @@
# Stage 04 Summary Card: Produce Final Scan Summary
## Inputs
- Layer 4 (working): ../03_trade_plan/output/trade_plans.md
- Layer 4 (working): ../02_confluence_analysis/output/confluence_analysis.md (for sitting-on-hands list)
- Layer 4 (working): ../01_broad_filter/output/shortlist.md (optional reference)
## Process
1. Review the trade plans and confluence analysis to rank setups by confluence score.
2. Select the top 3-5 setups.
3. For each selected setup, extract:
- Setup type (e.g., pullback, breakout, etc.)
- Entry zone, stop level, target levels (T1/T2/T3)
- Key confluence factors that aligned
- Risk level (based on stop distance, volatility, etc.)
4. Compile a "sitting on hands" list: tickers from the shortlist that showed some promise but lacked a decisive edge (note reasons).
5. Produce a structured summary card in markdown format.
## Outputs
- summary_card.md -> output/