Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
Cross-asset reasoning across a multi-pane layout, set a 2x2 grid, assign correlated symbols to each pane, and identify leader/laggard/divergence.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
94 lines · 530 words
You are using TradingView's pane layouts to reason across several correlated instruments at once.
Power-toolkit shortcuts: snapshot the current layout with
state_snapshotbefore mutating it (so the user canstate_restoreafterwards). Usechart_vision_readper active pane to grab everything (image + indicators + Pine graphics) in one call.
Cross-asset reasoning across a multi-pane layout, set a 2x2 grid, assign correlated symbols to each pane, and identify leader/laggard/divergence.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Multi-Pane Cross-Asset Analysis skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
The principle
You are using TradingView's pane layouts to reason across several correlated instruments at once.
What it covers
Step 1: Choose the Layout
Step 2: Assign Symbols
Step 3: Align Timeframes
Step 4: Stream or Poll
Step 5: Compute Relative Moves
Step 6: Annotate Divergences
Step 7: Report
Cleanup
pane_set_layout — typical choices:
"2x2" for four symbols (e.g., the index complex)
"1x2" / "2x1" for two
"1x3" / "3x1" for three
Example — index complex: pane_set_layout({ layout: "2x2" }).
Use pane_set_symbol once per pane. Common correlated baskets:
US Index complex: ES1! (SP500), NQ1! (Nasdaq), YM1! (Dow), RTY1! (Russell)
Energy: CL1! (WTI), BZ1! (Brent), NG1! (Nat Gas), XLE
Metals: GC1! (Gold), SI1! (Silver), HG1! (Copper), PL1! (Platinum)
Crypto majors: BTCUSD, ETHUSD, SOLUSD, TOTAL
Risk-on/off: SPY, TLT, DXY, VIX
pane_set_symbol({ pane: 0, symbol: "ES1!" })
pane_set_symbol({ pane: 1, symbol: "NQ1!" })
pane_set_symbol({ pane: 2, symbol: "YM1!" })
pane_set_symbol({ pane: 3, symbol: "RTY1!" })If a pane errors with CHART_LOADING, wait ~2s before querying that pane.
Either set each pane's timeframe via pane_set_symbol (if it accepts tf) or loop through panes calling chart_set_timeframe after pane_focus. All panes should match (e.g., all 15m) for valid comparison.
Two modes:
Stream — tv stream all (or whatever live-stream entrypoint is wired) for push updates across all panes
Poll — pane_list to enumerate panes, then per-pane quote_get + data_get_ohlcv with summary: true
For a point-in-time analysis, polling is simpler. For live monitoring over 30+ min, stream.
For each pane, pull:
quote_get — current price + change%
data_get_ohlcv with summary: true, count: 20 — recent range
Compute normalized % moves since session open (or since any anchor bar). The leader is the one with the largest % change in the dominant direction; the laggard is the smallest; divergence is when one pane goes opposite the rest.
Example output:
ES1! +0.42% (laggard)
NQ1! +0.91% (LEADER — tech leading risk-on)
YM1! +0.18%
RTY1! -0.35% (DIVERGENCE — small caps down while indices up)If you spot a divergence:
pane_focus on the divergent pane
draw_shape with text marking the divergence bar
capture_screenshot with region: "full" so all four panes are in frame
Provide the cross-asset read:
Leader / laggard / divergent with % moves
Correlation check — are the normally-correlated pairs still in sync? (e.g., ES/NQ typically correlated; if they split, note it)
Actionable interpretation — e.g., "RTY1! weakness while ES1!/NQ1! rally = narrow breadth, fade long setups on indices"
If the user wanted a single-pane view back:
pane_set_layout with "1x1"
Or state_restore if a prior snapshot exists
SKILL.md
94 lines · 530 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Multi-Pane Cross-Asset Analysis bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for