Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
Post-trade review, pull losing trades from the strategy tester, screenshot each entry in context, and cluster common failure patterns.
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
87 lines · 573 words
You are running a post-trade forensic review to identify patterns in losing trades.
data_get_trades — fetch trade log from the active strategy (capped 20 per request; paginate if needed)
Filter to losses only: pnl < 0
Post-trade review, pull losing trades from the strategy tester, screenshot each entry in context, and cluster common failure patterns.
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 Learn From Losses 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 running a post-trade forensic review to identify patterns in losing trades.
What it covers
Step 1: Pull Trade History
Step 2: Set Up Review Chart
Step 3: Walk Each Loss
Step 4: Read Each Context
Step 5: Cluster Patterns
Step 6: Report
Cleanup
Sort by abs(pnl) descending — biggest losses first, these teach the most
If the strategy tester isn't open: ui_open_panel with panel: "strategy-tester" first.
chart_get_state — confirm symbol/timeframe match the strategy run
Optionally state_snapshot current chart state with tag pre-review so you can restore cleanly at the end
Add context indicators if missing (e.g., EMA200 for trend, ATR for volatility):
chart_manage_indicator add "Moving Average Exponential" (length 200)
chart_manage_indicator add "Average True Range"
For each losing trade (limit to top 10 by size to stay focused):
chart_scroll_to_date — jump to the entry bar (ISO date from the trade record)
chart_set_visible_range — zoom to ~50 bars around the entry for context
draw_shape with horizontal_line at entry price (label "E")
draw_shape with horizontal_line at stop price (label "SL")
draw_shape with horizontal_line at exit price (label "X")
capture_screenshot — save the annotated context
Example — reviewing a $ES1!` long that stopped out:
chart_scroll_to_date({ date: "2025-03-14T09:45:00" })
chart_set_visible_range({ ... ~50 bars ... })
draw_shape({ type: "horizontal_line", point: { price: 5812.50 }, text: "E" })
draw_shape({ type: "horizontal_line", point: { price: 5805.00 }, text: "SL" })
capture_screenshot()If CHART_LOADING errors fire between scrolls, wait 1s and retry.
For each loss, pull the state at entry:
data_get_study_values — what were RSI, MACD, EMA readings saying at entry?
data_get_pine_labels with study_filter — any "Bias" or "Regime" label on that bar?
data_get_ohlcv with summary: true, count: 20 — recent price action leading in
Collect into a per-trade record: {date, side, entry_regime, rsi, trend_vs_ema200, atr_multiple_of_sl, outcome}.
Look for recurring failure modes across the loss set:
Counter-trend entries — longs taken below EMA200 (or vice versa)
Overbought/oversold shorts/longs — RSI > 70 on longs, < 30 on shorts
Tight stops in high vol — SL < 1 ATR when ATR is elevated
Chop zone trades — entries inside a recently flat range
News/session edge — clustering around open, close, or pre-economic releases
Count frequencies. A pattern that appears in 6 of 10 losses is a real leak.
Produce a structured writeup:
Top 3 failure patterns with counts (e.g., "Counter-trend longs: 5/10, avg -$180")
Specific rule violations (e.g., "40% of losses taken below EMA200 — rule says longs only above")
Screenshot references for the 2-3 most illustrative examples
Concrete filter proposals — e.g., "Add close > ema200 gate; would have skipped 4 losses totaling -$620"
draw_clear — remove all the E/SL/X markers
state_restore with the pre-review snapshot id to return to the prior layout
Offer to codify the proposed filter into the Pine strategy (hand off to the pine-develop skill)
SKILL.md
87 lines · 573 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
Learn From Losses bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for