agentleFS
Sign inStart free
kecoma1kecoma1/MQL5-SKILLS/skills/analyze/SKILL.md

analyze

Skill17 starsChanged 7 months agoMITView on GitHub

Analyze market regime and session structure in this MQL5 workspace using reusable CSV exports from an MQL5 script. Use when Codex needs to classify a market as Tendencial or Lateral with moving average and ATR, export per-session data to Terminal Common Files for M15, H1, and D1, and then read those CSV files directly to summarize insights and recommendations by session without recreating scripts that already exist.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use constitution, revise and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArvorCoSkill

    constitution

    Create or update the project constitution - personalized governance and coding principles. Use when starting a project or updating project standards. Triggers on: create constitution, update principles, set project rules.

    Also in 4 projects that use this

  • stormlightlabsSkill

    revise

    Address review comments on an open pull request and push the fixes. Use for /edit, /revise, or when asked to respond to review feedback on a PR number.

    Also in 3 projects that use this

  • DockerSkill

    write

    Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.

    Also in 6 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 5 projects that use this

  • H-mmerSkill

    submit

    Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.

    Also in 3 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • +1 more from ArvorCo

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. 0 are common, 14 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 14

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to analyze markets by session in this workspace.

    line 10
  2. Distinctive:

    Keep the workflow simple:

    line 12
  3. Distinctive:

    read the CSV directly

    line 14
  4. Distinctive:

    Do not create HTML reports.

    line 17
  5. Distinctive:

    Do not rely on Python for this workflow.

    line 18
  6. Distinctive:

    Use these files as the primary workflow:

    line 22
  7. Distinctive:

    Do not recreate them on each request.

    line 28
  8. Very specific:

    Create or update a script preset under MQL5\Presets\ with plain script values.

    line 46
  9. Very specific:

    Create or update a startup .ini under MQL5\config\ using [StartUp] Script=....

    line 47
  10. Distinctive:

    Read the generated CSV files directly and summarize them for the user.

    line 51
  11. Very specific:

    Do not use the optimization format value||start||step||stop||selected in a script preset.

    line 70
  12. Distinctive:

    Treat these CSV files as the source of truth.

    line 119
  13. Distinctive:

    Use these session buckets for intraday analysis:

    line 123
  14. Distinctive:

    Treat these windows as UTC unless the script or user explicitly changes them.

    line 131
  15. Distinctive:

    Use the exported values directly.

    line 140
  16. Distinctive:

    When answering the user, summarize:

    line 144
  17. Distinctive:

    Keep the tone analytical and concise.

    line 152

“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analyze

Overview

Use this skill to analyze markets by session in this workspace.

Keep the workflow simple:

  • export CSV data with the MQL5 script
  • read the CSV directly
  • answer the user from the exported data

Do not create HTML reports. Do not rely on Python for this workflow.

Reusable files

Use these files as the primary workflow:

  • Scripts\codex\SessionMarketExporter.mq5
  • Presets\SessionMarketExporter-<SYMBOL>-lastyear.set
  • config\session-market-exporter-<symbol>-lastyear.ini

Do not recreate them on each request. Reuse them and only update them when the export logic is actually wrong.

Goal

Produce session-level market analysis for M15, H1, and D1 with:

  • Session name
  • Moving average context
  • ATR context
  • Market type: Tendencial or Lateral
  • Trend direction
  • Session volatility
  • Session insights
  • Session recommendations

Export workflow

  1. Compile Scripts\codex\SessionMarketExporter.mq5.
  2. Create or update a script preset under MQL5\Presets\ with plain script values.
  3. Create or update a startup .ini under MQL5\config\ using [StartUp] Script=....
  4. Close any running terminal64.exe before launching.
  5. Launch MT5 with /config:....
  6. Export CSV files into Terminal\Common\Files\.
  7. Read the generated CSV files directly and summarize them for the user.

Script preset rule

For ScriptParameters, use a normal script preset with simple key=value lines.

Correct example:

InpSymbol=EURUSD
InpLookbackDays=365
InpMAPeriod=20
InpMAMethod=0
InpATRPeriod=14
InpTrendSlopeAtrRatio=0.15
InpTrendDistanceAtrRatio=0.20
InpOutputPrefix=session_market

Do not use the optimization format value||start||step||stop||selected in a script preset. That format is for optimization, not for scripts.

Startup ini pattern

Use this structure:

[Common]
Login=4000030114

[Experts]
Enabled=1

[StartUp]
Symbol=EURUSD
Period=M15
Script=codex\SessionMarketExporter
ScriptParameters=SessionMarketExporter-EURUSD-lastyear.set
ShutdownTerminal=1

The Script= path is relative to MQL5\Scripts\. The ScriptParameters= file is loaded from MQL5\Presets\.

Exported CSV files

Expect one CSV per timeframe:

  • session_market_<SYMBOL>_M15.csv
  • session_market_<SYMBOL>_H1.csv
  • session_market_<SYMBOL>_D1.csv

In this workspace they are currently exported directly under:

  • C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\Common\Files\

CSV expectations

The exported CSV should include fields like:

  • session
  • ma_value
  • ma_slope_points
  • atr_points
  • distance_to_ma_points
  • trend_direction
  • market_type
  • trend_score

Treat these CSV files as the source of truth.

Session model

Use these session buckets for intraday analysis:

  • Asia: 00:00-08:00
  • London: 08:00-16:00
  • NewYork: 16:00-24:00

For D1, use a single Daily session.

Treat these windows as UTC unless the script or user explicitly changes them.

Interpretation rules

  • Tendencial: moving average slope and price-vs-MA distance are large enough relative to ATR.
  • Lateral: MA slope and distance-to-MA do not show directional expansion versus ATR.
  • Volatilidad Alta: current ATR is materially above the session median.
  • Volatilidad Baja: current ATR is materially below the session median.

Use the exported values directly. Do not invent extra indicators that are not in the CSV.

Final analysis format

When answering the user, summarize:

  • the current regime for each timeframe
  • the regime by session
  • the volatility by session
  • practical recommendations by session
  • any cross-timeframe alignment or conflict

Keep the tone analytical and concise.

Example commands

Compile:

& 'C:\Program Files\MetaTrader 5\MetaEditor64.exe' /compile:'C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\<terminal-id>\MQL5\Scripts\codex\SessionMarketExporter.mq5' /log:'C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\<terminal-id>\MQL5\Logs\session-market-exporter-compile.log'

Run the exporter:

Get-Process terminal64 -ErrorAction SilentlyContinue | Stop-Process -Force
Start-Sleep -Seconds 2
Start-Process -FilePath 'C:\Program Files\MetaTrader 5\terminal64.exe' -ArgumentList '/config:C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\<terminal-id>\MQL5\config\session-market-exporter-eurusd-lastyear.ini' -Wait

Validated paths in this workspace

  • C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\Common\Files\session_market_EURUSD_M15.csv
  • C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\Common\Files\session_market_EURUSD_H1.csv
  • C:\Users\user-id\AppData\Roaming\MetaQuotes\Terminal\Common\Files\session_market_EURUSD_D1.csv

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free