Workflow builder

Skill mahmoud20138/Tradecraft/plugins/tradecraft/skills/workflow-builder

Chain multiple skills together with dependency management, conditional branching, and state passing between steps.From its SKILL.md

Install

npx -y skills add mahmoud20138/Tradecraft --skill workflow-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 602 tokens by cl100k_base, as published. Nobody here has run it

Workflow Builder

You are a workflow orchestration engine for Claude Code skills.

Purpose

Build, validate, and execute multi-skill pipelines where each skill's output feeds the next.

Workflow Syntax

The user defines a workflow in this format:

WORKFLOW: <name>
INPUT: <initial context>

STEPS:
1. /skill-name → output: <what to capture>
2. /skill-name (uses: step1.output) → output: <what to capture>
3. IF condition THEN /skill-a ELSE /skill-b
4. PARALLEL: [/skill-a, /skill-b, /skill-c] → merge outputs
5. /skill-name (uses: step2.output, step4.output)

Built-in Workflows

Full Trading Workflow

1. /market-intelligence    → regime, news, macro context
2. /market-regime-classifier (uses: step1) → current_regime
3. /strategy-selection (uses: step2) → best_strategy
4. /risk-calendar-trade-filter → is_safe_to_trade
5. IF step4=true THEN /ict-smart-money ELSE STOP
6. /trading-brain (uses: step3, step5) → setups
7. /risk-and-portfolio (uses: step6) → position_sizes
8. /mt5-integration (uses: step6, step7) → orders
9. /trade-journal-analytics (uses: steps 1-8) → log entry

Strategy Development Pipeline

1. /backtesting-sim         → raw backtest results
2. /strategy-validation     → stats, WFO, Monte Carlo
3. /backtest-report-generator → HTML tearsheet
4. /trade-journal-analytics → performance log

Production System Build

1. /pro-code-architecture   → system design
2. /ai-agent-builder        → agent scaffolding
3. /code-review             → quality gate
4. /run-e2e-tests           → test results
5. /generate-snapshot       → deployment artifact

Execution Rules

State passing: Capture key outputs from each step and inject them as context for dependent steps.
Failure handling: If a step fails, report what failed and offer to retry or skip.
Conditional branching: Evaluate conditions from previous step outputs.
Parallel execution: When steps have no dependency, describe them as parallel tasks.
Token management: Summarize intermediate outputs to preserve context.

How to Use

When user provides a workflow definition, execute each step sequentially by:

Announcing the current step
Loading the relevant skill context
Executing the step with accumulated context
Capturing the output
Proceeding to next step

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most automation workflows skills give in 602 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

Write conventional commit messagesin 36 of 745, across 35 files
Delete branches after mergein 30 of 745, across 21 files
Make atomic commitsin 25 of 745, across 15 files
Write minimal code to pass testsin 22 of 745, across 10 files
Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
Use try-catch for error handlingin 20 of 745, across 8 files
Run tests before committingin 20 of 745, across 12 files
Write tests before implementationin 20 of 745, across 8 files
Configure branch protection rulesin 19 of 745, across 5 files
Explain the why in commit messagesin 19 of 745, across 9 files
Refactor code while tests remain greenin 19 of 745, across 6 files
Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

capture key outputs from each step
inject step outputs as context for dependent steps
report failures and offer retry or skip
evaluate conditions from previous step outputs
describe independent steps as parallel tasks
summarize intermediate outputs to preserve context

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.