By e-stpierre
[Beta] YAML-based workflow orchestration with parallel execution, conditional logic, and retry mechanisms for complex multi-step tasks
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin e-stpierre-agentic-forgeAdd a new improvement entry to the improvements tracking document. This skill creates a structured improvement record with a unique ID, progress tracking checkbox, and detailed description section.
Analyze codebase for bugs, debt, documentation, security, or style issues
Create a checkpoint to track progress and share context
Add a log entry to the workflow log
Create a new Claude Code skill following best practices and guidelines
Fix issues from an analysis document iteratively
Create and checkout a new git branch following the naming convention: `<category>/<issue-id>_<branch-name>` or `<category>/<branch-name>` when no issue ID is provided. Links to issue tracking when available.
Create a well-structured commit with a concise title and optional bullet-point description. Commits staged changes with proper formatting and AI attribution.
Create a pull request using the GitHub CLI with a descriptive title and appropriately-sized description. The PR description is automatically scaled based on the scope and impact of the changes.
Evaluate workflow state and determine next action
Create an implementation plan for a task
Review implementation quality and plan compliance
Create, update, explain, validate, and debug agentic-sdlc YAML workflows with comprehensive schema knowledge
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Uses power tools
Uses Bash, Write, or Edit tools
Autonomous workflow orchestration for Claude Code
YAML-defined workflows | Multi-step execution | Progress tracking | Error recovery
Add this repository as a plugin marketplace in Claude Code:
/plugin marketplace add e-stpierre/agentic-forge
Install the plugin(s) you need and refer to their README for usage.
YAML-based workflow orchestration for autonomous task execution with parallel execution, conditional logic, and retry mechanisms.
Best for: Autonomous development where you prefer Claude works independently.
Install the plugin in Claude Code:
/plugin install agentic-sdlc@agentic-forge
Install the python CLI tools:
# Windows (PowerShell)
uv tool install "$env:USERPROFILE\.claude\plugins\marketplaces\agentic-forge\plugins\agentic-sdlc"
# macOS/Linux
uv tool install ~/.claude/plugins/marketplaces/agentic-forge/plugins/agentic-sdlc
See Agentic-SDLC README for all skills and workflow options.
# Run plan-build-review workflow for full SDLC automation
agentic-sdlc run plan-build-review.yaml --var "task=Add dark mode support"
# Complete a task end-to-end autonomously
agentic-sdlc run one-shot.yaml --var "task=Add user authentication"
# List available workflows
agentic-sdlc workflows
# Run a workflow with variables for iterative task completion
agentic-sdlc run ralph-loop.yaml --var "max_iterations=20" \
--var "task=Follow the improvement plan. Each iteration: read plan, implement next task, commit, STOP."
This project is licensed under the MIT License - see the LICENSE file for details.
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
AI-powered development tools for code review, research, design, and workflow automation.
Complete collection of battle-tested Claude Code configs agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.