workflow-core

Canonical repository workflow contract for all runtimes.

9 stars

Best use case

workflow-core is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Canonical repository workflow contract for all runtimes.

Teams using workflow-core should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/workflow-core/SKILL.md --create-dirs "https://raw.githubusercontent.com/mlucascosta/ia_boilerplate/main/.agents/skills/workflow-core/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/workflow-core/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How workflow-core Compares

Feature / Agentworkflow-coreStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Canonical repository workflow contract for all runtimes.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Purpose

Load the shared operating contract from `.agents/AGENTS.md` and route work through the canonical repository workflow.

# Read First

- `.agents/AGENTS.md`
- `docs/ai/WORKFLOW_SHORT.md`
- `docs/ai/ARTIFACTS.md`

# Use When

- Any runtime needs the canonical repository rules
- A task needs path selection, verification level, or artifact guidance

# Output

- Minimal diff or patch
- Explicit verification evidence only when needed

# Prohibitions

- No runtime-specific rule invention
- No duplicate policy outside `.agents/`