agentleFS
youmissedaspotyoumissedaspot/ymas-agent-workflows/skills/workflow-orientation/SKILL.md

workflow-orientation

Skill1 starsChanged 46 days agoMITView on GitHub

Explain how to begin or resume work with YMAS when a user asks how the workflow works or where to start. Orientation only; do not execute development or replace an actual work request with onboarding.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use human explanation and editorial judgment for readable explanations and documentation.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Getting started with YMAS

YMAS helps turn an idea or consequential change into accepted definitions, coherent architecture, and verified implementation under the project's own authority. This skill explains how to use that process; it does not run it.

Read the repository's instructions and index when available, then inspect only enough current authority and operational context to identify a useful starting stage. An existing project resumes from its settled decisions, specifications, or implementation; it does not restart discovery. If no project is available, give general orientation without inventing its state or creating a repository.

Give a short explanation of the lifecycle:

Discuss → True Spec worksheet → Decide → SPEC / SPECARC → systems.md → Plan → Implement → Verify → Human Acceptance where applicable

Explain the principal artifacts:

  • True Spec worksheet: a structured aid for exploring consequential questions and capturing decisions; not product authority.
  • SPEC: an accepted specification of what must be true for a product or system.
  • SPECARC: an accepted architecture specification for a defined concern. SPEC and SPECARC are siblings and can be developed in either order.
  • systems.md: the integrated architecture/system map derived from the complete current specification set, once that set supports a useful map.

Users can describe work naturally; they do not need to memorize skill names, IDs, or filing rules. Small or already-specified work skips unnecessary stages. The agent follows normal routing when actual work begins. Offer a relevant next prompt from examples such as:

  • “I have an idea for an economic simulation.”
  • “Help me figure out how shipping contracts should work.”
  • “We need to define the architecture for event reconciliation.”
  • “These decisions are settled; turn them into specifications.”
  • “Update the architecture map from the current specifications.”

Use the workflow index to explain the relevant next stage. End after orientation. Do not generate a decision worksheet, settle product choices, write specifications, adopt documentation rules, make a plan, or implement changes as part of this skill. /start is a temporary conversational label, not a registered command alias; the packaged skill name is workflow-orientation.

Use human explanation and editorial judgment for readable explanations and documentation. Consider ordinary documentation purposes only where useful; do not reclassify canonical specifications or infer migration authority from editorial guidance.

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.