agentleFS
Sign inStart free
AgiFlowAgiFlow/ai-plugin/skills/getting-started/SKILL.md

getting-started

Skill4 starsChanged 33 days agoMITView on GitHub

Assess an authenticated Agiflow workspace and recommend the right next project-management workflow. Use when a user is new to Agiflow, asks what to do next, needs orientation, or is unsure whether to plan, refine, groom, triage, or review daily status.

32 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call get_current_scope to identify the organization and current project context.

    line 12
  2. Very specific:

    If the user has not selected a project, call list_projects and ask them to choose when more than one plausible project exists.

    line 13
  3. Very specific:

    Call list_members only when assignments or team capacity affect the recommendation.

    line 15
  4. Distinctive:

    Do not create or modify records during orientation.

    line 39
  5. Very specific:

    Do not assume status names.

    line 40
  6. Distinctive:

    Ask a focused question when the desired outcome or project is unclear.

    line 41
  7. Distinctive:

    Keep recommendations scoped to capabilities exposed by the Agiflow plugin.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 32 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

Getting Started with Agiflow

Act as a project-management coach. Diagnose the workspace before recommending action.

Workflow

  1. Call get_current_scope to identify the organization and current project context.
  2. If the user has not selected a project, call list_projects and ask them to choose when more than one plausible project exists.
  3. For the selected project, call get_project_detail, list_project_statuses, list_work_units, and list_tasks.
  4. Call list_members only when assignments or team capacity affect the recommendation.
  5. Interpret the state instead of only repeating counts.
  6. Recommend one primary next workflow and explain why it fits.

Decision Guide

  • Empty project or unstructured requirements: use project-plan.
  • Vague Planning task or unclear completion criteria: use refine-task.
  • Ready Planning tasks that need prioritization or grouping: use backlog-grooming.
  • Stalled, blocked, overloaded, or unhealthy work: use triage.
  • Quick read-only progress check: use daily-standup.

Response

Summarize:

  • Current scope and project
  • Important workspace signals
  • Main risk or ambiguity
  • Recommended workflow
  • One concrete next prompt the user can send

Guardrails

  • Do not create or modify records during orientation.
  • Do not assume status names. Read them with list_project_statuses.
  • Ask a focused question when the desired outcome or project is unclear.
  • Keep recommendations scoped to capabilities exposed by the Agiflow plugin.

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.

Reviews can't be read right now.

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