agentleFS
AgiFlowAgiFlow/ai-plugin/skills/project-plan/SKILL.md

project-plan

Skill4 starsChanged 33 days agoMITView on GitHub

Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.

9 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

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 6

    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. Distinctive:

    Create a focused near-term plan.

    line 8
  2. Very specific:

    Call get_current_scope and resolve the target project with list_projects when needed.

    line 12
  3. Very specific:

    Call get_project_detail, list_project_statuses, and list_tasks to understand goals, configured statuses, and existing work.

    line 13
  4. Distinctive:

    Ask only the questions needed to resolve the intended outcome, users, scope, constraints, and definition of done.

    line 14
  5. Distinctive:

    Check for duplicate or overlapping tasks before proposing new ones.

    line 15
  6. Very specific:

    After approval, use batch_create_tasks for multiple tasks or create_task for one task.

    line 25
  7. Very specific:

    Call list_tasks to verify the created tasks and report any per-item errors.

    line 26
  8. Distinctive:

    Do not create work units in this workflow.

    line 30
  9. Distinctive:

    Do not promote tasks to Todo.

    line 31
  10. Distinctive:

    Prefer the smallest plan that delivers useful progress.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 7 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

Agiflow Project Plan

Create a focused near-term plan. Plan tasks first and leave work-unit creation to backlog grooming.

Workflow

  1. Call get_current_scope and resolve the target project with list_projects when needed.
  2. Call get_project_detail, list_project_statuses, and list_tasks to understand goals, configured statuses, and existing work.
  3. Ask only the questions needed to resolve the intended outcome, users, scope, constraints, and definition of done.
  4. Check for duplicate or overlapping tasks before proposing new ones.
  5. Decompose the outcome into small vertical slices that can be completed and verified independently.
  6. For each proposed task, include:
    • Clear title
    • Outcome-focused description
    • At least two testable acceptance criteria
    • Explicit in-scope and out-of-scope boundaries
    • Priority and useful categorization tags
    • Dependencies or sequencing notes when relevant
  7. Present the complete task plan and request approval before writing.
  8. After approval, use batch_create_tasks for multiple tasks or create_task for one task. Use the exact Planning status name returned by list_project_statuses.
  9. Call list_tasks to verify the created tasks and report any per-item errors.

Planning Rules

  • Do not create work units in this workflow.
  • Do not promote tasks to Todo.
  • Prefer the smallest plan that delivers useful progress.
  • Split tasks that combine unrelated outcomes or cannot be verified independently.
  • Preserve existing work and avoid duplicates.

Response

Report created task titles, priorities, dependencies, and any tasks that still need user decisions. Recommend refine-task for ambiguous tasks or backlog-grooming when the Planning backlog is ready.

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.