agentleFS
AgiFlowAgiFlow/ai-plugin/skills/backlog-grooming/SKILL.md

backlog-grooming

Skill4 starsChanged 33 days agoMITView on GitHub

Review Agiflow Planning tasks for readiness, prioritize approved work, group related tasks into work units, and promote ready tasks to Todo. Use when grooming a backlog, organizing planned tasks, creating work units, or deciding what should be executed next.

10 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, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat grooming as the quality gate between Planning and Todo.

    line 8
  2. Very specific:

    Call list_tasks for Planning tasks, list_work_units for existing active work units, and list_members for assignment context.

    line 13
  3. Very specific:

    Call get_task for tasks whose readiness, dependencies, or acceptance criteria are unclear.

    line 14
  4. Very specific:

    Use batch_create_work_units for approved groups.

    line 26
  5. Very specific:

    Use update_task to move only ready, ungated tasks to the exact Todo status and set their ordering.

    line 27
  6. Very specific:

    Verify with list_tasks and list_work_units.

    line 28
  7. Distinctive:

    Never promote a vague task or a task missing testable acceptance criteria.

    line 32
  8. Distinctive:

    Never promote a downstream task whose required upstream work is incomplete.

    line 33
  9. Distinctive:

    Do not force unrelated work into one work unit.

    line 34
  10. Distinctive:

    Do not modify records before the user approves the proposed grooming plan.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 9 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 Backlog Grooming

Treat grooming as the quality gate between Planning and Todo.

Workflow

  1. Resolve the target project and call list_project_statuses to discover its exact status names.
  2. Call list_tasks for Planning tasks, list_work_units for existing active work units, and list_members for assignment context.
  3. Call get_task for tasks whose readiness, dependencies, or acceptance criteria are unclear.
  4. Classify every Planning task as:
    • Ready
    • Needs refinement
    • Blocked by a dependency
    • Duplicate or obsolete
  5. Require a clear outcome, sufficient context, and at least two testable acceptance criteria before promotion.
  6. Propose a priority order and explain the tradeoffs.
  7. Group three to eight cohesive tasks into a work unit only when they deliver one shared capability. Leave one or two related tasks standalone and split groups larger than eight.
  8. Review existing work units for shared dependencies and sequencing conflicts.
  9. Present the proposed promotions, work units, assignments, and dependency order. Request approval before writing.
  10. After approval:
    • Use batch_create_work_units for approved groups.
    • Use update_task to move only ready, ungated tasks to the exact Todo status and set their ordering.
  11. Verify with list_tasks and list_work_units.

Guardrails

  • Never promote a vague task or a task missing testable acceptance criteria.
  • Never promote a downstream task whose required upstream work is incomplete.
  • Do not force unrelated work into one work unit.
  • Do not modify records before the user approves the proposed grooming plan.
  • Recommend refine-task for tasks that fail readiness checks.

Response

Report promoted tasks, created work units, items left in Planning, dependency gates, and the recommended execution order.

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.