agentleFS
Sign inStart free
roborracleroborracle/agent-workflow-kit/skills/sprint-planner/SKILL.md

sprint-planner

Skill0 starsChanged 3 months agoMITView on GitHub

Break down a project into sprints with atomic, testable tasks as GitHub Issues (plan sprints, decompose tasks, sprint breakdown).

5 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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read existing project docs (CHANGELOG, README, PLAN, PRD)

    line 12
  2. Distinctive:

    No more than 20 tasks — split if larger

    line 22
  3. Distinctive:

    If multiple purposes or can't describe in one sentence, split it

    line 31
  4. Very specific:

    Write the final plan to docs/[project-name]-sprint-plan.md containing:

    line 69

“Common” is measured: kept by at least 6 in 10 of the 4 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

Sprint Decomposition Protocol

1. Analyze

  • Read existing project docs (CHANGELOG, README, PLAN, PRD)
  • Map scope: components, dependencies, risks, unknowns
  • Identify what "demoable" means at each increment
  • List technical constraints and external dependencies

2. Decompose into Sprints

Each sprint:

  • Single goal statement and concrete demo criteria
  • Produces runnable software building on previous sprint
  • Sprint 1 always results in something that runs
  • No more than 20 tasks — split if larger
  • No "infrastructure-only" sprints — every sprint is demoable

3. Atomize into Tasks

Each task:

  • 1 commit. 1 purpose. 1 testable outcome.
  • Has validation: tests preferred, or explicit manual verification
  • Specifies: objective (one sentence), type, dependencies, files affected, validation, commit message
  • Types: feature | bugfix | refactor | test | docs | config | spike
  • If multiple purposes or can't describe in one sentence, split it

4. Wire Dependencies

  • Explicit, acyclic dependency declarations
  • Encoded as GitHub Issue references
  • Front-load unknowns and spikes

5. Validate Coverage

  • Every requirement maps to at least one task
  • Every task serves a sprint goal (no orphans)
  • Error handling and edge cases have dedicated tasks
  • No task has multiple purposes
  • No task lacks validation criteria
  • No sprint lacks a demoable outcome
  • Dependency graph is acyclic

6. Mandatory Subagent Review

Pass the full plan to a subagent:

Review this sprint plan for: (1) task atomicity, (2) missing tests/validation, (3) dependency correctness, (4) coverage gaps, (5) sprint demoability, (6) ordering — unknowns front-loaded? (7) GitHub Issue structure. Flag as CRITICAL / WARNING / SUGGESTION with specific fixes.

Incorporate all CRITICAL and WARNING items before proceeding.

7. Create GitHub Issues

gh auth status && gh repo view
gh label list --limit 200

# Reuse labels per the Label Taxonomy in rules/git-workflow.md (priority/P0..P2,
# type/*, area/*). Create only what is missing, without --force: it overwrites an
# existing label's color and description.

# Create milestones per sprint, then issues per task

Output

Write the final plan to docs/[project-name]-sprint-plan.md containing:

  • Project overview and success criteria
  • Sprint summary table
  • Full task details with GitHub Issue numbers
  • Dependency graph (ASCII)
  • Risk register

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.

Check your setup, free