agentleFS
Sign inStart free
juandelossantosjuandelossantos/another-agent-skills/skills/planning-and-task-breakdown/SKILL.md

planning-and-task-breakdown

Skill1 starsChanged 11 days agoMITView on GitHub

Decompose work into small, verifiable tasks with explicit acceptance criteria. Use when a spec needs breakdown into implementable steps. Do NOT use for single-file changes.

We split this skill into the rules it gives an agent

3 rules. 1 is common, 2 are distinctive, and 0 are very specific to this project.

  • 1

    Common

    Most of the 68 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read the spec and relevant code.

    line 39
  2. Distinctive:

    If a task takes >2 hours, has >3 acceptance criteria, touches independent subsystems, or has "and" in the title — break it down.

    line 73
  3. Common:

    Before starting implementation, confirm:

    line 89

“Common” is measured: kept by at least 6 in 10 of the 68 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

Planning and Task Breakdown

Overview

Decompose work into small, verifiable tasks with explicit acceptance criteria. Every task should be small enough to implement, test, and verify in a single focused session.

When to Use

  • You have a spec and need to break it into implementable units
  • A task feels too large or vague to start
  • Work needs to be parallelized across multiple agents or sessions
  • The implementation order isn't obvious

When NOT to Use

  • Single-file changes with obvious scope
  • Spec already contains well-defined tasks

Output Contract

Task breakdown plan — ordered task list (any project, any stack) with acceptance criteria, verification steps, dependencies, and file scope per task, sized XS/S/M/L, with parallelization markers ([S]/[P]/[Pm]), checkpoint every 2-3 tasks, reviewed and approved by user before implementation.

The Planning Process

Step 1: Enter Plan Mode

Read the spec and relevant code. Identify patterns, map dependencies, note risks. Do NOT write code during planning. The output is a plan document, not implementation.

Step 2: Identify the Dependency Graph

Map what depends on what. Implementation order follows the dependency graph bottom-up: build foundations first.

Database schema → API models → API endpoints → Frontend client → UI

Step 3: Slice Vertically

Build one complete feature path at a time, not all of one layer.

Bad: Task 1: All DB → Task 2: All API → Task 3: All UI Good: Task 1: Create account → Task 2: Log in → Task 3: Create task

Step 4: Write Tasks

→ See guides/TEMPLATES.md for full templates.

Each task needs: Description, Acceptance criteria, Verification steps, Dependencies, Files touched, Estimated scope.

Step 5: Order and Checkpoint

Arrange so dependencies are satisfied, each task leaves a working state, checkpoints every 2-3 tasks, and high-risk tasks are early (fail fast).

Task Sizing

→ See guides/TEMPLATES.md for checkpoint format.

SizeFilesScope
XS1Single function or config
S1-2One component or endpoint
M3-5One feature slice
L5+Break it down further

If a task takes >2 hours, has >3 acceptance criteria, touches independent subsystems, or has "and" in the title — break it down.

Parallelization

→ See guides/PARALLELIZATION-AND-ANTI-PATTERNS.md for full guide.

Mark tasks: [S] sequential, [P] parallelizable, [Pm] merge point.

References

  • PATTERNS.md — Workflow pattern selection guide. Consult before choosing a pattern (Guardian, Lazy Loading, Skill Gate, etc.).
  • ANTI-PATTERNS.md — Common workflow anti-patterns to avoid.
  • GLOSSARY.md — Terminology reference for framework terms.

Verification

Before starting implementation, confirm:

  • PATTERNS.md consulted for workflow pattern selection
  • Every task has acceptance criteria
  • Every task has a verification step
  • Task dependencies are identified and ordered correctly
  • No task touches more than ~5 files
  • Checkpoints exist between major phases
  • The human has reviewed and approved the plan

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