agentsclimarketplace
Sign in

Task breakdown from plan

Skill roronoazoroshao369/vibe-coding-os/skills/core/task-breakdown-from-plan

Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.From the repository description

Install
npx -y skills add roronoazoroshao369/vibe-coding-os --skill task-breakdown-from-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 587 tokens by cl100k_base, as published. Nobody here has run it

Task Breakdown From Plan

Purpose

Decompose an implementation plan into small, reviewable, independently grabbable tasks with explicit dependencies, parallel markers, and test-first ordering.

When to use

Use after a plan is agreed and before implementation, especially when work can be parallelized, handed to multiple agents, or needs a clear order of execution.

Inputs

The agreed plan (steps, technical context, risks), acceptance criteria, and any constraints on ordering (shared interfaces, data migrations).

Workflow

  1. Convert each plan step into one or more concrete tasks.
  2. For each task, write a clear subject, the files involved, and a done condition.
  3. Add a depends-on field listing prerequisite task IDs.
  4. Mark tasks that can run concurrently with a parallel marker.
  5. Sequence test tasks before the implementation tasks they cover (TDD ordering).
  6. Confirm every acceptance criterion is covered by at least one task.
  7. Record the ordering rationale so reviewers understand the dependency graph.

Outputs

A task list using templates/tasks-template.md with dependencies, parallel markers, TDD ordering, and acceptance-criteria coverage.

Failure modes

  • Tasks are too large or vaguely scoped to grab independently.
  • Hidden dependencies cause rework when tasks run out of order.
  • Implementation tasks precede their tests.
  • Some acceptance criteria have no covering task.

Verification checklist

  • Each task has a clear done condition and named files.
  • Dependencies are explicit; the graph has no cycles.
  • Parallelizable tasks are marked.
  • Test tasks precede their implementation tasks.
  • Every acceptance criterion maps to a task.

Applied / Not Applied

  • Applied: dependency-aware decomposition, parallel markers, and TDD ordering from github/spec-kit.
  • Not applied: upstream tasks template text or [P] syntax verbatim, and upstream command names. Complements (does not replace) skills/core/issue-slicing/SKILL.md, which slices ideas into issues; this skill turns an agreed plan into ordered tasks.

Ghi chú tiếng Việt

Chia kế hoạch thành các task nhỏ, độc lập, có depends-on, đánh dấu task song song, và xếp test trước implementation (TDD). Đảm bảo mọi tiêu chí chấp nhận đều có task. Khác với issue-slicing (chia ý tưởng thành issue); skill này biến plan thành task có thứ tự. Liên kết: skills/core/dependency-aware-task-ordering/SKILL.md, skills/core/test-driven-development/SKILL.md.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most task breakdown skills give in 587 tokens

Counted across 221 of the 230 authors here whose files we hold, read 2026-09-06

  • Write acceptance criteria for every taskhere, and in 32 of 221, across 30 files
  • Add checkpoints every two to three tasksin 18 of 221, across 16 files
  • Schedule high-risk tasks earlyin 16 of 221, across 14 files
  • Slice work vertically into complete feature pathsin 16 of 221, across 14 files
  • Include verification steps in every taskin 15 of 221, across 13 files
  • Map dependencies between componentsin 14 of 221, across 12 files
  • Get human approval before implementingin 14 of 221, across 12 files
  • Enter read-only plan mode before writing codein 10 of 221
  • Read the spec and codebase before planningin 9 of 221, across 7 files
  • Map the dependency graph before ordering tasksin 8 of 221
  • Break any task touching more than five filesin 8 of 221
  • List each task's dependenciesin 7 of 221

Said here and by no other author read

  • Convert each plan step into concrete tasks
  • Keep tasks small and independently grabbable
  • Write a subject, files, and done condition per task
  • List prerequisite task IDs in a depends-on field
  • Sequence test tasks before their implementation tasks
  • Record the ordering rationale for reviewers

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.