agentleFS
roronoazoroshao369roronoazoroshao369/vibe-coding-os/skills/core/dependency-aware-task-ordering/SKILL.md

dependency-aware-task-ordering

Skill1 starsChanged 5 months agoMITView on GitHub

Order tasks by their real dependencies and identify which tasks can safely run in parallel, so execution avoids rework and concurrency is exploited without conflicts. Use after task breakdown, when planning execution order, when assigning work to multiple agents, or when a build keeps breaking because tasks ran out of order. The task list with per-task depends-on fields, shared interfaces or files, and any data/migration ordering constraints. An ordered task list with a dependency graph, parallel-safe groups, and exclusive-access notes.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Use after task breakdown, when planning execution order, when assigning work to multiple agents, or when a build keeps breaking because …

    line 21
  2. Very specific:

    Not applied: upstream marker syntax verbatim or CLI-driven ordering.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Dependency-Aware Task Ordering

Purpose

Order tasks by their real dependencies and identify which tasks can safely run in parallel, so execution avoids rework and concurrency is exploited without conflicts.

When to use

Use after task breakdown, when planning execution order, when assigning work to multiple agents, or when a build keeps breaking because tasks ran out of order.

Inputs

The task list with per-task depends-on fields, shared interfaces or files, and any data/migration ordering constraints.

Workflow

  1. Build the dependency graph from each task's depends-on.
  2. Detect cycles; break them by splitting or re-scoping tasks.
  3. Topologically order tasks so prerequisites come first.
  4. Group tasks with no shared files or interfaces as parallel-safe and mark them.
  5. Sequence test tasks before the implementation tasks they verify.
  6. Note any task that touches a shared resource and must run exclusively.
  7. Record the ordering and parallel groups for reviewers and executors.

Outputs

An ordered task list with a dependency graph, parallel-safe groups, and exclusive-access notes.

Failure modes

  • Cycles or hidden dependencies cause repeated rework.
  • Tasks marked parallel actually share a file and conflict.
  • Tests are scheduled after the code they should drive.
  • The ordering is implicit and not reviewable.

Verification checklist

  • The dependency graph is acyclic.
  • Parallel-marked tasks share no files or interfaces.
  • Test tasks precede their implementation tasks.
  • Exclusive-access tasks are flagged.
  • Ordering rationale is recorded.

Applied / Not Applied

  • Applied: task dependencies, parallel markers, and TDD ordering from github/spec-kit.
  • Not applied: upstream marker syntax verbatim or CLI-driven ordering. Ordering is a documented local convention in templates/tasks-template.md.

Ghi chú tiếng Việt

Sắp xếp task theo phụ thuộc thật, phát hiện chu trình, và đánh dấu nhóm chạy song song an toàn (không chung file/interface). Xếp test trước code. Ghi rõ thứ tự để review. Liên kết: skills/core/task-breakdown-from-plan/SKILL.md, templates/tasks-template.md.

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.