agentleFS
madeincartelmadeincartel/claude-code-framework/skills/task-decomposition/SKILL.md

task-decomposition

Skill1 starsChanged 9 months agoMITView on GitHub

Decompose approved tech-spec into atomic task files with parallel creation and validation.

19 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 6

    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:

    Ask user for feature name if not provided.

    line 20
  2. Very specific:

    Read work/{feature}/tech-spec.md.

    line 22
  3. Very specific:

    If not approved — tell user: "tech-spec не утверждён.

    line 23
  4. Distinctive:

    Read skills/reviewers catalog from skills-and-reviewers.md — for passing correct skills/reviewers to task-creators.

    line 29
  5. Distinctive:

    Read JSON reports, collect findings.

    line 69
  6. Very specific:

    If issues found — for each task with issues, launch task-creator in fix mode:

    line 70
  7. Very specific:

    After each validation round, git commit: chore(tasks): validation round {N} — {summary}

    line 73
  8. Distinctive:

    If problems remain after 3rd iteration — show user: "Вот что осталось — давай решим вместе."

    line 75
  9. Distinctive:

    After individual validation passes, run a final cross-task check:

    line 79
  10. Very specific:

    If issues found → launch task-creator in fix mode for affected tasks.

    line 85
  11. Distinctive:

    Wait for user approval.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 15 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

Task Decomposition

Decompose tech-spec Implementation Tasks into individual task files with parallel creation and validation.

Input: work/{feature}/tech-spec.md (status: approved) Output: work/{feature}/tasks/*.md (validated) Language: Task files in English, communication in Russian

Phase 1: Create Tasks

  1. Ask user for feature name if not provided.
  2. Read work/{feature}/tech-spec.md. Check frontmatter status: approved. If not approved — tell user: "tech-spec не утверждён. Сначала запусти /new-tech-spec и доведи до approved." Stop.
  3. Read work/{feature}/user-spec.md.
  4. Note the task template path: ~/.claude/shared/work-templates/tasks/task.md.template
  5. Read skills/reviewers catalog from skills-and-reviewers.md — for passing correct skills/reviewers to task-creators.
  6. For each task in Implementation Tasks — launch task-creator subagent in parallel. Pass each task-creator:
    • feature_path, task_number, task_name
    • template_path: ~/.claude/shared/work-templates/tasks/task.md.template
    • files_to_modify, files_to_read (from tech-spec)
    • depends_on, wave, skills, reviewers, verify (from tech-spec)
    • teammate_name (if specified in tech-spec, optional) Each task-creator copies the template to tasks/{N}.md first, then edits each section in place. This ensures no sections are skipped.
  7. Confirm each task-creator returned a file path. Skip reading task content — preserve context budget for validation phase.
  8. Git commit: draft(tasks): create {N} tasks from tech-spec for {feature}

Checkpoint:

  • All tasks/*.md files created
  • Each task-creator returned file path
  • Draft committed

Phase 2: Validation (up to 3 iterations)

Tech-spec was already validated by 6 validators. This phase checks only: (1) task-creator correctly expanded tasks by template, (2) no mismatches with real code appeared during detailing.

Validators

Launch both in parallel:

task-validator (sonnet) — Template Compliance + AC/TDD carry-forward:

  • Batch: 5 tasks per call
  • Pass: feature_path, task_numbers array, batch_number, iteration
  • Report: logs/tasks/template-batch{N}-review.json

reality-checker (sonnet) — Reality & Adequacy:

  • Batch: 3 tasks per call
  • Pass: feature_path, task_numbers array, batch_number, iteration
  • Report: logs/tasks/reality-batch{N}-review.json

Process

  1. Launch both validators in parallel (task-validator in batches of 5, reality-checker in batches of 3).
  2. Read JSON reports, collect findings.
  3. If issues found — for each task with issues, launch task-creator in fix mode:
    • Pass: same inputs as creation + mode: fix + findings from validators
    • task-creator reads existing task, applies fixes, overwrites file
  4. After each validation round, git commit: chore(tasks): validation round {N} — {summary}
  5. Re-validate fixed tasks (repeat 1-4). Maximum 3 iterations.
  6. If problems remain after 3rd iteration — show user: "Вот что осталось — давай решим вместе."

Cross-Task Integration Check

After individual validation passes, run a final cross-task check:

  1. Launch both validators on ALL tasks in a single batch (not split into smaller batches):
    • task-validator — focus: shared resource ownership (one owner, consumers depend_on owner), no competing instances in same wave
    • reality-checker — focus: duplicate heavy resource init, hidden dependencies, inconsistent approaches across tasks
  2. If issues found → launch task-creator in fix mode for affected tasks. Re-validate fixed tasks.
  3. Max 2 iterations for cross-task check (on top of the 3 individual iterations).

Checkpoint:

  • Both validators: status=approved OR user resolved remaining issues
  • Cross-task integration check: no cross-task conflicts

Phase 3: Present to User

  1. Summary: task count, waves, dependencies, validation results (iterations, issues found/fixed).
  2. Wait for user approval.
  3. Git commit: chore(tasks): task decomposition approved for {feature}
  4. Suggest next step: /do-task for individual tasks.

Checkpoint:

  • Summary presented to user
  • User approved task decomposition
  • Approval committed

Final Check

  • All phases completed (tasks created, validation passed)
  • All tasks match template (frontmatter: status, depends_on, wave, skills, reviewers, teammate_name)
  • Validation: both validators passed or user confirmed remaining issues

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.