agentleFS
ChristopherAlphonseChristopherAlphonse/calphonse-skills/task-generation-mode/SKILL.md

task-generation-mode

Skill1 starsChanged 10 days agoMITView on GitHub

Generates tasks by analyzing the PRD and breaking it into actionable work items.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer the smallest task breakdown that can deliver the PRD.

    line 19
  2. Distinctive:

    Every task should have a verifiable outcome: a test, command, review step, or observable behavior.

    line 20
  3. Very specific:

    Use /lets-talk-about-it before finalizing the task list.

    line 27
  4. Distinctive:

    Analyze PRD: Read functional requirements, user stories, and technical constraints.

    line 35
  5. Very specific:

    Context: Use codebase and usages to ensure task descriptions align with existing patterns in the repository.

    line 63

≈ “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

Context

  • Current branch: git branch --show-current
  • Current git status: git status --short
  • Project AGENTS.md: cat AGENTS.md 2>/dev/null | head -50

Description: Assistant instructions for converting a Product Requirements Document (PRD) into a structured, actionable implementation task list for developers.


Guardrails

  • Convert ambiguity into explicit assumptions, open questions, or user checkpoints.
  • Prefer the smallest task breakdown that can deliver the PRD. Do not add speculative features, abstractions, or future-proofing.
  • Every task should have a verifiable outcome: a test, command, review step, or observable behavior.
  • Mark out-of-scope work explicitly instead of silently including it.

Required Companion Skill

Use /lets-talk-about-it before finalizing the task list. Let it stress-test the PRD, assumptions, dependencies, sequencing, risks, and implementation boundaries one question at a time. Incorporate the resulting assumptions, decisions, risks, and unresolved issues into parent tasks, sub-tasks, Relevant Files, Notes, and checkpoint prompts.


The Two-Phase Process

Phase 1: Parent Tasks (High-Level)

  1. Analyze PRD: Read functional requirements, user stories, and technical constraints.
  2. Generate Roadmap: Identify the fewest high-level parent tasks that cover the PRD, usually 3-6.
  3. Checkpoint: Present these parent tasks to the user and wait for approval.
  • Required Message: "I have generated the high-level tasks based on the PRD. Ready to generate the sub-tasks? Respond with 'Go' to proceed."

Phase 2: Sub-Tasks & Finalization

  1. Breakdown: Once "Go" is received, expand each parent task into granular, actionable sub-tasks.
  2. Mapping: Identify all files to be created or modified, including unit tests.
  3. Documentation: Compile the final Markdown file.

Output Specification

  • Format: Markdown (.md)
  • Path: .planning/tasks/tasks-[prd-file-name].md
  • Structure:
    • Task List: Hierarchical checkboxes (- [ ] 1.0 ..., - [ ] 1.1 ...).
    • Relevant Files: Potential code and test files involved.
    • Notes: Testing commands and architectural reminders tied to the PRD.

Developer Guidelines

  • Test Placement: Unit tests must be co-located with their respective source files (e.g., feature.ts and feature.test.ts).
  • Context: Use codebase and usages to ensure task descriptions align with existing patterns in the repository.

Example Task Entry

- [ ] 1.0 Data Model Implementation
  - [ ] 1.1 Define Zod schema for [Entity]
  - [ ] 1.2 Create Prisma migration for [Table Name]
  - [ ] 1.3 Implement repository pattern for CRUD operations

Ask the user whether each task or subtask should be committed to git, and keep the work sequential.


Install: npx skills add ChristopherAlphonse/calphonse-skills --skill task-generation-mode

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.