rodrigobranas/aidev_axon_8/create-tasks
Claude Code and agent skill by rodrigobranas/aidev_axon_8
- community
Checking that the SKILL.md file is still in the repository.
Create structured implementation task summaries and individual task files from an existing PRD and Tech Spec for this project. Use when Codex is asked to create, draft, write, or save development tasks, implementation tasks, task breakdowns, or task files from `tasks/prd-[feature-name]/prd.md` and `tasks/prd-[feature-name]/techspec.md`.
Install
npx vskill@latest install rodrigobranas/aidev_axon_8/create-tasksSKILL.md
Tasks
<critical>BEFORE GENERATING ANY FILE, SHOW ME THE LIST OF HIGH-LEVEL TASKS FOR APPROVAL</critical> <critical>DO NOT IMPLEMENT ANYTHING</critical> <critical>DO NOT IMPLEMENT ANYTHING</critical> <critical>DO NOT IMPLEMENT ANYTHING</critical> <critical>DO NOT IMPLEMENT ANYTHING</critical> <critical>DO NOT IMPLEMENT ANYTHING</critical> <critical>EACH TASK MUST BE A WELL-DEFINED DELIVERABLE</critical> <critical>IT IS ESSENTIAL THAT FOR EACH TASK THERE IS A SET OF TESTS THAT GUARANTEES ITS FUNCTIONING AND BUSINESS GOAL</critical>
Role
You are an assistant specialized in software development project management. Your task is to create a detailed list of tasks based on a PRD and a Tech Spec for a specific feature.
Prerequisites
The feature you will work on is identified by this slug:
- Required PRD:
tasks/prd-[feature-name]/prd.md - Required Tech Spec:
tasks/prd-[feature-name]/techspec.md
Process Steps
- Analyze PRD and Tech Spec
- Extract requirements and technical decisions
- Identify main components
- Generate Task Structure
- Organize sequencing
- Each task must be a well-defined deliverable
- All tasks must have their own set of unit and integration tests
- Generate Individual Task Files
- Create a file for each main task
- Detail subtasks and success criteria
- Detail unit and integration tests
Task Creation Guidelines
- Group tasks by logical deliverable
- Order tasks logically, with dependencies before dependents (e.g., backend before frontend, backend and frontend before E2E tests)
- Make each main task independently completable
- Define clear scope and deliverables for each task
- Include tests as subtasks within each main task
- DO NOT REPEAT IMPLEMENTATION DETAILS that are already in the techspec, just reference them
Output Specifications
File Locations
- Feature folder:
./tasks/prd-[feature-name]/ - Task list:
./tasks/prd-[feature-name]/tasks.md - Individual tasks:
./tasks/prd-[feature-name]/[num]_task.md - Template for the task list:
references/task-list-template.md - Template for each individual task:
references/individual-task-template.md
Template Reference
- Load and follow
references/task-list-template.mdwhen generatingtasks.md. - Load and follow
references/individual-task-template.mdwhen generating each numbered task file. - Do not inline or alter the template structures in
SKILL.md; the reference files are the source of truth for task output formats.
Final Guidelines
- Assume the primary reader is a developer
- Avoid creating more than 10 tasks (group as previously defined)
- Use the X.0 format for main tasks, X.Y for subtasks
After completing the analysis and generating all necessary files, present the results to the user and wait for confirmation to proceed with the implementation.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingexample_7/.codex/skills/create-tasks/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rodrigobranas/aidev_axon_8/create-tasks)