Tasks New
Productivitytasks-newTasks New is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Derives or refines tasklist items from PRD, plan, and spec artifacts. Use when tasklist stage prepares implementation-ready work items.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/planning/tasks-new/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/tasks-new, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Follow feature-dev-aidd:aidd-core.
Steps
- Inputs: resolve active feature and verify PRD/plan/spec artifacts needed for tasklist generation.
- Preflight: set active stage
tasklistand active feature. - Orchestration: run
python3 ${CLAUDE_PLUGIN_ROOT}/skills/tasks-new/runtime/tasks_new.py --ticket <ticket>, then gate PRD readiness withpython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/prd_check.py. - Use the existing rolling context pack as input evidence; do not invoke standalone context-pack builder scripts from this stage.
- Run subagent
feature-dev-aidd:tasklist-refiner(internal orchestration role). First action: read the rolling context pack. - Postflight: validate via
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/tasklist_check.pyand updateaidd/docs/tasklist/<ticket>.mdwhen needed. - Output: return the output contract and explicit next step
/feature-dev-aidd:implement <ticket>.
Command contracts
python3 ${CLAUDE_PLUGIN_ROOT}/skills/tasks-new/runtime/tasks_new.py
- When to run: as canonical tasklist stage entrypoint before implement phase.
- Inputs:
--ticket <ticket>and current PRD/plan/spec artifacts. - Outputs: normalized tasklist structure and stage readiness signal.
- Failure mode: non-zero exit when required artifacts are missing or tasklist contract checks fail.
- Next action: fix source artifacts/tasklist issues and rerun tasklist orchestration.
Notes
- Planning stage:
AIDD:ACTIONS_LOG: n/a.
Additional resources
- Tasklist template source: templates/tasklist.template.md (when: generating or normalizing tasklist sections; why: keep iteration/handoff structure aligned with canonical template).