Manage and work through task lists with completion tracking and commit protocols.
When to use
After generating a task list
When working through implementation tasks systematically
When you need structured task-by-task execution
Task implementation rules
One sub-task at a time: Do NOT start the next sub-task until the user says "yes" or "y"
Completion protocol:
Finish sub-task, mark as completed ([x])
If all subtasks under a parent are [x]:
Run the full test suite
Only if tests pass: stage changes
Clean up temporary files and code
Commit with conventional commit format (feat:, fix:, refactor:, etc.)
Mark parent task as completed
Stop after each sub-task and wait for user's go-ahead
Task list maintenance
Mark tasks and subtasks as completed per protocol
Add new tasks as they emerge
Keep "Relevant Files" section accurate and up to date
For the full implementation protocol and maintenance rules, see references/process-task-list.md.
Follow the writing standards in _shared/writing-standards.md for all outputs.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: mjrtl-agentic-product-manager-process-tasks3description: Process Task List4---56# Process Task List78Manage and work through task lists with completion tracking and commit protocols.910## When to use1112- After generating a task list13- When working through implementation tasks systematically14- When you need structured task-by-task execution1516## Task implementation rules1718- **One sub-task at a time**: Do NOT start the next sub-task until the user says "yes" or "y"19- **Completion protocol**:20 1. Finish sub-task, mark as completed (`[x]`)21 2. If all subtasks under a parent are `[x]`:22 - Run the full test suite23 - Only if tests pass: stage changes24 - Clean up temporary files and code25 - Commit with conventional commit format (`feat:`, `fix:`, `refactor:`, etc.)26 3. Mark parent task as completed27- Stop after each sub-task and wait for user's go-ahead2829## Task list maintenance30311. Mark tasks and subtasks as completed per protocol322. Add new tasks as they emerge333. Keep "Relevant Files" section accurate and up to date3435For the full implementation protocol and maintenance rules, see `references/process-task-list.md`.3637Follow the writing standards in `_shared/writing-standards.md` for all outputs.3839---40> Converted and distributed by [TomeVault](https://tomevault.io/claim/mjrtl) — claim your Tome and manage your conversions.41<!-- tomevault:4.0:skill_md:2026-04-15 -->
Run npx skillmds@latest add tomevault-io/mjrtl-agentic-product-manager-process-tasks in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Process Task List It is listed under Productivity on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.