You have a product mission + docs and need a clear task breakdown
Starting implementation of a new feature
Need to estimate effort and dependencies
Instructions
Extract acceptance criteria and constraints from discovery phase
Create tasks (T1..TN) with:
User story + criteria: What the user should be able to do
Files to create/modify: Specific paths
Tests to add/run: Test file locations and descriptions
Dependencies: Which tasks depend on others
Keep tasks small and parallelizable:
Each task should be completable in one session
Minimize dependencies between tasks
Group related changes together
Task Format
## Task T1: [Title]
### User Story
As a [user], I want to [action], so that [benefit].
### Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
### Files
- CREATE: `src/module.py`
- MODIFY: `src/existing.py`
### Tests
- `tests/test_module.py::test_feature`
### Dependencies
- None (can start immediately)
Planning Checklist
All acceptance criteria covered by tasks
Each task has clear file scope
Each task has defined tests
Dependencies are documented
Tasks are small enough for one session
1---2name: plan-443description: Plan4---56# Plan78## When to use910- You have a product mission + docs and need a clear task breakdown11- Starting implementation of a new feature12- Need to estimate effort and dependencies1314## Instructions15161. Extract acceptance criteria and constraints from discovery phase17182. Create tasks (T1..TN) with:19 - **User story + criteria**: What the user should be able to do20 - **Files to create/modify**: Specific paths21 - **Tests to add/run**: Test file locations and descriptions22 - **Dependencies**: Which tasks depend on others23243. Keep tasks small and parallelizable:25 - Each task should be completable in one session26 - Minimize dependencies between tasks27 - Group related changes together2829## Task Format3031```markdown32## Task T1: [Title]3334### User Story35As a [user], I want to [action], so that [benefit].3637### Acceptance Criteria38- [ ] Criterion 139- [ ] Criterion 24041### Files42- CREATE: `src/module.py`43- MODIFY: `src/existing.py`4445### Tests46- `tests/test_module.py::test_feature`4748### Dependencies49- None (can start immediately)50```5152## Planning Checklist5354- [ ] All acceptance criteria covered by tasks55- [ ] Each task has clear file scope56- [ ] Each task has defined tests57- [ ] Dependencies are documented58- [ ] Tasks are small enough for one session
Run npx skillmds@latest add majiayu000/plan-44 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.
Plan It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. 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.
majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.