plan-feature
Break a feature into implementation tasks with milestone and Eisenhower classification
Best use case
plan-feature is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Break a feature into implementation tasks with milestone and Eisenhower classification
Teams using plan-feature should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/plan-feature/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How plan-feature Compares
| Feature / Agent | plan-feature | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Break a feature into implementation tasks with milestone and Eisenhower classification
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
Plan the following feature: $ARGUMENTS 1. Read `mission-control/data/ai-context.md` for a quick snapshot of current state 2. Read the relevant project's CLAUDE.md and codebase structure 3. Read `mission-control/data/goals.json` to understand which goal this supports 4. Break the feature into implementation tasks (5-15 tasks) 5. For each task, determine importance and urgency 6. Create a new milestone in `goals.json` linked to the appropriate goal 7. Add all tasks to `tasks.json` with: - Proper importance/urgency classification - kanban: `"not-started"` - Link to the new milestone and project - Appropriate `assignedTo` agent role - 2-4 daily actions per task 8. Present the plan as a summary before saving 9. After saving, run `pnpm gen:context` in `mission-control/` to update the AI context Ask me clarifying questions before starting if the feature description is ambiguous.
Related Skills
ship-feature
Ship a feature by running verification, committing, and updating task status
daily-plan
Create a focused daily plan with top priorities, brain dump triage, and time blocks
task-management
Manages tasks in Mission Control. Use when creating, updating, or querying tasks, goals, projects, or brain dump entries. Applies when the user mentions tasks, priorities, to-dos, planning, or asks about what needs to be done.
eisenhower-triage
Applies Eisenhower matrix logic to prioritize work. Use when the user asks about priorities, what to work on next, or when triaging tasks and brain dump items.
agentic-company
Context about running a fully agentic solo entrepreneur company. Use when the user discusses business strategy, agent delegation, team structure, or company operations. Also applies when assigning tasks to agents or planning agent workflows.
weekly-review
Conduct a weekly review with accomplishments, goal progress, and recommendations
standup
Generate daily standup summary with in-progress tasks, git activity, and goal progress
researcher
Activate the researcher agent persona for thorough topic investigation
research
Research a topic thoroughly and save structured findings to research/
marketer
Activate the marketer agent persona for growth marketing and content tasks
business-analyst
Activate the business analyst agent persona for strategy and planning tasks
brainstorm
Generate creative ideas on a topic and optionally save to brain dump