task-planning
$
npx mdskill add gradion-ai/freeact/task-planningStructured workflow for planning and executing tasks when explicitly requested by the user.
SKILL.md
.github/skills/task-planningView on GitHub ↗
---
name: task-planning
description: Structured task planning workflow with user feedback loops. Use when the user explicitly requests planning (e.g., "make a plan", "plan first", "create a plan"). Covers creating plans with actionable steps, iterating based on feedback, saving confirmed plans, and executing step-by-step with progress tracking.
---
# Task Planning
Structured workflow for planning and executing tasks when explicitly requested by the user.
## Planning Phase
### 1. Create Initial Plan
Draft a plan with clear, actionable steps using markdown checklist format:
```markdown
- [ ] Step 1: Description
- [ ] Step 2: Description
- [ ] Step 3: Description
```
### 2. Request Feedback
Present the plan to the user and ask for feedback. Do not proceed until feedback is received.
### 3. Iterate Until Confirmed
Revise the plan based on user feedback. Continue the proposal-feedback loop until the user confirms.
### 4. Save Confirmed Plan
Write the confirmed plan to `{plans_rel_dir}/<task-name>.md` where:
- `<task-name>` is a descriptive kebab-case name
- Example: `{plans_rel_dir}/add-user-authentication.md`
- The `{plans_rel_dir}/` directory already exists
## Execution Phase
### 5. Execute Step-by-Step
Work through the plan sequentially:
- First unchecked item is the current task
- After completing each step, mark with checkmark: `- [x] Step description`
- Update the plan file to reflect progress
### 6. Revise as Needed
If execution reveals the need for plan adjustments:
- Update the plan file with revised steps
- Inform the user of significant changes
### 7. Request Feedback During Execution
If encountering uncertainty or needing user input during execution, ask for feedback before proceeding.
## Plan File Format
```markdown
# <Task Title>
## Steps
- [x] Completed step
- [ ] Pending step
- [ ] Another pending step
## Notes
Optional section for context, decisions made, or issues encountered.
```
More from gradion-ai/freeact
- freeact-interactionInteract with freeact agent via tmux for testing
- output-parsersGenerate output parsers for mcptools with unstructured return types. Use when a tool returns raw strings or Result models with single str fields and needs structured ParseResult output. Covers testing tools, identifying parseable structures, extending modules with ParseResult models, and creating parser implementations.
- saving-codeactsSave executed Python code as reusable tools in the gentools package. Use when preserving successful code executions for later reuse. Covers creating package structure (api.py, impl.py), defining Pydantic output models, and implementing the run() interface.