output-parsers
Generate output parsers for mcptools with unstructured return types. Use when a tool returns raw strings or Result models with…
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
$ npx -y skills add gradion-ai/freeact --skill task-planning --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/task-planningContext preview
The summary Claude sees to decide when to auto-load this skill.
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
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.
Structured workflow for planning and executing tasks when explicitly requested by the user.
Draft a plan with clear, actionable steps using markdown checklist format:
- [ ] Step 1: Description - [ ] Step 2: Description - [ ] Step 3: Description
Present the plan to the user and ask for feedback. Do not proceed until feedback is received.
Revise the plan based on user feedback. Continue the proposal-feedback loop until the user confirms.
Write the confirmed plan to `{plans_rel_dir}/<task-name>.md` where:
Work through the plan sequentially:
If execution reveals the need for plan adjustments:
If encountering uncertainty or needing user input during execution, ask for feedback before proceeding.
# <Task Title> ## Steps - [x] Completed step - [ ] Pending step - [ ] Another pending step ## Notes Optional section for context, decisions made, or issues encountered.
General-purpose AI agent that acts via code actions through a unified execution interface.
Generate output parsers for mcptools with unstructured return types. Use when a tool returns raw strings or Result models with…
Save executed Python code as reusable tools in the gentools package. Use when preserving successful code executions for later…