Agent skill

planning

Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task requires more than 5 tool calls and needs structured phase tracking to stay focused and avoid goal drift.

Stars 23,776
Forks 2,298

Install this agent skill to your Project

npx add-skill https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-maestro/planning

SKILL.md

AI Maestro Planning

Solve the execution problem -- staying focused during complex, multi-step tasks. Uses persistent markdown files to track goals, findings, and progress so you never lose context. Part of the AI Maestro suite.

When to Use

  • Multi-step tasks (3+ steps)
  • Research projects
  • Building features requiring >5 tool calls
  • Any task where you might lose track of the goal

The 3-File Pattern

Create in docs_dev/ (or $AIMAESTRO_PLANNING_DIR):

File Purpose Update When
task_plan.md Goals, phases, decisions, errors After each phase
findings.md Research, discoveries, resources During research
progress.md Session log, test results Throughout session

Quick Start

bash
PLAN_DIR="${AIMAESTRO_PLANNING_DIR:-docs_dev}"
mkdir -p "$PLAN_DIR"

Then create task_plan.md with:

markdown
# Task: [Goal]

## Phases
- [ ] Phase 1: Research
- [ ] Phase 2: Design
- [ ] Phase 3: Implement
- [ ] Phase 4: Test

## Decisions
| Decision | Rationale | Date |
|----------|-----------|------|

## Errors Encountered
| Error | Attempt | Resolution |
|-------|---------|------------|

The 6 Rules

  1. Create plan first -- Never start complex work without task_plan.md
  2. Read before decide -- Re-read the plan before any major decision
  3. Update after act -- Mark phases complete, log what changed
  4. 2-action rule -- After every 2 search/browse operations, save findings to findings.md
  5. Log all errors -- Every error goes in the plan with attempt number and resolution
  6. Never repeat failures -- If an action failed, change your approach

The 3-Strike Protocol

Strike Action
1 Diagnose root cause, apply targeted fix
2 Try a different approach entirely
3 Question assumptions, search for similar issues
After 3 Escalate to user with all attempts documented

The 5-Question Reboot

Lost? Answer these from your planning files:

  1. Where am I? (current phase in task_plan.md)
  2. Where am I going? (remaining phases)
  3. What's the goal? (goal section)
  4. What have I learned? (findings.md)
  5. What have I done? (progress.md)

Full AI Maestro Experience

This skill works standalone with no dependencies. For the complete experience including memory search, docs search, graph query, agent messaging, and agent management, install the full AI Maestro platform.

Expand your agent's capabilities with these related and highly-rated skills.

davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore
davila7/claude-code-templates

behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results