changelog-observer
Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
@claude-worldInstall SkillDevelopment
Skill
/plan
Break a complex task into an ordered, dependency-aware task list with estimates and verification steps. Use when a request spans multiple components or days, before starting large features, or when the user runs /plan.
Claude Code
$ npx -y skills add claude-world/director-mode-lite --skill plan --agent claude-code
Codex
$ npx skills add claude-world/director-mode-lite --skill plan -a codex -y
Cursor
$ npx skills add claude-world/director-mode-lite --skill plan -a cursor -y
Gemini CLI
$ npx skills add claude-world/director-mode-lite --skill plan -a gemini-cli -y
GitHub Copilot
$ npx skills add claude-world/director-mode-lite --skill plan -a github-copilot -y
OpenCode
$ npx skills add claude-world/director-mode-lite --skill plan -a opencode -y
Windsurf
$ npx skills add claude-world/director-mode-lite --skill plan -a windsurf -y
SKILL.md
plan.SKILL.mdname: plan
description: Break a complex task into an ordered, dependency-aware task list with estimates and verification steps. Use when a request spans multiple components or days, before starting large features, or when the user runs /plan.
user-invocable: true
Task Planning
Create a detailed execution plan for the current task.
Process
1. **Analyze Requirements**
- What is the goal?
- What are the constraints?
- What resources are available?
2. **Break Down Tasks**
- Decompose into specific, actionable steps
- Each task should be completable independently
- Estimate relative complexity (small/medium/large)
3. **Create Task List**
- Track progress in the plan's checklist (use a task tool such as
TodoWrite only when the active CLI and model offer it)
- Mark priorities and dependencies
- Keep tasks granular
4. **Identify Risks**
- What could go wrong?
- What are the unknowns?
- What needs clarification?
---
Task Template
## Task: [Task Name]
### Goal
[What this task achieves]
### Steps
1. [ ] [Step 1]
2. [ ] [Step 2]
3. [ ] [Step 3]
### Dependencies
- Requires: [other tasks]
- Blocks: [dependent tasks]
### Acceptance Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]
---
Guidelines
- Keep tasks small (completable in one session)
- Be specific about acceptance criteria
- Identify dependencies early
- Update plan as you learn more
Read more
name: plan description: Break a complex task into an ordered, dependency-aware task list with estimates and verification steps. Use when a request spans multiple components or days, before starting large features, or when the user runs /plan. user-invocable: true
Task Planning
Create a detailed execution plan for the current task.
Process
1. **Analyze Requirements**
- What is the goal?
- What are the constraints?
- What resources are available?
2. **Break Down Tasks**
- Decompose into specific, actionable steps
- Each task should be completable independently
- Estimate relative complexity (small/medium/large)
3. **Create Task List**
- Track progress in the plan's checklist (use a task tool such as
TodoWrite only when the active CLI and model offer it)
- Mark priorities and dependencies
- Keep tasks granular
4. **Identify Risks**
- What could go wrong?
- What are the unknowns?
- What needs clarification?
---
Task Template
## Task: [Task Name] ### Goal [What this task achieves] ### Steps 1. [ ] [Step 1] 2. [ ] [Step 2] 3. [ ] [Step 3] ### Dependencies - Requires: [other tasks] - Blocks: [dependent tasks] ### Acceptance Criteria - [ ] [Criterion 1] - [ ] [Criterion 2]
---
Guidelines
- Keep tasks small (completable in one session)
- Be specific about acceptance criteria
- Identify dependencies early
- Update plan as you learn more
Ships withdirector-mode-lite
Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.
8036 skills14 agents
Stars on GitHub
Momentum
- stars in total
- 80
Other skills on director-mode-lite.
@claude-worldInstall Skillagent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when…
@claude-worldInstall Skillagent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct…
@claude-worldInstall Skillagents
List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
@claude-worldInstall Skillauto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog
@claude-worldInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about plan.
- Which coding agents can use plan?
- plan installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.