Planner

Create structured plans for multi-task projects that can be used by the task-orchestrator skill.

How to use it

Claude Code
  1. Run the line below. It pulls the whole folder into ~/.claude/skills/planner, including the files SKILL.md points to.
  2. Describe your job in plain words. Claude Code follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit jdrhyne/agent-skills/skills/planner#main ~/.claude/skills/planner

For one project only, change the path to .claude/skills/planner. This skill also uses parallel-task.md, my-plan.md, plan.md — copying SKILL.md alone won't be enough. See the folder on GitHub.

Claude (web or desktop app)
  1. On this page open ⋯ → Download .md.
  2. Save it as SKILL.md in a folder, zip the folder, then Customize → Skills → + → Create skill → Upload a skill.
  3. Pick the file and Save. Claude shows the name and description and runs a security scan.
  4. Check the skill is switched on.
  5. Start a new chat and describe your job in plain words. The AI follows the skill from there.
ChatGPT or another app
  1. ChatGPT: make a Project and paste it into Instructions.
  2. Neither? Paste it at the top of a new chat — it works for that chat.
Not working?
  • Check which app you pasted it into — the steps above name the right one.
  • Some skills need the paid tier of Claude or ChatGPT.
Step-by-step guide with screenshots · Ask in the forum

Paste into Claude, ChatGPT or Cursor.

Source of Planner

Show the full text135 lines
namedescriptionmetadatapermissions
plannerCreate structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.{"clawdbot":{"emoji":"📋"}} - file_write: "May save the completed plan to a file when the user asks for a persisted artifact.

Planner

Create structured, orchestrator-ready plans for multi-task projects.

Source: Adapted from am-will's codex-skills workflow patterns Pairs with: task-orchestrator skill for follow-on implementation


Quick Start

Follow this process:

  1. Phase 0: Clarify requirements (ask up to 5 targeted questions)
  2. Phase 1: Research & understand the codebase
  3. Phase 2: Create detailed plan with sprints, tasks, acceptance criteria
  4. Phase 3: Subagent review of the plan
  5. Phase 4: Return the plan in markdown and save a file only if the user asked for a persisted artifact

Key Principles

Task Atomicity

Each task must be:

  • Atomic and committable — small, independent pieces of work
  • Specific and actionable — not vague
  • Testable — include tests or validation method
  • Located — include file paths and code locations
Bad vs Good Task Breakdown

❌ Bad: "Implement third-party sign-in"

✓ Good:

  • "Add sign-in config to environment variables"
  • "Install and configure the required authentication package"
  • "Create sign-in callback route handler in src/routes/auth.ts"
  • "Add the sign-in button to the login UI"
Sprint Structure

Each sprint must:

  • Result in a demoable, runnable, testable increment
  • Build on prior sprint work
  • Include clear demo/verification checklist

Plan Template

# Plan: [Task Name]

**Generated**: [Date]
**Estimated Complexity**: [Low/Medium/High]

## Overview
[Brief summary of what needs to be done and the general approach]

## Prerequisites
- [Dependencies or requirements that must be met first]
- [Tools, libraries, or access needed]
- [Tooling limitations, e.g., browser relay/CDP restrictions]

## Sprint 1: [Sprint Name]
**Goal**: [What this sprint accomplishes]
**Demo/Validation**:
- [How to run/demo this sprint's output]
- [What to verify]

### Task 1.1: [Task Name]
- **Location**: [File paths or components involved]
- **Description**: [What needs to be done]
- **Perceived Complexity**: [1-10]
- **Dependencies**: [Any previous tasks this depends on]
- **Acceptance Criteria**:
  - [Specific, testable criteria]
- **Validation**:
  - [Test(s) or alternate validation steps]

### Task 1.2: [Task Name]
[...]

## Sprint 2: [Sprint Name]
[...]

## Testing Strategy
- [How to test the implementation]
- [What to verify at each sprint]

## Potential Risks
- [Things that could go wrong]
- [Mitigation strategies]

## Rollback Plan
- [How to undo changes if needed]

Hand-off

Once plan is ready, hand off to the parallel-task worker:

Please run parallel-task.md against my-plan.md

Or invoke directly:

"Run all unblocked tasks in plan.md using parallel subagents. Keep looping until all tasks are complete."

Safety Boundaries

  • Do not save a plan file unless the user asked for one or the surrounding workflow explicitly needs a persisted artifact.
  • Do not assign overlapping write scopes to parallel tasks without calling out the conflict.
  • Do not invent dependencies, validation steps, or completion status that the repo context does not support.
  • Do not turn a planning request into implementation work unless the user explicitly asks to move from planning to implementation.

  • parallel-task — Parallel task worker that executes the plan this skill produces

Adapted from am-will's codex-skills planner/parallel-task prompts.

1---
2name: planner
3description: Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.
4metadata: {"clawdbot":{"emoji":"📋"}}
5permissions:
6 - file_write: "May save the completed plan to a file when the user asks for a persisted artifact."
7---
8 
9# Planner
10 
11Create structured, orchestrator-ready plans for multi-task projects.
12 
13**Source**: Adapted from am-will's codex-skills workflow patterns
14**Pairs with**: task-orchestrator skill for follow-on implementation
15 
16---
17 
18## Quick Start
19 
20Follow this process:
21 
221. **Phase 0**: Clarify requirements (ask up to 5 targeted questions)
232. **Phase 1**: Research & understand the codebase
243. **Phase 2**: Create detailed plan with sprints, tasks, acceptance criteria
254. **Phase 3**: Subagent review of the plan
265. **Phase 4**: Return the plan in markdown and save a file only if the user asked for a persisted artifact
27 
28---
29 
30## Key Principles
31 
32### Task Atomicity
33Each task must be:
34- **Atomic and committable** — small, independent pieces of work
35- **Specific and actionable** — not vague
36- **Testable** — include tests or validation method
37- **Located** — include file paths and code locations
38 
39### Bad vs Good Task Breakdown
40 
41❌ Bad: "Implement third-party sign-in"
42 
43✓ Good:
44- "Add sign-in config to environment variables"
45- "Install and configure the required authentication package"
46- "Create sign-in callback route handler in src/routes/auth.ts"
47- "Add the sign-in button to the login UI"
48 
49### Sprint Structure
50 
51Each sprint must:
52- Result in a **demoable, runnable, testable** increment
53- Build on prior sprint work
54- Include clear demo/verification checklist
55 
56---
57 
58## Plan Template
59 
60```markdown
61# Plan: [Task Name]
62 
63**Generated**: [Date]
64**Estimated Complexity**: [Low/Medium/High]
65 
66## Overview
67[Brief summary of what needs to be done and the general approach]
68 
69## Prerequisites
70- [Dependencies or requirements that must be met first]
71- [Tools, libraries, or access needed]
72- [Tooling limitations, e.g., browser relay/CDP restrictions]
73 
74## Sprint 1: [Sprint Name]
75**Goal**: [What this sprint accomplishes]
76**Demo/Validation**:
77- [How to run/demo this sprint's output]
78- [What to verify]
79 
80### Task 1.1: [Task Name]
81- **Location**: [File paths or components involved]
82- **Description**: [What needs to be done]
83- **Perceived Complexity**: [1-10]
84- **Dependencies**: [Any previous tasks this depends on]
85- **Acceptance Criteria**:
86 - [Specific, testable criteria]
87- **Validation**:
88 - [Test(s) or alternate validation steps]
89 
90### Task 1.2: [Task Name]
91[...]
92 
93## Sprint 2: [Sprint Name]
94[...]
95 
96## Testing Strategy
97- [How to test the implementation]
98- [What to verify at each sprint]
99 
100## Potential Risks
101- [Things that could go wrong]
102- [Mitigation strategies]
103 
104## Rollback Plan
105- [How to undo changes if needed]
106```
107 
108---
109 
110## Hand-off
111 
112Once plan is ready, hand off to the **parallel-task worker**:
113 
114```
115Please run parallel-task.md against my-plan.md
116```
117 
118Or invoke directly:
119> "Run all unblocked tasks in plan.md using parallel subagents. Keep looping until all tasks are complete."
120 
121## Safety Boundaries
122 
123- Do not save a plan file unless the user asked for one or the surrounding workflow explicitly needs a persisted artifact.
124- Do not assign overlapping write scopes to parallel tasks without calling out the conflict.
125- Do not invent dependencies, validation steps, or completion status that the repo context does not support.
126- Do not turn a planning request into implementation work unless the user explicitly asks to move from planning to implementation.
127 
128---
129 
130## Related
131 
132- [`parallel-task`](../parallel-task/) — Parallel task worker that executes the plan this skill produces
133 
134Adapted from am-will's codex-skills planner/parallel-task prompts.
135 

Discussion