Delegate independent tasks to specialized agents working concurrently with isolated context.
Repo Curriculum Planner
curriculum-planner
Generates sequences of high-leverage tasks that increase understanding and improve the code. Use when: - "what should I work on next?" - suggests prioritized tasks - "create a plan for this repo" - generates a curriculum - "what's the roadmap?" - shows curriculum overview - "help me onboard to th...
SKILL.md
Full skill instructions
Repo Curriculum Planner
Generates structured learning/improvement plans based on repo state and session brain.
Two Usage Modes
Mode 1: Propose in Chat (default)
When a user asks for planning help, propose tasks directly in the conversation without writing files. This is the default behavior for quick suggestions.
Examples:
- "what should I work on next?" → Suggest 2-3 high-priority tasks in chat
- "what's the roadmap?" → Describe the plan conversationally
- "help me prioritize" → Discuss tradeoffs and recommend order
Mode 2: Write Artifacts to Disk
Only write to .claude/voyager/ when the user explicitly asks to persist the plan:
- "write the curriculum to disk"
- "save this plan"
- "generate curriculum files"
- "materialize the plan"
This writes:
.claude/voyager/curriculum.json— structured task backlog.claude/voyager/curriculum.md— human-readable plan
Trigger Phrases
Use this skill when you hear:
- "what should I work on next?"
- "create a plan"
- "what's the roadmap?"
- "help me onboard"
- "plan the work"
- "prioritize features"
- "what tasks remain?"
- "make an onboarding plan"
- "roadmap this refactor"
On-Disk Plan Artifacts
When persisted, the plan lives at:
.claude/voyager/curriculum.json— structured JSON with full task details.claude/voyager/curriculum.md— rendered Markdown for human review
To refresh an existing plan, run:
voyager curriculum plan
To preview without saving:
voyager curriculum plan --dry-run
Task Structure
Each task includes:
id— unique identifier (e.g.,t01)title— short action-oriented titlewhy— rationale for the taskestimated_scope—trivial,small,medium, orlargeacceptance_criteria— how to know it's donesuggested_files— where to lookcommands_to_run— verification commandsdepends_on— prerequisite task IDsstatus—pending,in_progress,done, orblocked
Updating Task Status
Edit curriculum.json directly to update task status:
- Change
"status": "pending"to"in_progress"when starting - Change to
"done"when complete
See reference.md for implementation details and schema reference.
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
